diff --git a/.agents/skills/skills_claude/SKILL.md b/.agents/skills/skills_claude/SKILL.md
new file mode 100644
index 000000000..3640d6a4a
--- /dev/null
+++ b/.agents/skills/skills_claude/SKILL.md
@@ -0,0 +1,338 @@
+---
+name: skills-claude-conventions
+description: Development conventions and patterns for skills_claude. Python project with mixed commits.
+---
+
+# Skills Claude Conventions
+
+> Generated from [Eaprime1/skills_claude](https://github.com/Eaprime1/skills_claude) on 2026-03-24
+
+## Overview
+
+This skill teaches Claude the development patterns and conventions used in skills_claude.
+
+## Tech Stack
+
+- **Primary Language**: Python
+- **Architecture**: hybrid module organization
+- **Test Location**: separate
+
+## When to Use This Skill
+
+Activate this skill when:
+- Making changes to this repository
+- Adding new features following established patterns
+- Writing tests that match project conventions
+- Creating commits with proper message format
+
+## Commit Conventions
+
+Follow these commit message conventions based on 42 analyzed commits.
+
+### Commit Style: Mixed Style
+
+### Prefixes Used
+
+- `feat`
+- `chore`
+
+### Message Guidelines
+
+- Average message length: ~56 characters
+- Keep first line concise and descriptive
+- Use imperative mood ("Add feature" not "Added feature")
+
+
+*Commit message example*
+
+```text
+feat: add skills_claude ECC bundle (.claude/commands/update-or-export-example-skills.md)
+```
+
+*Commit message example*
+
+```text
+chore: update claude-api skill [auto-sync] (#729)
+```
+
+*Commit message example*
+
+```text
+Merge branch 'anthropics:main' into claude/skills-brainstorm-Nd4vz
+```
+
+*Commit message example*
+
+```text
+Merge pull request #2 from Eaprime1/ecc-tools/skills_claude-1774393541560
+```
+
+*Commit message example*
+
+```text
+feat: add skills_claude ECC bundle (.claude/commands/add-new-skill.md)
+```
+
+*Commit message example*
+
+```text
+feat: add skills_claude ECC bundle (.claude/commands/feature-development.md)
+```
+
+*Commit message example*
+
+```text
+feat: add skills_claude ECC bundle (.codex/agents/docs-researcher.toml)
+```
+
+*Commit message example*
+
+```text
+feat: add skills_claude ECC bundle (.codex/agents/reviewer.toml)
+```
+
+## Architecture
+
+### Project Structure: Single Package
+
+This project uses **hybrid** module organization.
+
+### Guidelines
+
+- This project uses a hybrid organization
+- Follow existing patterns when adding new code
+
+## Code Style
+
+### Language: Python
+
+### Naming Conventions
+
+| Element | Convention |
+|---------|------------|
+| Files | kebab-case |
+| Functions | camelCase |
+| Classes | PascalCase |
+| Constants | SCREAMING_SNAKE_CASE |
+
+### Import Style: Relative Imports
+
+### Export Style: Named Exports
+
+
+*Preferred import style*
+
+```typescript
+// Use relative imports
+import { Button } from '../components/Button'
+import { useAuth } from './hooks/useAuth'
+```
+
+*Preferred export style*
+
+```typescript
+// Use named exports
+export function calculateTotal() { ... }
+export const TAX_RATE = 0.1
+export interface Order { ... }
+```
+
+## Common Workflows
+
+These workflows were detected from analyzing commit patterns.
+
+### Feature Development
+
+Standard feature implementation workflow
+
+**Frequency**: ~19 times per month
+
+**Steps**:
+1. Add feature implementation
+2. Add tests for feature
+3. Update documentation
+
+**Files typically involved**:
+- `**/*.test.*`
+- `**/api/**`
+
+**Example commit sequence**:
+```
+Add 3rd Party notices (#4)
+Add initial Agent Skills Spec (#2)
+Small tweak to blog link (#7)
+```
+
+### Refactoring
+
+Code refactoring and cleanup workflow
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Ensure tests pass before refactor
+2. Refactor code structure
+3. Verify tests still pass
+
+**Files typically involved**:
+- `src/**/*`
+
+**Example commit sequence**:
+```
+Reorganize the example skills (#1)
+Adding more details to README (#3)
+Add 3rd Party notices (#4)
+```
+
+### Add Or Update Skill
+
+Adds a new skill or updates an existing skill, including its SKILL.md and related scripts/assets.
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Create or update SKILL.md in skills/<skill-name>/
+2. Add or update supporting scripts, templates, or assets in the skill's folder
+3. If applicable, update marketplace or index files (e.g., .claude-plugin/marketplace.json)
+4. Optionally, add language-specific guides or reference files
+
+**Files typically involved**:
+- `skills/*/SKILL.md`
+- `skills/*/scripts/*.py`
+- `skills/*/templates/*`
+- `skills/*/reference/*`
+- `.claude-plugin/marketplace.json`
+
+**Example commit sequence**:
+```
+Create or update SKILL.md in skills/<skill-name>/
+Add or update supporting scripts, templates, or assets in the skill's folder
+If applicable, update marketplace or index files (e.g., .claude-plugin/marketplace.json)
+Optionally, add language-specific guides or reference files
+```
+
+### Export Or Bundle Skills
+
+Exports multiple skills as distributable bundles or updates the exported set of skills.
+
+**Frequency**: ~1 times per month
+
+**Steps**:
+1. Aggregate or update SKILL.md and related files for all relevant skills
+2. Generate distributable bundles (e.g., .skill files in dist/)
+3. Update index/marketplace files if needed
+
+**Files typically involved**:
+- `dist/*.skill`
+- `skills/*/SKILL.md`
+- `.claude-plugin/marketplace.json`
+
+**Example commit sequence**:
+```
+Aggregate or update SKILL.md and related files for all relevant skills
+Generate distributable bundles (e.g., .skill files in dist/)
+Update index/marketplace files if needed
+```
+
+### Office Skill Shared Module Update
+
+Updates or reorganizes shared Office document processing modules (docx, pptx, xlsx) and their schemas/scripts.
+
+**Frequency**: ~1 times per month
+
+**Steps**:
+1. Update or reorganize scripts in skills/{docx,pptx,xlsx}/scripts/office/
+2. Update or add schemas in skills/{docx,pptx,xlsx}/scripts/office/schemas/
+3. Update pack/unpack/validate scripts for each Office skill
+4. Optionally, update SKILL.md or documentation for each skill
+
+**Files typically involved**:
+- `skills/docx/scripts/office/**/*`
+- `skills/pptx/scripts/office/**/*`
+- `skills/xlsx/scripts/office/**/*`
+- `skills/docx/scripts/office/schemas/**/*`
+- `skills/pptx/scripts/office/schemas/**/*`
+- `skills/xlsx/scripts/office/schemas/**/*`
+- `skills/docx/scripts/office/pack.py`
+- `skills/pptx/scripts/office/pack.py`
+- `skills/xlsx/scripts/office/pack.py`
+- `skills/docx/SKILL.md`
+- `skills/pptx/SKILL.md`
+- `skills/xlsx/SKILL.md`
+
+**Example commit sequence**:
+```
+Update or reorganize scripts in skills/{docx,pptx,xlsx}/scripts/office/
+Update or add schemas in skills/{docx,pptx,xlsx}/scripts/office/schemas/
+Update pack/unpack/validate scripts for each Office skill
+Optionally, update SKILL.md or documentation for each skill
+```
+
+### Skill Creator Tooling Update
+
+Updates scripts, references, or documentation in the skill-creator tool, including validation, packaging, and optimization scripts.
+
+**Frequency**: ~1 times per month
+
+**Steps**:
+1. Update or add scripts in skills/skill-creator/scripts/
+2. Update references or documentation in skills/skill-creator/references/
+3. Update SKILL.md for skill-creator if needed
+
+**Files typically involved**:
+- `skills/skill-creator/scripts/*.py`
+- `skills/skill-creator/references/*.md`
+- `skills/skill-creator/SKILL.md`
+
+**Example commit sequence**:
+```
+Update or add scripts in skills/skill-creator/scripts/
+Update references or documentation in skills/skill-creator/references/
+Update SKILL.md for skill-creator if needed
+```
+
+### Add Or Update Claude Api Skill
+
+Adds or updates the claude-api documentation skill, including language-specific guides and shared references.
+
+**Frequency**: ~1 times per month
+
+**Steps**:
+1. Add or update skills/claude-api/SKILL.md
+2. Add or update language guides in skills/claude-api/{python,typescript,java,go,ruby,csharp,php,curl}/
+3. Update shared documentation in skills/claude-api/shared/
+4. Update marketplace or index if needed
+
+**Files typically involved**:
+- `skills/claude-api/SKILL.md`
+- `skills/claude-api/*/claude-api.md`
+- `skills/claude-api/*/README.md`
+- `skills/claude-api/*/*.md`
+- `skills/claude-api/shared/*.md`
+- `.claude-plugin/marketplace.json`
+
+**Example commit sequence**:
+```
+Add or update skills/claude-api/SKILL.md
+Add or update language guides in skills/claude-api/{python,typescript,java,go,ruby,csharp,php,curl}/
+Update shared documentation in skills/claude-api/shared/
+Update marketplace or index if needed
+```
+
+
+## Best Practices
+
+Based on analysis of the codebase, follow these practices:
+
+### Do
+
+- Use kebab-case for file names
+- Prefer named exports
+
+### Don't
+
+- Don't deviate from established patterns without discussion
+
+---
+
+*This skill was auto-generated by [ECC Tools](https://ecc.tools). Review and customize as needed for your team.*
diff --git a/.agents/skills/skills_claude/agents/openai.yaml b/.agents/skills/skills_claude/agents/openai.yaml
new file mode 100644
index 000000000..6b23ac58f
--- /dev/null
+++ b/.agents/skills/skills_claude/agents/openai.yaml
@@ -0,0 +1,6 @@
+interface:
+  display_name: "Skills Claude"
+  short_description: "Repo-specific patterns and workflows for skills_claude"
+  default_prompt: "Use the skills_claude repo skill to follow existing architecture, testing, and workflow conventions."
+policy:
+  allow_implicit_invocation: true
\ No newline at end of file
diff --git a/.claude/commands/add-new-skill.md b/.claude/commands/add-new-skill.md
new file mode 100644
index 000000000..e4ee5b190
--- /dev/null
+++ b/.claude/commands/add-new-skill.md
@@ -0,0 +1,41 @@
+---
+name: add-new-skill
+description: Workflow command scaffold for add-new-skill in skills_claude.
+allowed_tools: ["Bash", "Read", "Write", "Grep", "Glob"]
+---
+
+# /add-new-skill
+
+Use this workflow when working on **add-new-skill** in `skills_claude`.
+
+## Goal
+
+Adds a new skill to the repository, including its SKILL.md and any supporting files.
+
+## Common Files
+
+- `skills/*/SKILL.md`
+- `skills/*/LICENSE.txt`
+- `skills/*/scripts/*`
+- `skills/*/templates/*`
+- `skills/*/examples/*`
+- `skills/*/reference/*`
+
+## Suggested Sequence
+
+1. Understand the current state and failure mode before editing.
+2. Make the smallest coherent change that satisfies the workflow goal.
+3. Run the most relevant verification for touched files.
+4. Summarize what changed and what still needs review.
+
+## Typical Commit Signals
+
+- Create a new folder under skills/ (or previously examples/, document-skills/, office-examples/).
+- Add SKILL.md to the new skill folder.
+- Optionally add LICENSE.txt, scripts/, templates/, examples/, or reference/ subfolders and files as needed.
+- Update skills/README.md or .claude-plugin/marketplace.json if necessary.
+
+## Notes
+
+- Treat this as a scaffold, not a hard-coded script.
+- Update the command if the workflow evolves materially.
\ No newline at end of file
diff --git a/.claude/commands/add-or-update-skill.md b/.claude/commands/add-or-update-skill.md
new file mode 100644
index 000000000..c507405fa
--- /dev/null
+++ b/.claude/commands/add-or-update-skill.md
@@ -0,0 +1,40 @@
+---
+name: add-or-update-skill
+description: Workflow command scaffold for add-or-update-skill in skills_claude.
+allowed_tools: ["Bash", "Read", "Write", "Grep", "Glob"]
+---
+
+# /add-or-update-skill
+
+Use this workflow when working on **add-or-update-skill** in `skills_claude`.
+
+## Goal
+
+Adds a new skill or updates an existing skill, including its SKILL.md and related scripts/assets.
+
+## Common Files
+
+- `skills/*/SKILL.md`
+- `skills/*/scripts/*.py`
+- `skills/*/templates/*`
+- `skills/*/reference/*`
+- `.claude-plugin/marketplace.json`
+
+## Suggested Sequence
+
+1. Understand the current state and failure mode before editing.
+2. Make the smallest coherent change that satisfies the workflow goal.
+3. Run the most relevant verification for touched files.
+4. Summarize what changed and what still needs review.
+
+## Typical Commit Signals
+
+- Create or update SKILL.md in skills/<skill-name>/
+- Add or update supporting scripts, templates, or assets in the skill's folder
+- If applicable, update marketplace or index files (e.g., .claude-plugin/marketplace.json)
+- Optionally, add language-specific guides or reference files
+
+## Notes
+
+- Treat this as a scaffold, not a hard-coded script.
+- Update the command if the workflow evolves materially.
\ No newline at end of file
diff --git a/.claude/commands/feature-development.md b/.claude/commands/feature-development.md
new file mode 100644
index 000000000..70704fd43
--- /dev/null
+++ b/.claude/commands/feature-development.md
@@ -0,0 +1,36 @@
+---
+name: feature-development
+description: Workflow command scaffold for feature-development in skills_claude.
+allowed_tools: ["Bash", "Read", "Write", "Grep", "Glob"]
+---
+
+# /feature-development
+
+Use this workflow when working on **feature-development** in `skills_claude`.
+
+## Goal
+
+Standard feature implementation workflow
+
+## Common Files
+
+- `**/*.test.*`
+- `**/api/**`
+
+## Suggested Sequence
+
+1. Understand the current state and failure mode before editing.
+2. Make the smallest coherent change that satisfies the workflow goal.
+3. Run the most relevant verification for touched files.
+4. Summarize what changed and what still needs review.
+
+## Typical Commit Signals
+
+- Add feature implementation
+- Add tests for feature
+- Update documentation
+
+## Notes
+
+- Treat this as a scaffold, not a hard-coded script.
+- Update the command if the workflow evolves materially.
\ No newline at end of file
diff --git a/.claude/commands/refactoring.md b/.claude/commands/refactoring.md
new file mode 100644
index 000000000..7ccd6579f
--- /dev/null
+++ b/.claude/commands/refactoring.md
@@ -0,0 +1,35 @@
+---
+name: refactoring
+description: Workflow command scaffold for refactoring in skills_claude.
+allowed_tools: ["Bash", "Read", "Write", "Grep", "Glob"]
+---
+
+# /refactoring
+
+Use this workflow when working on **refactoring** in `skills_claude`.
+
+## Goal
+
+Code refactoring and cleanup workflow
+
+## Common Files
+
+- `src/**/*`
+
+## Suggested Sequence
+
+1. Understand the current state and failure mode before editing.
+2. Make the smallest coherent change that satisfies the workflow goal.
+3. Run the most relevant verification for touched files.
+4. Summarize what changed and what still needs review.
+
+## Typical Commit Signals
+
+- Ensure tests pass before refactor
+- Refactor code structure
+- Verify tests still pass
+
+## Notes
+
+- Treat this as a scaffold, not a hard-coded script.
+- Update the command if the workflow evolves materially.
\ No newline at end of file
diff --git a/.claude/commands/update-or-export-example-skills.md b/.claude/commands/update-or-export-example-skills.md
new file mode 100644
index 000000000..f7f724e53
--- /dev/null
+++ b/.claude/commands/update-or-export-example-skills.md
@@ -0,0 +1,40 @@
+---
+name: update-or-export-example-skills
+description: Workflow command scaffold for update-or-export-example-skills in skills_claude.
+allowed_tools: ["Bash", "Read", "Write", "Grep", "Glob"]
+---
+
+# /update-or-export-example-skills
+
+Use this workflow when working on **update-or-export-example-skills** in `skills_claude`.
+
+## Goal
+
+Bulk updates or exports of example skills, often including renaming, reorganizing, or synchronizing multiple skill folders and their contents.
+
+## Common Files
+
+- `skills/*/SKILL.md`
+- `skills/*/LICENSE.txt`
+- `skills/*/scripts/*`
+- `skills/*/templates/*`
+- `skills/*/examples/*`
+- `skills/*/reference/*`
+
+## Suggested Sequence
+
+1. Understand the current state and failure mode before editing.
+2. Make the smallest coherent change that satisfies the workflow goal.
+3. Run the most relevant verification for touched files.
+4. Summarize what changed and what still needs review.
+
+## Typical Commit Signals
+
+- Modify, move, or rename multiple skill folders (e.g., from examples/ to skills/, or document-skills/).
+- Update SKILL.md and supporting files for each skill.
+- Update marketplace.json or skills/README.md as needed.
+
+## Notes
+
+- Treat this as a scaffold, not a hard-coded script.
+- Update the command if the workflow evolves materially.
\ No newline at end of file
diff --git a/.claude/ecc-tools.json b/.claude/ecc-tools.json
new file mode 100644
index 000000000..b5f8b6e99
--- /dev/null
+++ b/.claude/ecc-tools.json
@@ -0,0 +1,240 @@
+{
+  "version": "1.3",
+  "schemaVersion": "1.0",
+  "generatedBy": "ecc-tools",
+  "generatedAt": "2026-03-24T23:11:26.356Z",
+  "repo": "https://github.com/Eaprime1/skills_claude",
+  "profiles": {
+    "requested": "research",
+    "recommended": "research",
+    "effective": "developer",
+    "requestedAlias": "research",
+    "recommendedAlias": "research",
+    "effectiveAlias": "developer"
+  },
+  "requestedProfile": "research",
+  "profile": "developer",
+  "recommendedProfile": "research",
+  "effectiveProfile": "developer",
+  "tier": "free",
+  "requestedComponents": [
+    "repo-baseline",
+    "workflow-automation",
+    "research-tooling"
+  ],
+  "selectedComponents": [
+    "repo-baseline",
+    "workflow-automation"
+  ],
+  "requestedAddComponents": [],
+  "requestedRemoveComponents": [],
+  "blockedRemovalComponents": [],
+  "tierFilteredComponents": [
+    "research-tooling"
+  ],
+  "requestedRootPackages": [
+    "runtime-core",
+    "workflow-pack",
+    "research-pack"
+  ],
+  "selectedRootPackages": [
+    "runtime-core",
+    "workflow-pack"
+  ],
+  "requestedPackages": [
+    "runtime-core",
+    "workflow-pack",
+    "research-pack"
+  ],
+  "requestedAddPackages": [],
+  "requestedRemovePackages": [],
+  "selectedPackages": [
+    "runtime-core",
+    "workflow-pack"
+  ],
+  "packages": [
+    "runtime-core",
+    "workflow-pack"
+  ],
+  "blockedRemovalPackages": [],
+  "tierFilteredRootPackages": [
+    "research-pack"
+  ],
+  "tierFilteredPackages": [
+    "research-pack"
+  ],
+  "conflictingPackages": [],
+  "dependencyGraph": {
+    "runtime-core": [],
+    "workflow-pack": [
+      "runtime-core"
+    ]
+  },
+  "resolutionOrder": [
+    "runtime-core",
+    "workflow-pack"
+  ],
+  "requestedModules": [
+    "runtime-core",
+    "workflow-pack",
+    "research-pack"
+  ],
+  "selectedModules": [
+    "runtime-core",
+    "workflow-pack"
+  ],
+  "modules": [
+    "runtime-core",
+    "workflow-pack"
+  ],
+  "managedFiles": [
+    ".claude/skills/skills_claude/SKILL.md",
+    ".agents/skills/skills_claude/SKILL.md",
+    ".agents/skills/skills_claude/agents/openai.yaml",
+    ".claude/identity.json",
+    ".codex/config.toml",
+    ".codex/AGENTS.md",
+    ".codex/agents/explorer.toml",
+    ".codex/agents/reviewer.toml",
+    ".codex/agents/docs-researcher.toml",
+    ".claude/homunculus/instincts/inherited/skills_claude-instincts.yaml",
+    ".claude/commands/feature-development.md",
+    ".claude/commands/refactoring.md",
+    ".claude/commands/add-or-update-skill.md"
+  ],
+  "packageFiles": {
+    "runtime-core": [
+      ".claude/skills/skills_claude/SKILL.md",
+      ".agents/skills/skills_claude/SKILL.md",
+      ".agents/skills/skills_claude/agents/openai.yaml",
+      ".claude/identity.json",
+      ".codex/config.toml",
+      ".codex/AGENTS.md",
+      ".codex/agents/explorer.toml",
+      ".codex/agents/reviewer.toml",
+      ".codex/agents/docs-researcher.toml",
+      ".claude/homunculus/instincts/inherited/skills_claude-instincts.yaml"
+    ],
+    "workflow-pack": [
+      ".claude/commands/feature-development.md",
+      ".claude/commands/refactoring.md",
+      ".claude/commands/add-or-update-skill.md"
+    ]
+  },
+  "moduleFiles": {
+    "runtime-core": [
+      ".claude/skills/skills_claude/SKILL.md",
+      ".agents/skills/skills_claude/SKILL.md",
+      ".agents/skills/skills_claude/agents/openai.yaml",
+      ".claude/identity.json",
+      ".codex/config.toml",
+      ".codex/AGENTS.md",
+      ".codex/agents/explorer.toml",
+      ".codex/agents/reviewer.toml",
+      ".codex/agents/docs-researcher.toml",
+      ".claude/homunculus/instincts/inherited/skills_claude-instincts.yaml"
+    ],
+    "workflow-pack": [
+      ".claude/commands/feature-development.md",
+      ".claude/commands/refactoring.md",
+      ".claude/commands/add-or-update-skill.md"
+    ]
+  },
+  "files": [
+    {
+      "moduleId": "runtime-core",
+      "path": ".claude/skills/skills_claude/SKILL.md",
+      "description": "Repository-specific Claude Code skill generated from git history."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".agents/skills/skills_claude/SKILL.md",
+      "description": "Codex-facing copy of the generated repository skill."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".agents/skills/skills_claude/agents/openai.yaml",
+      "description": "Codex skill metadata so the repo skill appears cleanly in the skill interface."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".claude/identity.json",
+      "description": "Suggested identity.json baseline derived from repository conventions."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".codex/config.toml",
+      "description": "Repo-local Codex MCP and multi-agent baseline aligned with ECC defaults."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".codex/AGENTS.md",
+      "description": "Codex usage guide that points at the generated repo skill and workflow bundle."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".codex/agents/explorer.toml",
+      "description": "Read-only explorer role config for Codex multi-agent work."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".codex/agents/reviewer.toml",
+      "description": "Read-only reviewer role config focused on correctness and security."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".codex/agents/docs-researcher.toml",
+      "description": "Read-only docs researcher role config for API verification."
+    },
+    {
+      "moduleId": "runtime-core",
+      "path": ".claude/homunculus/instincts/inherited/skills_claude-instincts.yaml",
+      "description": "Continuous-learning instincts derived from repository patterns."
+    },
+    {
+      "moduleId": "workflow-pack",
+      "path": ".claude/commands/feature-development.md",
+      "description": "Workflow command scaffold for feature-development."
+    },
+    {
+      "moduleId": "workflow-pack",
+      "path": ".claude/commands/refactoring.md",
+      "description": "Workflow command scaffold for refactoring."
+    },
+    {
+      "moduleId": "workflow-pack",
+      "path": ".claude/commands/add-or-update-skill.md",
+      "description": "Workflow command scaffold for add-or-update-skill."
+    }
+  ],
+  "workflows": [
+    {
+      "command": "feature-development",
+      "path": ".claude/commands/feature-development.md"
+    },
+    {
+      "command": "refactoring",
+      "path": ".claude/commands/refactoring.md"
+    },
+    {
+      "command": "add-or-update-skill",
+      "path": ".claude/commands/add-or-update-skill.md"
+    }
+  ],
+  "adapters": {
+    "claudeCode": {
+      "skillPath": ".claude/skills/skills_claude/SKILL.md",
+      "identityPath": ".claude/identity.json",
+      "commandPaths": [
+        ".claude/commands/feature-development.md",
+        ".claude/commands/refactoring.md",
+        ".claude/commands/add-or-update-skill.md"
+      ]
+    },
+    "codex": {
+      "configPath": ".codex/config.toml",
+      "agentsGuidePath": ".codex/AGENTS.md",
+      "skillPath": ".agents/skills/skills_claude/SKILL.md"
+    }
+  }
+}
\ No newline at end of file
diff --git a/.claude/homunculus/instincts/inherited/skills_claude-instincts.yaml b/.claude/homunculus/instincts/inherited/skills_claude-instincts.yaml
new file mode 100644
index 000000000..e50e1aa5b
--- /dev/null
+++ b/.claude/homunculus/instincts/inherited/skills_claude-instincts.yaml
@@ -0,0 +1,227 @@
+# Instincts generated from https://github.com/Eaprime1/skills_claude
+# Generated: 2026-03-24T23:05:41.152Z
+# Version: 2.0
+# NOTE: This file supplements (does not replace) any existing curated instincts.
+# High-confidence manually curated instincts should be preserved alongside these.
+
+---
+id: skills_claude-commit-length
+trigger: "when writing a commit message"
+confidence: 0.6
+domain: git
+source: repo-analysis
+source_repo: https://github.com/Eaprime1/skills_claude
+---
+
+# Skills_claude Commit Length
+
+## Action
+
+Keep commit messages concise (~46 characters)
+
+## Evidence
+
+- Average commit message length: 46 chars
+- Based on 19 commits
+
+---
+id: skills_claude-naming-files
+trigger: "when creating a new file"
+confidence: 0.8
+domain: code-style
+source: repo-analysis
+source_repo: https://github.com/Eaprime1/skills_claude
+---
+
+# Skills_claude Naming Files
+
+## Action
+
+Use kebab-case naming convention
+
+## Evidence
+
+- Analyzed file naming patterns in repository
+- Dominant pattern: kebab-case
+
+---
+id: skills_claude-import-relative
+trigger: "when importing modules"
+confidence: 0.75
+domain: code-style
+source: repo-analysis
+source_repo: https://github.com/Eaprime1/skills_claude
+---
+
+# Skills_claude Import Relative
+
+## Action
+
+Use relative imports for project files
+
+## Evidence
+
+- Import analysis shows relative import pattern
+- Example: import { x } from '../lib/x'
+
+---
+id: skills_claude-export-style
+trigger: "when exporting from a module"
+confidence: 0.7
+domain: code-style
+source: repo-analysis
+source_repo: https://github.com/Eaprime1/skills_claude
+---
+
+# Skills_claude Export Style
+
+## Action
+
+Prefer named exports
+
+## Evidence
+
+- Export pattern analysis
+- Dominant style: named
+
+---
+id: skills_claude-test-separate
+trigger: "when writing tests"
+confidence: 0.8
+domain: testing
+source: repo-analysis
+source_repo: https://github.com/Eaprime1/skills_claude
+---
+
+# Skills_claude Test Separate
+
+## Action
+
+Place tests in the tests/ or __tests__/ directory, mirroring src structure
+
+## Evidence
+
+- Separate test directory pattern detected
+- Tests live in dedicated test folders
+
+---
+id: skills_claude-workflow-feature-development
+trigger: "when implementing a new feature"
+confidence: 0.9
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/Eaprime1/skills_claude
+---
+
+# Skills_claude Workflow Feature Development
+
+## Action
+
+Follow the feature-development workflow:
+1. Add feature implementation
+2. Add tests for feature
+3. Update documentation
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~13x per month
+- Files: **/*.test.*
+
+---
+id: skills_claude-workflow-add-new-skill
+trigger: "when doing add new skill"
+confidence: 0.55
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/Eaprime1/skills_claude
+---
+
+# Skills_claude Workflow Add New Skill
+
+## Action
+
+Follow the add-new-skill workflow:
+1. Create a new folder under skills/ (or previously examples/, document-skills/, office-examples/).
+2. Add SKILL.md to the new skill folder.
+3. Optionally add LICENSE.txt, scripts/, templates/, examples/, or reference/ subfolders and files as needed.
+4. Update skills/README.md or .claude-plugin/marketplace.json if necessary.
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~1x per month
+- Files: skills/*/SKILL.md, skills/*/LICENSE.txt, skills/*/scripts/*
+
+---
+id: skills_claude-workflow-update-or-export-example-skills
+trigger: "when doing update or export example skills"
+confidence: 0.55
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/Eaprime1/skills_claude
+---
+
+# Skills_claude Workflow Update Or Export Example Skills
+
+## Action
+
+Follow the update-or-export-example-skills workflow:
+1. Modify, move, or rename multiple skill folders (e.g., from examples/ to skills/, or document-skills/).
+2. Update SKILL.md and supporting files for each skill.
+3. Update marketplace.json or skills/README.md as needed.
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~1x per month
+- Files: skills/*/SKILL.md, skills/*/LICENSE.txt, skills/*/scripts/*
+
+---
+id: skills_claude-workflow-package-skills-for-distribution
+trigger: "when doing package skills for distribution"
+confidence: 0.55
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/Eaprime1/skills_claude
+---
+
+# Skills_claude Workflow Package Skills For Distribution
+
+## Action
+
+Follow the package-skills-for-distribution workflow:
+1. Run packaging scripts or commands.
+2. Generate .skill files in the dist/ directory.
+3. Ensure SKILL.md and all necessary assets are included in each .skill file.
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~1x per month
+- Files: dist/*.skill, skills/*/SKILL.md, skills/*/scripts/*
+
+---
+id: skills_claude-workflow-update-spec-or-documentation
+trigger: "when doing update spec or documentation"
+confidence: 0.55
+domain: workflow
+source: repo-analysis
+source_repo: https://github.com/Eaprime1/skills_claude
+---
+
+# Skills_claude Workflow Update Spec Or Documentation
+
+## Action
+
+Follow the update-spec-or-documentation workflow:
+1. Edit spec/agent-skills-spec.md or related spec/*.md files.
+2. Optionally split or merge documentation files.
+3. Update README.md with new links or notes.
+
+## Evidence
+
+- Workflow detected from commit patterns
+- Frequency: ~1x per month
+- Files: spec/agent-skills-spec.md, spec/skill-authoring.md, spec/skill-client-integration.md
+
diff --git a/.claude/identity.json b/.claude/identity.json
new file mode 100644
index 000000000..408095e5a
--- /dev/null
+++ b/.claude/identity.json
@@ -0,0 +1,14 @@
+{
+  "version": "2.0",
+  "technicalLevel": "technical",
+  "preferredStyle": {
+    "verbosity": "moderate",
+    "codeComments": true,
+    "explanations": true
+  },
+  "domains": [
+    "python"
+  ],
+  "suggestedBy": "ecc-tools-repo-analysis",
+  "createdAt": "2026-03-24T23:11:41.389Z"
+}
\ No newline at end of file
diff --git a/.claude/skills/skills_claude/SKILL.md b/.claude/skills/skills_claude/SKILL.md
new file mode 100644
index 000000000..3640d6a4a
--- /dev/null
+++ b/.claude/skills/skills_claude/SKILL.md
@@ -0,0 +1,338 @@
+---
+name: skills-claude-conventions
+description: Development conventions and patterns for skills_claude. Python project with mixed commits.
+---
+
+# Skills Claude Conventions
+
+> Generated from [Eaprime1/skills_claude](https://github.com/Eaprime1/skills_claude) on 2026-03-24
+
+## Overview
+
+This skill teaches Claude the development patterns and conventions used in skills_claude.
+
+## Tech Stack
+
+- **Primary Language**: Python
+- **Architecture**: hybrid module organization
+- **Test Location**: separate
+
+## When to Use This Skill
+
+Activate this skill when:
+- Making changes to this repository
+- Adding new features following established patterns
+- Writing tests that match project conventions
+- Creating commits with proper message format
+
+## Commit Conventions
+
+Follow these commit message conventions based on 42 analyzed commits.
+
+### Commit Style: Mixed Style
+
+### Prefixes Used
+
+- `feat`
+- `chore`
+
+### Message Guidelines
+
+- Average message length: ~56 characters
+- Keep first line concise and descriptive
+- Use imperative mood ("Add feature" not "Added feature")
+
+
+*Commit message example*
+
+```text
+feat: add skills_claude ECC bundle (.claude/commands/update-or-export-example-skills.md)
+```
+
+*Commit message example*
+
+```text
+chore: update claude-api skill [auto-sync] (#729)
+```
+
+*Commit message example*
+
+```text
+Merge branch 'anthropics:main' into claude/skills-brainstorm-Nd4vz
+```
+
+*Commit message example*
+
+```text
+Merge pull request #2 from Eaprime1/ecc-tools/skills_claude-1774393541560
+```
+
+*Commit message example*
+
+```text
+feat: add skills_claude ECC bundle (.claude/commands/add-new-skill.md)
+```
+
+*Commit message example*
+
+```text
+feat: add skills_claude ECC bundle (.claude/commands/feature-development.md)
+```
+
+*Commit message example*
+
+```text
+feat: add skills_claude ECC bundle (.codex/agents/docs-researcher.toml)
+```
+
+*Commit message example*
+
+```text
+feat: add skills_claude ECC bundle (.codex/agents/reviewer.toml)
+```
+
+## Architecture
+
+### Project Structure: Single Package
+
+This project uses **hybrid** module organization.
+
+### Guidelines
+
+- This project uses a hybrid organization
+- Follow existing patterns when adding new code
+
+## Code Style
+
+### Language: Python
+
+### Naming Conventions
+
+| Element | Convention |
+|---------|------------|
+| Files | kebab-case |
+| Functions | camelCase |
+| Classes | PascalCase |
+| Constants | SCREAMING_SNAKE_CASE |
+
+### Import Style: Relative Imports
+
+### Export Style: Named Exports
+
+
+*Preferred import style*
+
+```typescript
+// Use relative imports
+import { Button } from '../components/Button'
+import { useAuth } from './hooks/useAuth'
+```
+
+*Preferred export style*
+
+```typescript
+// Use named exports
+export function calculateTotal() { ... }
+export const TAX_RATE = 0.1
+export interface Order { ... }
+```
+
+## Common Workflows
+
+These workflows were detected from analyzing commit patterns.
+
+### Feature Development
+
+Standard feature implementation workflow
+
+**Frequency**: ~19 times per month
+
+**Steps**:
+1. Add feature implementation
+2. Add tests for feature
+3. Update documentation
+
+**Files typically involved**:
+- `**/*.test.*`
+- `**/api/**`
+
+**Example commit sequence**:
+```
+Add 3rd Party notices (#4)
+Add initial Agent Skills Spec (#2)
+Small tweak to blog link (#7)
+```
+
+### Refactoring
+
+Code refactoring and cleanup workflow
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Ensure tests pass before refactor
+2. Refactor code structure
+3. Verify tests still pass
+
+**Files typically involved**:
+- `src/**/*`
+
+**Example commit sequence**:
+```
+Reorganize the example skills (#1)
+Adding more details to README (#3)
+Add 3rd Party notices (#4)
+```
+
+### Add Or Update Skill
+
+Adds a new skill or updates an existing skill, including its SKILL.md and related scripts/assets.
+
+**Frequency**: ~2 times per month
+
+**Steps**:
+1. Create or update SKILL.md in skills/<skill-name>/
+2. Add or update supporting scripts, templates, or assets in the skill's folder
+3. If applicable, update marketplace or index files (e.g., .claude-plugin/marketplace.json)
+4. Optionally, add language-specific guides or reference files
+
+**Files typically involved**:
+- `skills/*/SKILL.md`
+- `skills/*/scripts/*.py`
+- `skills/*/templates/*`
+- `skills/*/reference/*`
+- `.claude-plugin/marketplace.json`
+
+**Example commit sequence**:
+```
+Create or update SKILL.md in skills/<skill-name>/
+Add or update supporting scripts, templates, or assets in the skill's folder
+If applicable, update marketplace or index files (e.g., .claude-plugin/marketplace.json)
+Optionally, add language-specific guides or reference files
+```
+
+### Export Or Bundle Skills
+
+Exports multiple skills as distributable bundles or updates the exported set of skills.
+
+**Frequency**: ~1 times per month
+
+**Steps**:
+1. Aggregate or update SKILL.md and related files for all relevant skills
+2. Generate distributable bundles (e.g., .skill files in dist/)
+3. Update index/marketplace files if needed
+
+**Files typically involved**:
+- `dist/*.skill`
+- `skills/*/SKILL.md`
+- `.claude-plugin/marketplace.json`
+
+**Example commit sequence**:
+```
+Aggregate or update SKILL.md and related files for all relevant skills
+Generate distributable bundles (e.g., .skill files in dist/)
+Update index/marketplace files if needed
+```
+
+### Office Skill Shared Module Update
+
+Updates or reorganizes shared Office document processing modules (docx, pptx, xlsx) and their schemas/scripts.
+
+**Frequency**: ~1 times per month
+
+**Steps**:
+1. Update or reorganize scripts in skills/{docx,pptx,xlsx}/scripts/office/
+2. Update or add schemas in skills/{docx,pptx,xlsx}/scripts/office/schemas/
+3. Update pack/unpack/validate scripts for each Office skill
+4. Optionally, update SKILL.md or documentation for each skill
+
+**Files typically involved**:
+- `skills/docx/scripts/office/**/*`
+- `skills/pptx/scripts/office/**/*`
+- `skills/xlsx/scripts/office/**/*`
+- `skills/docx/scripts/office/schemas/**/*`
+- `skills/pptx/scripts/office/schemas/**/*`
+- `skills/xlsx/scripts/office/schemas/**/*`
+- `skills/docx/scripts/office/pack.py`
+- `skills/pptx/scripts/office/pack.py`
+- `skills/xlsx/scripts/office/pack.py`
+- `skills/docx/SKILL.md`
+- `skills/pptx/SKILL.md`
+- `skills/xlsx/SKILL.md`
+
+**Example commit sequence**:
+```
+Update or reorganize scripts in skills/{docx,pptx,xlsx}/scripts/office/
+Update or add schemas in skills/{docx,pptx,xlsx}/scripts/office/schemas/
+Update pack/unpack/validate scripts for each Office skill
+Optionally, update SKILL.md or documentation for each skill
+```
+
+### Skill Creator Tooling Update
+
+Updates scripts, references, or documentation in the skill-creator tool, including validation, packaging, and optimization scripts.
+
+**Frequency**: ~1 times per month
+
+**Steps**:
+1. Update or add scripts in skills/skill-creator/scripts/
+2. Update references or documentation in skills/skill-creator/references/
+3. Update SKILL.md for skill-creator if needed
+
+**Files typically involved**:
+- `skills/skill-creator/scripts/*.py`
+- `skills/skill-creator/references/*.md`
+- `skills/skill-creator/SKILL.md`
+
+**Example commit sequence**:
+```
+Update or add scripts in skills/skill-creator/scripts/
+Update references or documentation in skills/skill-creator/references/
+Update SKILL.md for skill-creator if needed
+```
+
+### Add Or Update Claude Api Skill
+
+Adds or updates the claude-api documentation skill, including language-specific guides and shared references.
+
+**Frequency**: ~1 times per month
+
+**Steps**:
+1. Add or update skills/claude-api/SKILL.md
+2. Add or update language guides in skills/claude-api/{python,typescript,java,go,ruby,csharp,php,curl}/
+3. Update shared documentation in skills/claude-api/shared/
+4. Update marketplace or index if needed
+
+**Files typically involved**:
+- `skills/claude-api/SKILL.md`
+- `skills/claude-api/*/claude-api.md`
+- `skills/claude-api/*/README.md`
+- `skills/claude-api/*/*.md`
+- `skills/claude-api/shared/*.md`
+- `.claude-plugin/marketplace.json`
+
+**Example commit sequence**:
+```
+Add or update skills/claude-api/SKILL.md
+Add or update language guides in skills/claude-api/{python,typescript,java,go,ruby,csharp,php,curl}/
+Update shared documentation in skills/claude-api/shared/
+Update marketplace or index if needed
+```
+
+
+## Best Practices
+
+Based on analysis of the codebase, follow these practices:
+
+### Do
+
+- Use kebab-case for file names
+- Prefer named exports
+
+### Don't
+
+- Don't deviate from established patterns without discussion
+
+---
+
+*This skill was auto-generated by [ECC Tools](https://ecc.tools). Review and customize as needed for your team.*
diff --git a/.codex/AGENTS.md b/.codex/AGENTS.md
new file mode 100644
index 000000000..a7a340fba
--- /dev/null
+++ b/.codex/AGENTS.md
@@ -0,0 +1,28 @@
+# ECC for Codex CLI
+
+This supplements the root `AGENTS.md` with a repo-local ECC baseline.
+
+## Repo Skill
+
+- Repo-generated Codex skill: `.agents/skills/skills_claude/SKILL.md`
+- Claude-facing companion skill: `.claude/skills/skills_claude/SKILL.md`
+- Keep user-specific credentials and private MCPs in `~/.codex/config.toml`, not in this repo.
+
+## MCP Baseline
+
+Treat `.codex/config.toml` as the default ECC-safe baseline for work in this repository.
+The generated baseline enables GitHub, Context7, Exa, Memory, Playwright, and Sequential Thinking.
+
+## Multi-Agent Support
+
+- Explorer: read-only evidence gathering
+- Reviewer: correctness, security, and regression review
+- Docs researcher: API and release-note verification
+
+## Workflow Files
+
+- `.claude/commands/feature-development.md`
+- `.claude/commands/add-new-skill.md`
+- `.claude/commands/update-or-export-example-skills.md`
+
+Use these workflow files as reusable task scaffolds when the detected repository workflows recur.
\ No newline at end of file
diff --git a/.codex/agents/docs-researcher.toml b/.codex/agents/docs-researcher.toml
new file mode 100644
index 000000000..0daae570b
--- /dev/null
+++ b/.codex/agents/docs-researcher.toml
@@ -0,0 +1,9 @@
+model = "gpt-5.4"
+model_reasoning_effort = "medium"
+sandbox_mode = "read-only"
+
+developer_instructions = """
+Verify APIs, framework behavior, and release-note claims against primary documentation before changes land.
+Cite the exact docs or file paths that support each claim.
+Do not invent undocumented behavior.
+"""
\ No newline at end of file
diff --git a/.codex/agents/explorer.toml b/.codex/agents/explorer.toml
new file mode 100644
index 000000000..732df7aff
--- /dev/null
+++ b/.codex/agents/explorer.toml
@@ -0,0 +1,9 @@
+model = "gpt-5.4"
+model_reasoning_effort = "medium"
+sandbox_mode = "read-only"
+
+developer_instructions = """
+Stay in exploration mode.
+Trace the real execution path, cite files and symbols, and avoid proposing fixes unless the parent agent asks for them.
+Prefer targeted search and file reads over broad scans.
+"""
\ No newline at end of file
diff --git a/.codex/agents/reviewer.toml b/.codex/agents/reviewer.toml
new file mode 100644
index 000000000..b13ed9cf1
--- /dev/null
+++ b/.codex/agents/reviewer.toml
@@ -0,0 +1,9 @@
+model = "gpt-5.4"
+model_reasoning_effort = "high"
+sandbox_mode = "read-only"
+
+developer_instructions = """
+Review like an owner.
+Prioritize correctness, security, behavioral regressions, and missing tests.
+Lead with concrete findings and avoid style-only feedback unless it hides a real bug.
+"""
\ No newline at end of file
diff --git a/.codex/config.toml b/.codex/config.toml
new file mode 100644
index 000000000..bc1ee67f6
--- /dev/null
+++ b/.codex/config.toml
@@ -0,0 +1,48 @@
+#:schema https://developers.openai.com/codex/config-schema.json
+
+# ECC Tools generated Codex baseline
+approval_policy = "on-request"
+sandbox_mode = "workspace-write"
+web_search = "live"
+
+[mcp_servers.github]
+command = "npx"
+args = ["-y", "@modelcontextprotocol/server-github"]
+
+[mcp_servers.context7]
+command = "npx"
+args = ["-y", "@upstash/context7-mcp@latest"]
+
+[mcp_servers.exa]
+url = "https://mcp.exa.ai/mcp"
+
+[mcp_servers.memory]
+command = "npx"
+args = ["-y", "@modelcontextprotocol/server-memory"]
+
+[mcp_servers.playwright]
+command = "npx"
+args = ["-y", "@playwright/mcp@latest", "--extension"]
+
+[mcp_servers.sequential-thinking]
+command = "npx"
+args = ["-y", "@modelcontextprotocol/server-sequential-thinking"]
+
+[features]
+multi_agent = true
+
+[agents]
+max_threads = 6
+max_depth = 1
+
+[agents.explorer]
+description = "Read-only codebase explorer for gathering evidence before changes are proposed."
+config_file = "agents/explorer.toml"
+
+[agents.reviewer]
+description = "PR reviewer focused on correctness, security, and missing tests."
+config_file = "agents/reviewer.toml"
+
+[agents.docs_researcher]
+description = "Documentation specialist that verifies APIs, framework behavior, and release notes."
+config_file = "agents/docs-researcher.toml"
\ No newline at end of file
diff --git a/dist/a11y-auditor.skill b/dist/a11y-auditor.skill
new file mode 100644
index 000000000..ae6c4e6ad
Binary files /dev/null and b/dist/a11y-auditor.skill differ
diff --git a/dist/changelog-curator.skill b/dist/changelog-curator.skill
new file mode 100644
index 000000000..28399c512
Binary files /dev/null and b/dist/changelog-curator.skill differ
diff --git a/dist/code-review-guide.skill b/dist/code-review-guide.skill
new file mode 100644
index 000000000..0d8844322
Binary files /dev/null and b/dist/code-review-guide.skill differ
diff --git a/dist/data-storytelling.skill b/dist/data-storytelling.skill
new file mode 100644
index 000000000..a9ceb0621
Binary files /dev/null and b/dist/data-storytelling.skill differ
diff --git a/dist/github-actions-builder.skill b/dist/github-actions-builder.skill
new file mode 100644
index 000000000..630630b3a
Binary files /dev/null and b/dist/github-actions-builder.skill differ
diff --git a/dist/quiz-generator.skill b/dist/quiz-generator.skill
new file mode 100644
index 000000000..979c0d51b
Binary files /dev/null and b/dist/quiz-generator.skill differ
diff --git a/dist/rfc-architect.skill b/dist/rfc-architect.skill
new file mode 100644
index 000000000..69cc60f88
Binary files /dev/null and b/dist/rfc-architect.skill differ
diff --git a/dist/tutorial-builder.skill b/dist/tutorial-builder.skill
new file mode 100644
index 000000000..befc60e2e
Binary files /dev/null and b/dist/tutorial-builder.skill differ
diff --git a/skills/a11y-auditor/SKILL.md b/skills/a11y-auditor/SKILL.md
new file mode 100644
index 000000000..5410e14a5
--- /dev/null
+++ b/skills/a11y-auditor/SKILL.md
@@ -0,0 +1,252 @@
+---
+name: a11y-auditor
+description: Accessibility audit guidance and WCAG compliance checking. Use when users need to evaluate web content accessibility, check WCAG compliance, review for screen reader compatibility, audit color contrast, assess keyboard navigation, or improve accessibility of digital content. Triggers on requests like "check accessibility", "WCAG audit", "screen reader compatible", "accessibility review", "ADA compliance", or "a11y check".
+---
+
+# Accessibility Auditor
+
+Guide accessibility evaluations using WCAG standards as the reality benchmark for validation.
+
+## WCAG Quick Reference
+
+### Conformance Levels
+
+| Level | Meaning | Typical Requirement |
+|-------|---------|---------------------|
+| **A** | Minimum | Legal baseline in most jurisdictions |
+| **AA** | Standard | Most common compliance target |
+| **AAA** | Enhanced | Specialized contexts (government, healthcare) |
+
+### Four Principles (POUR)
+
+1. **Perceivable** - Information must be presentable to users
+2. **Operable** - Interface must be navigable and usable
+3. **Understandable** - Content and operation must be clear
+4. **Robust** - Content must work with assistive technologies
+
+## Audit Checklist by Category
+
+### 1. Text Alternatives (WCAG 1.1)
+
+**Images**
+- [ ] All `<img>` have `alt` attributes
+- [ ] Decorative images use `alt=""` or CSS background
+- [ ] Complex images have extended descriptions
+- [ ] Alt text describes function, not appearance
+
+**Verification:**
+```
+Check: Does alt text answer "What information does this image convey?"
+Pass: "Submit button" or "Company logo linking to homepage"
+Fail: "image.jpg" or "picture of a button"
+```
+
+### 2. Time-Based Media (WCAG 1.2)
+
+- [ ] Videos have captions
+- [ ] Audio has transcripts
+- [ ] Live audio has real-time captions (AA)
+- [ ] Audio descriptions for visual-only content (AA)
+
+### 3. Adaptable Content (WCAG 1.3)
+
+**Structure**
+- [ ] Headings in logical order (h1 → h2 → h3)
+- [ ] Lists use proper `<ul>`, `<ol>`, `<dl>` markup
+- [ ] Tables have headers (`<th>`) and scope
+- [ ] Forms have associated labels
+
+**Verification:**
+```
+Test: Read content with CSS disabled
+Pass: Content order and structure still make sense
+Fail: Content becomes jumbled or loses meaning
+```
+
+### 4. Distinguishable Content (WCAG 1.4)
+
+**Color Contrast**
+
+| Text Type | AA Requirement | AAA Requirement |
+|-----------|----------------|-----------------|
+| Normal text | 4.5:1 | 7:1 |
+| Large text (18pt+) | 3:1 | 4.5:1 |
+| UI components | 3:1 | 3:1 |
+
+- [ ] Text meets contrast ratios
+- [ ] Color is not only indicator of meaning
+- [ ] Text resizes to 200% without loss
+- [ ] No horizontal scroll at 320px width (AA)
+
+**Verification:**
+```
+Tool: Use contrast checker (WebAIM, Colour Contrast Analyser)
+Test: View in grayscale - is all information still clear?
+```
+
+### 5. Keyboard Accessible (WCAG 2.1)
+
+- [ ] All functions available via keyboard
+- [ ] No keyboard traps
+- [ ] Focus order is logical
+- [ ] Focus indicator is visible
+- [ ] Skip navigation link present
+
+**Verification:**
+```
+Test: Unplug mouse, navigate entire site using only:
+- Tab / Shift+Tab (move focus)
+- Enter / Space (activate)
+- Arrow keys (within components)
+- Escape (close dialogs)
+
+Pass: Can access all content and functions
+Fail: Any element unreachable or traps focus
+```
+
+### 6. Timing (WCAG 2.2)
+
+- [ ] Time limits can be extended or disabled
+- [ ] Auto-updating content can be paused
+- [ ] No content flashes more than 3 times/second
+
+### 7. Navigation (WCAG 2.4)
+
+- [ ] Pages have descriptive titles
+- [ ] Focus order matches visual order
+- [ ] Link purpose clear from text (or context)
+- [ ] Multiple ways to find pages (AA)
+- [ ] Headings and labels are descriptive
+
+**Verification:**
+```
+Test: Read only the links on a page
+Pass: Each link makes sense out of context
+Fail: "Click here", "Read more", "Link" without context
+```
+
+### 8. Input Modalities (WCAG 2.5)
+
+- [ ] Touch targets at least 44x44 CSS pixels
+- [ ] Gestures have alternatives
+- [ ] Labels match accessible names
+
+### 9. Readable Content (WCAG 3.1)
+
+- [ ] Page language declared (`lang` attribute)
+- [ ] Language changes marked in content
+- [ ] Unusual words/abbreviations explained
+
+### 10. Predictable Behavior (WCAG 3.2)
+
+- [ ] Focus doesn't trigger unexpected changes
+- [ ] Input doesn't trigger unexpected changes
+- [ ] Navigation is consistent across pages
+
+### 11. Input Assistance (WCAG 3.3)
+
+- [ ] Errors clearly identified
+- [ ] Error suggestions provided
+- [ ] Labels/instructions for input
+- [ ] Error prevention for legal/financial (AA)
+
+**Verification:**
+```
+Test: Submit forms with errors intentionally
+Pass: Error messages are specific and adjacent to field
+Fail: Generic "Form error" or error at page top only
+```
+
+### 12. Compatible Markup (WCAG 4.1)
+
+- [ ] Valid HTML (no duplicate IDs)
+- [ ] ARIA used correctly
+- [ ] Custom components have proper roles
+- [ ] Status messages announced (AA)
+
+## Screen Reader Testing
+
+### Quick Test Protocol
+
+1. **Headings navigation**: Press `H` to jump between headings
+2. **Links list**: View all links (should make sense)
+3. **Forms mode**: Tab through form, verify labels read
+4. **Images**: Confirm alt text is appropriate
+5. **Dynamic content**: Check live regions announce updates
+
+### Common Screen Readers
+
+| Platform | Screen Reader | Key Commands |
+|----------|---------------|--------------|
+| Windows | NVDA (free) | Insert = NVDA key |
+| Windows | JAWS | Insert = JAWS key |
+| macOS/iOS | VoiceOver | VO = Ctrl+Option |
+| Android | TalkBack | Swipe gestures |
+
+## Automated Testing Tools
+
+### Integrate in Workflow
+
+```bash
+# Axe-core (CLI)
+npx @axe-core/cli https://example.com
+
+# Pa11y
+npx pa11y https://example.com
+
+# Lighthouse (Chrome)
+lighthouse --only-categories=accessibility https://example.com
+```
+
+### Tool Limitations
+
+Automated tools catch ~30-40% of issues. Manual testing required for:
+- Alt text quality (not just presence)
+- Focus order logic
+- Cognitive accessibility
+- Actual screen reader experience
+
+## Audit Report Structure
+
+```markdown
+# Accessibility Audit Report
+
+**Site/Application**: [Name]
+**Date**: [Date]
+**Standard**: WCAG 2.1 Level AA
+**Auditor**: [Name]
+
+## Executive Summary
+[Overall findings, critical issues count, pass rate]
+
+## Critical Issues (Must Fix)
+### Issue 1: [Description]
+- **WCAG Criterion**: [Number and name]
+- **Location**: [URL/component]
+- **Impact**: [User groups affected]
+- **Recommendation**: [How to fix]
+
+## Major Issues (Should Fix)
+[Same format]
+
+## Minor Issues (Consider Fixing)
+[Same format]
+
+## Passed Criteria
+[List of criteria that passed]
+
+## Testing Methodology
+[Tools used, manual tests performed]
+```
+
+## Quick Fixes Reference
+
+| Issue | Quick Fix |
+|-------|-----------|
+| Missing alt text | Add descriptive `alt` attribute |
+| Low contrast | Increase color difference (use checker) |
+| Missing form labels | Add `<label for="id">` |
+| No focus indicator | Add `:focus { outline: 2px solid }` |
+| Missing page title | Add descriptive `<title>` |
+| No skip link | Add hidden skip to main content link |
+| Missing lang | Add `<html lang="en">` |
diff --git a/skills/changelog-curator/SKILL.md b/skills/changelog-curator/SKILL.md
new file mode 100644
index 000000000..db67e9738
--- /dev/null
+++ b/skills/changelog-curator/SKILL.md
@@ -0,0 +1,283 @@
+---
+name: changelog-curator
+description: Generate and maintain changelogs, release notes, and version history documentation. Use when users need to document changes between versions, create release notes, maintain CHANGELOG files, summarize git commits, or track version history. Triggers on requests like "update changelog", "write release notes", "document changes", "version history", "what changed", or "summarize commits".
+---
+
+# Changelog Curator
+
+Create clear, useful change documentation that serves both developers and users.
+
+## Changelog Formats
+
+### Keep a Changelog Format (Recommended)
+
+Standard format from keepachangelog.com:
+
+```markdown
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/),
+and this project adheres to [Semantic Versioning](https://semver.org/).
+
+## [Unreleased]
+
+### Added
+- New feature description
+
+### Changed
+- Modification to existing functionality
+
+### Deprecated
+- Features that will be removed in future
+
+### Removed
+- Features removed in this release
+
+### Fixed
+- Bug fixes
+
+### Security
+- Security-related changes
+
+## [1.2.0] - 2024-03-15
+
+### Added
+- User profile avatars (#142)
+- Export to CSV functionality
+
+### Fixed
+- Login timeout issue on slow connections (#138)
+
+## [1.1.0] - 2024-02-01
+...
+
+[Unreleased]: https://github.com/user/repo/compare/v1.2.0...HEAD
+[1.2.0]: https://github.com/user/repo/compare/v1.1.0...v1.2.0
+[1.1.0]: https://github.com/user/repo/releases/tag/v1.1.0
+```
+
+### Change Categories
+
+| Category | Use For |
+|----------|---------|
+| **Added** | New features, capabilities |
+| **Changed** | Changes to existing features |
+| **Deprecated** | Features marked for removal |
+| **Removed** | Deleted features |
+| **Fixed** | Bug fixes |
+| **Security** | Vulnerability patches |
+
+## Writing Effective Entries
+
+### Good Entry Structure
+
+```markdown
+- [Action verb] [what changed] [context/benefit] (#issue)
+```
+
+Examples:
+```markdown
+### Added
+- Add dark mode theme with system preference detection (#234)
+- Support WebP image uploads alongside PNG and JPEG
+
+### Changed
+- Improve search performance by 40% using indexed queries
+- Update authentication flow to require email verification
+
+### Fixed
+- Fix crash when uploading files larger than 10MB (#189)
+- Resolve incorrect timezone display for UTC+12 users
+```
+
+### Avoid
+
+```markdown
+# Bad examples
+- Fixed bug          # Too vague
+- Updated stuff      # Meaningless
+- v1.2.3 changes     # No information
+- Refactored code    # Internal, not user-facing
+- Misc improvements  # Says nothing
+```
+
+### Audience Awareness
+
+**For Developers (CHANGELOG.md)**:
+- Include issue/PR references
+- Mention breaking changes prominently
+- Note migration steps
+
+**For Users (Release Notes)**:
+- Focus on benefits, not implementation
+- Use plain language
+- Group by user-facing impact
+
+## Generating from Git History
+
+### Extract Commits Since Last Tag
+
+```bash
+# Get commits since last tag
+git log $(git describe --tags --abbrev=0)..HEAD --oneline
+
+# With more detail
+git log $(git describe --tags --abbrev=0)..HEAD --pretty=format:"- %s (%h)"
+
+# Filter by type (if using conventional commits)
+git log --oneline | grep -E "^[a-f0-9]+ (feat|fix|docs):"
+```
+
+### Conventional Commits Mapping
+
+If project uses conventional commits:
+
+| Prefix | Changelog Category |
+|--------|-------------------|
+| `feat:` | Added |
+| `fix:` | Fixed |
+| `docs:` | (Usually skip) |
+| `refactor:` | (Usually skip) |
+| `perf:` | Changed |
+| `security:` | Security |
+| `BREAKING CHANGE:` | Changed (highlight!) |
+
+### Processing Commits
+
+1. **Group** commits by category
+2. **Filter** out internal changes (refactors, tests, CI)
+3. **Summarize** related commits into single entries
+4. **Link** to issues/PRs where helpful
+5. **Highlight** breaking changes
+
+## Semantic Versioning Reference
+
+```
+MAJOR.MINOR.PATCH
+
+MAJOR: Breaking changes (API incompatible)
+MINOR: New features (backwards compatible)
+PATCH: Bug fixes (backwards compatible)
+```
+
+### Version Decision Tree
+
+```
+Does this change break existing API/behavior?
+├─ YES → Increment MAJOR (reset MINOR, PATCH to 0)
+└─ NO → Does this add new functionality?
+        ├─ YES → Increment MINOR (reset PATCH to 0)
+        └─ NO → Increment PATCH
+```
+
+### Pre-release Versions
+
+```
+1.0.0-alpha.1    # Early testing
+1.0.0-beta.1     # Feature complete, testing
+1.0.0-rc.1       # Release candidate
+```
+
+## Release Notes Template
+
+For user-facing release communications:
+
+```markdown
+# [Product Name] v[X.Y.Z] Release Notes
+
+**Release Date**: [Date]
+
+## Highlights
+
+[2-3 sentence summary of the most important changes]
+
+## What's New
+
+### [Feature Name]
+[Description focused on user benefit, not technical implementation]
+[Optional: screenshot or example]
+
+### [Feature Name]
+...
+
+## Improvements
+
+- [Improvement 1]
+- [Improvement 2]
+
+## Bug Fixes
+
+- Fixed [issue description] ([#123])
+
+## Breaking Changes
+
+> **Action Required**: [What users need to do]
+
+[Description of what changed and migration steps]
+
+## Upgrade Instructions
+
+[Steps to upgrade from previous version]
+
+## Known Issues
+
+- [Issue description] - Workaround: [workaround]
+
+---
+
+[Full changelog](link) | [Documentation](link) | [Support](link)
+```
+
+## Maintenance Practices
+
+### Continuous Updates
+
+Add entries as changes are merged, not at release time:
+```markdown
+## [Unreleased]
+
+### Added
+- Feature merged today (#456)
+```
+
+### Release Checklist
+
+When cutting a release:
+1. [ ] Move `[Unreleased]` entries to new version section
+2. [ ] Add version number and date
+3. [ ] Update comparison links at bottom
+4. [ ] Create new empty `[Unreleased]` section
+5. [ ] Review entries for clarity and completeness
+6. [ ] Verify all breaking changes are prominently noted
+
+### Breaking Change Format
+
+Always make breaking changes obvious:
+
+```markdown
+## [2.0.0] - 2024-03-20
+
+### Changed
+
+- **BREAKING**: Rename `getUser()` to `fetchUser()` for consistency
+
+  Migration:
+  ```diff
+  - const user = api.getUser(id)
+  + const user = api.fetchUser(id)
+  ```
+
+- **BREAKING**: Remove deprecated `legacy` option from config
+```
+
+## Quality Checklist
+
+- [ ] Each entry starts with a verb (Add, Fix, Change, Remove)
+- [ ] Entries are user-meaningful, not implementation details
+- [ ] Issue/PR links included where helpful
+- [ ] Breaking changes clearly marked
+- [ ] Version follows semantic versioning
+- [ ] Date format consistent (YYYY-MM-DD recommended)
+- [ ] Comparison links at bottom are correct
diff --git a/skills/code-review-guide/SKILL.md b/skills/code-review-guide/SKILL.md
new file mode 100644
index 000000000..ce4efe3cc
--- /dev/null
+++ b/skills/code-review-guide/SKILL.md
@@ -0,0 +1,300 @@
+---
+name: code-review-guide
+description: Guide structured code reviews with security, performance, and quality checklists. Use when users need to review code changes, provide constructive feedback on pull requests, or establish code review standards. Triggers on requests like "review this code", "code review checklist", "PR feedback", "review standards", or "what to look for in code review".
+---
+
+# Code Review Guide
+
+Conduct thorough, constructive code reviews that improve quality without blocking progress.
+
+## Review Priorities
+
+Focus areas in order of importance:
+
+```
+1. CORRECTNESS   → Does it work? Does it handle edge cases?
+2. SECURITY      → Any vulnerabilities introduced?
+3. DESIGN        → Right abstraction? Maintainable?
+4. PERFORMANCE   → Obvious inefficiencies?
+5. STYLE         → Readable? Follows conventions?
+```
+
+## Quick Review Checklist
+
+### Correctness
+- [ ] Logic handles expected cases correctly
+- [ ] Edge cases considered (null, empty, boundaries)
+- [ ] Error conditions handled appropriately
+- [ ] Tests cover the changes
+- [ ] Changes match the stated intent/ticket
+
+### Security
+- [ ] No secrets/credentials in code
+- [ ] Input validated before use
+- [ ] SQL queries parameterized
+- [ ] User input escaped in output (XSS)
+- [ ] Authorization checks present
+- [ ] Sensitive data not logged
+
+### Design
+- [ ] Single responsibility maintained
+- [ ] No unnecessary coupling introduced
+- [ ] Abstractions at appropriate level
+- [ ] No code duplication added
+- [ ] Changes are reversible
+
+### Performance
+- [ ] No obvious N+1 queries
+- [ ] Large datasets paginated
+- [ ] Expensive operations cached or async
+- [ ] No blocking calls in hot paths
+
+### Readability
+- [ ] Names clearly express intent
+- [ ] Complex logic has explanatory comments
+- [ ] Functions are focused and small
+- [ ] Code matches existing patterns
+
+## Comment Guidelines
+
+### Be Specific, Not Vague
+
+```markdown
+# Bad
+"This is confusing"
+
+# Good
+"The variable name `data` doesn't indicate what it contains.
+Consider `userProfiles` to match the return type."
+```
+
+### Suggest, Don't Demand
+
+```markdown
+# Bad
+"Change this to use map()"
+
+# Good
+"Consider using `map()` here - it would eliminate the
+temporary array and express the transformation more directly."
+```
+
+### Explain the Why
+
+```markdown
+# Bad
+"Don't use var"
+
+# Good
+"Prefer `const` here since the value never changes.
+This signals intent to future readers and prevents accidental reassignment."
+```
+
+### Use Conventional Prefixes
+
+| Prefix | Meaning |
+|--------|---------|
+| `nit:` | Minor style issue, not blocking |
+| `suggestion:` | Optional improvement |
+| `question:` | Need clarification |
+| `issue:` | Needs to be addressed |
+| `blocking:` | Must fix before merge |
+
+### Example Comments
+
+```markdown
+**blocking:** This SQL query is vulnerable to injection.
+Use parameterized queries instead:
+`db.query('SELECT * FROM users WHERE id = ?', [userId])`
+
+**suggestion:** Consider extracting this into a named function -
+it would improve readability and make testing easier.
+
+**nit:** Missing trailing comma on line 47 (our style guide prefers them).
+
+**question:** What happens if `response.data` is undefined?
+Might need a null check.
+```
+
+## Security Deep-Dive
+
+### Injection Vulnerabilities
+
+```javascript
+// SQL Injection - VULNERABLE
+const query = `SELECT * FROM users WHERE id = ${userId}`;
+
+// SQL Injection - SAFE
+const query = 'SELECT * FROM users WHERE id = ?';
+db.query(query, [userId]);
+```
+
+```javascript
+// Command Injection - VULNERABLE
+exec(`ls ${userInput}`);
+
+// Command Injection - SAFE
+execFile('ls', [userInput]);
+```
+
+### Cross-Site Scripting (XSS)
+
+```javascript
+// XSS - VULNERABLE
+element.innerHTML = userComment;
+
+// XSS - SAFE
+element.textContent = userComment;
+// Or use a sanitization library
+```
+
+### Authentication/Authorization
+
+Questions to ask:
+- Is the user authenticated for this endpoint?
+- Is the user authorized for this specific resource?
+- Are admin functions properly protected?
+- Is session handling secure?
+
+### Data Exposure
+
+Watch for:
+- Logging sensitive data (passwords, tokens, PII)
+- Returning more data than needed in API responses
+- Error messages revealing system internals
+- Stack traces exposed to users
+
+## Performance Patterns
+
+### Database Queries
+
+```python
+# N+1 Query - INEFFICIENT
+for user in users:
+    orders = get_orders(user.id)  # Query per user!
+
+# Eager Loading - BETTER
+users = get_users_with_orders()  # Single query with JOIN
+```
+
+### Memory Usage
+
+```javascript
+// Loading entire dataset - PROBLEMATIC
+const allUsers = await db.getAllUsers(); // 1M users in memory!
+
+// Pagination - BETTER
+const users = await db.getUsers({ limit: 100, offset: page * 100 });
+
+// Streaming - BEST for large datasets
+const stream = db.getUserStream();
+stream.on('data', processUser);
+```
+
+### Async Operations
+
+```javascript
+// Sequential - SLOW
+const a = await fetchA();
+const b = await fetchB();
+const c = await fetchC();
+
+// Parallel - FASTER
+const [a, b, c] = await Promise.all([
+  fetchA(),
+  fetchB(),
+  fetchC()
+]);
+```
+
+## Design Smell Detection
+
+### Too Many Parameters
+
+```python
+# Smell: Long parameter list
+def create_user(name, email, age, address, city, country, phone, role):
+    ...
+
+# Better: Group related data
+def create_user(user_info: UserInfo, contact: ContactInfo):
+    ...
+```
+
+### Mixed Abstraction Levels
+
+```python
+# Smell: High and low-level operations mixed
+def process_order(order):
+    validate(order)
+    conn = psycopg2.connect(...)  # Low-level DB details
+    cursor = conn.cursor()
+    cursor.execute(...)           # SQL in business logic
+    send_email(order.customer)
+
+# Better: Consistent abstraction
+def process_order(order):
+    validate(order)
+    repository.save(order)        # Abstracted data access
+    notifications.order_confirmed(order)
+```
+
+### Boolean Parameter Smell
+
+```python
+# Smell: Boolean changes function behavior
+def get_users(include_inactive=False):
+    ...
+
+# Consider: Explicit separate functions or enum
+def get_active_users():
+    ...
+def get_all_users():
+    ...
+```
+
+## Review Workflow
+
+### Before Reviewing
+
+1. Understand the context (read PR description, linked issue)
+2. Check if tests pass in CI
+3. Review the overall change size (large PRs need more time)
+
+### During Review
+
+1. Start with the test files (understand intended behavior)
+2. Review main logic changes
+3. Check integration points (API changes, database changes)
+4. Look for missing edge cases
+
+### Completing Review
+
+- **Approve**: Good to merge, minor feedback can be addressed after
+- **Request Changes**: Blocking issues that need resolution
+- **Comment**: Questions or discussion, not blocking
+
+### After Review
+
+- Respond promptly to author's questions
+- Don't nitpick on follow-up commits
+- Trust the author to address feedback appropriately
+
+## Anti-Patterns in Reviews
+
+| Anti-Pattern | Problem | Instead |
+|--------------|---------|---------|
+| "Just do X" | Dismissive | Explain the reasoning |
+| "I would have..." | Preference, not issue | Ask if there's a reason |
+| Style crusade | Blocks progress | Use automated linting |
+| Rubber stamp | Misses issues | Take time, be thorough |
+| Gatekeeping | Demoralizing | Focus on teaching |
+
+## Receiving Reviews
+
+When your code is reviewed:
+- Assume good intent
+- Ask for clarification if feedback is unclear
+- Don't take feedback personally
+- Thank reviewers for thorough reviews
+- Address all comments (even if just "acknowledged")
diff --git a/skills/data-storytelling/SKILL.md b/skills/data-storytelling/SKILL.md
new file mode 100644
index 000000000..3082f86a3
--- /dev/null
+++ b/skills/data-storytelling/SKILL.md
@@ -0,0 +1,256 @@
+---
+name: data-storytelling
+description: Transform raw data into compelling narratives with insights and visualizations. Use when users need to communicate data findings to stakeholders, create executive summaries from analytics, build data-driven presentations, or explain trends and patterns. Triggers on requests like "explain this data", "summarize these metrics", "create a data presentation", "what does this data tell us", or "make a dashboard narrative".
+---
+
+# Data Storytelling
+
+Bridge the gap between raw data and meaningful communication by crafting narratives that drive understanding and action.
+
+## Storytelling Framework
+
+### 1. Context → Insight → Action
+
+Every data story follows this arc:
+
+```
+CONTEXT: What's the situation? Why does this matter now?
+    ↓
+INSIGHT: What did the data reveal? What's surprising or important?
+    ↓
+ACTION: What should we do about it? What's the recommendation?
+```
+
+### 2. Story Structure Template
+
+```markdown
+## The Headline
+[One sentence that captures the key insight]
+
+## The Setup
+[Why we looked at this data, what question we're answering]
+
+## The Journey
+[What the data shows, building from simple to complex]
+
+## The Revelation
+[The key insight, the "aha" moment]
+
+## The Path Forward
+[Recommendations and next steps]
+```
+
+## Audience Adaptation
+
+### Executive Summary (C-Suite)
+- Lead with the insight, not the methodology
+- Focus on business impact and dollars
+- One key metric, one key action
+- Keep to one page or 3 minutes
+
+```markdown
+**Bottom Line**: [Revenue/growth/risk impact in one sentence]
+
+**Key Finding**: [The insight]
+
+**Recommended Action**: [What to do]
+
+**Supporting Data**: [2-3 bullet points max]
+```
+
+### Operational Report (Managers)
+- Include trends and comparisons
+- Show what's within tolerance vs. needs attention
+- Provide enough detail for decisions
+
+### Technical Deep-Dive (Analysts)
+- Full methodology explanation
+- Statistical significance noted
+- Raw data access provided
+
+## Visualization Selection
+
+### Match Chart to Message
+
+| What You're Showing | Best Visualization |
+|---------------------|-------------------|
+| Change over time | Line chart |
+| Comparison between categories | Bar chart |
+| Part-to-whole relationship | Pie/donut (≤5 segments), stacked bar |
+| Correlation between variables | Scatter plot |
+| Distribution | Histogram, box plot |
+| Geographic patterns | Map |
+| Single metric status | Big number, gauge |
+
+### Visual Hierarchy
+
+```
+1. TITLE: What is this showing? (not "Revenue Chart")
+   → "Revenue grew 23% after campaign launch"
+
+2. FOCUS: Draw eye to the key insight
+   → Color, size, annotation
+
+3. CONTEXT: Reference points
+   → Benchmarks, targets, prior period
+
+4. DETAIL: Supporting information
+   → Legend, axis labels, source
+```
+
+## Insight Extraction Process
+
+### Step 1: Describe What You See
+
+```
+- Total: [value]
+- Range: [min] to [max]
+- Average/Median: [value]
+- Trend direction: [up/down/flat]
+- Notable outliers: [items]
+```
+
+### Step 2: Compare to Find Meaning
+
+| Comparison Type | Question Answered |
+|-----------------|-------------------|
+| vs. Prior Period | Is this better or worse? |
+| vs. Target/Goal | Are we on track? |
+| vs. Benchmark | How do we compare to others? |
+| vs. Segments | Where are the differences? |
+
+### Step 3: Ask "So What?"
+
+Transform observation into insight:
+
+```
+OBSERVATION: Sales dropped 15% in Q3
+    ↓ So what?
+INSIGHT: Our largest customer segment reduced spending
+    ↓ So what?
+IMPLICATION: We need to address churn risk or find new segments
+    ↓ So what?
+RECOMMENDATION: Launch retention program for enterprise accounts
+```
+
+## Narrative Patterns
+
+### The Trend Story
+
+```markdown
+**Where we were**: [Historical baseline]
+**What changed**: [The inflection point or trend]
+**Where we're headed**: [Projection if trend continues]
+**What to do**: [Action to maintain or reverse]
+```
+
+### The Comparison Story
+
+```markdown
+**The difference**: [Key gap between A and B]
+**Why it matters**: [Impact of that difference]
+**The cause**: [What explains the difference]
+**The learning**: [What we should do differently]
+```
+
+### The Anomaly Story
+
+```markdown
+**The surprise**: [What deviated from expectations]
+**The investigation**: [What we found when we dug in]
+**The explanation**: [Root cause]
+**The response**: [Whether to act or adjust expectations]
+```
+
+### The Correlation Story
+
+```markdown
+**The pattern**: [When X happens, Y tends to happen]
+**The evidence**: [Data showing the relationship]
+**The caveat**: [Correlation vs. causation acknowledgment]
+**The hypothesis**: [Proposed causal mechanism to test]
+```
+
+## Dashboard Narrative Flow
+
+### Layout Principles
+
+```
+┌─────────────────────────────────────────────┐
+│  HEADLINE METRIC                            │  ← Most important number
+│  +12% vs target                             │
+├─────────────────┬───────────────────────────┤
+│                 │                           │
+│  TREND          │  BREAKDOWN                │  ← Context and detail
+│  (line chart)   │  (bar chart)              │
+│                 │                           │
+├─────────────────┴───────────────────────────┤
+│  SUPPORTING DETAILS                         │  ← Tables, secondary metrics
+│  (as needed)                                │
+└─────────────────────────────────────────────┘
+```
+
+### Annotation Best Practices
+
+Add annotations to highlight:
+- Goal lines and targets
+- Events that explain changes
+- Anomalies requiring attention
+- Thresholds (good/warning/critical)
+
+## Output Templates
+
+### One-Page Data Brief
+
+```markdown
+# [Topic]: [Key Finding in Active Voice]
+
+## At a Glance
+| Metric | Current | vs. Prior | Status |
+|--------|---------|-----------|--------|
+| [KPI]  | [value] | [change]  | [↑/↓]  |
+
+## Key Insight
+[2-3 sentences explaining the most important finding]
+
+## What's Driving This
+1. [Factor 1]
+2. [Factor 2]
+
+## Recommended Action
+[Specific, actionable recommendation]
+
+## Methodology Note
+[One line on data source and time period]
+```
+
+### Talking Points Format
+
+```markdown
+# [Topic] - Talking Points
+
+**Lead with**: "[Quote-ready key finding]"
+
+**If asked about trend**:
+[Context and explanation]
+
+**If asked about comparison to X**:
+[Relevant benchmark data]
+
+**If asked about next steps**:
+[Recommended actions]
+
+**Caveat to mention**:
+[Any important limitations]
+```
+
+## Quality Checklist
+
+- [ ] Insight stated in headline (not just topic)
+- [ ] Data source and time period clear
+- [ ] Visualizations have descriptive titles
+- [ ] Comparison context provided
+- [ ] "So what" answered explicitly
+- [ ] Recommendation is specific and actionable
+- [ ] Appropriate for audience expertise level
+- [ ] Caveats and limitations noted
diff --git a/skills/github-actions-builder/SKILL.md b/skills/github-actions-builder/SKILL.md
new file mode 100644
index 000000000..e0daa0bbb
--- /dev/null
+++ b/skills/github-actions-builder/SKILL.md
@@ -0,0 +1,443 @@
+---
+name: github-actions-builder
+description: Create and optimize GitHub Actions CI/CD workflows. Use when users need to set up automated testing, deployment pipelines, release automation, or any GitHub Actions workflow. Triggers on requests like "create a GitHub Action", "set up CI/CD", "automate deployment", "github workflow", "actions pipeline", or "automate releases".
+---
+
+# GitHub Actions Builder
+
+Create efficient, maintainable CI/CD workflows for GitHub repositories.
+
+## Workflow Structure
+
+### Basic Workflow Anatomy
+
+```yaml
+name: CI                          # Display name in GitHub UI
+
+on:                               # Trigger events
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+permissions:                      # Explicit permissions (security best practice)
+  contents: read
+
+jobs:
+  build:                          # Job identifier
+    runs-on: ubuntu-latest        # Runner environment
+
+    steps:
+      - uses: actions/checkout@v4 # Clone repository
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+
+      - name: Install dependencies
+        run: npm ci
+
+      - name: Run tests
+        run: npm test
+```
+
+## Common Workflow Patterns
+
+### Pull Request Checks
+
+```yaml
+name: PR Checks
+
+on:
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+  pull-requests: write
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+
+      - run: npm ci
+      - run: npm run lint
+      - run: npm test
+
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+      - run: npm ci
+      - run: npm run build
+```
+
+### Release on Tag
+
+```yaml
+name: Release
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+permissions:
+  contents: write
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'npm'
+
+      - run: npm ci
+      - run: npm run build
+
+      - name: Create Release
+        uses: softprops/action-gh-release@v1
+        with:
+          files: dist/*
+          generate_release_notes: true
+```
+
+### Scheduled Jobs
+
+```yaml
+name: Nightly Build
+
+on:
+  schedule:
+    - cron: '0 0 * * *'  # Daily at midnight UTC
+  workflow_dispatch:      # Allow manual trigger
+
+jobs:
+  nightly:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - run: npm ci
+      - run: npm run build
+      - run: npm run e2e-tests
+```
+
+### Matrix Builds
+
+```yaml
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest, macos-latest]
+        node-version: [18, 20, 22]
+      fail-fast: false  # Continue other jobs if one fails
+
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: ${{ matrix.node-version }}
+      - run: npm ci
+      - run: npm test
+```
+
+## Language-Specific Patterns
+
+### Node.js
+
+```yaml
+- uses: actions/setup-node@v4
+  with:
+    node-version: '20'
+    cache: 'npm'
+
+- run: npm ci              # Use ci for reproducible builds
+- run: npm run build
+- run: npm test
+```
+
+### Python
+
+```yaml
+- uses: actions/setup-python@v5
+  with:
+    python-version: '3.12'
+    cache: 'pip'
+
+- run: pip install -r requirements.txt
+- run: pytest
+```
+
+### Go
+
+```yaml
+- uses: actions/setup-go@v5
+  with:
+    go-version: '1.22'
+
+- run: go mod download
+- run: go build ./...
+- run: go test ./...
+```
+
+### Rust
+
+```yaml
+- uses: dtolnay/rust-toolchain@stable
+
+- uses: Swatinem/rust-cache@v2
+
+- run: cargo build --release
+- run: cargo test
+```
+
+### Docker
+
+```yaml
+- uses: docker/setup-buildx-action@v3
+
+- uses: docker/login-action@v3
+  with:
+    registry: ghcr.io
+    username: ${{ github.actor }}
+    password: ${{ secrets.GITHUB_TOKEN }}
+
+- uses: docker/build-push-action@v5
+  with:
+    push: ${{ github.event_name != 'pull_request' }}
+    tags: ghcr.io/${{ github.repository }}:latest
+    cache-from: type=gha
+    cache-to: type=gha,mode=max
+```
+
+## Job Dependencies and Outputs
+
+### Sequential Jobs
+
+```yaml
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    outputs:
+      version: ${{ steps.version.outputs.version }}
+    steps:
+      - id: version
+        run: echo "version=$(cat VERSION)" >> $GITHUB_OUTPUT
+
+  deploy:
+    needs: build  # Waits for build to complete
+    runs-on: ubuntu-latest
+    steps:
+      - run: echo "Deploying version ${{ needs.build.outputs.version }}"
+```
+
+### Conditional Jobs
+
+```yaml
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    # ... test steps
+
+  deploy-staging:
+    needs: test
+    if: github.ref == 'refs/heads/main'
+    runs-on: ubuntu-latest
+    # ... deploy steps
+
+  deploy-production:
+    needs: deploy-staging
+    if: github.event_name == 'release'
+    runs-on: ubuntu-latest
+    # ... deploy steps
+```
+
+## Secrets and Environment Variables
+
+### Using Secrets
+
+```yaml
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Deploy
+        env:
+          API_KEY: ${{ secrets.API_KEY }}
+        run: ./deploy.sh
+```
+
+### Environments
+
+```yaml
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    environment: production  # Uses secrets from "production" environment
+    steps:
+      - name: Deploy to production
+        run: ./deploy.sh
+```
+
+## Caching Strategies
+
+### Dependency Caching
+
+```yaml
+# Node.js (automatic with setup-node)
+- uses: actions/setup-node@v4
+  with:
+    cache: 'npm'
+
+# Manual cache
+- uses: actions/cache@v4
+  with:
+    path: ~/.npm
+    key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
+    restore-keys: |
+      ${{ runner.os }}-node-
+```
+
+### Build Artifact Caching
+
+```yaml
+- uses: actions/cache@v4
+  with:
+    path: |
+      .next/cache
+      node_modules/.cache
+    key: ${{ runner.os }}-build-${{ hashFiles('**/package-lock.json') }}-${{ hashFiles('**/*.ts', '**/*.tsx') }}
+    restore-keys: |
+      ${{ runner.os }}-build-${{ hashFiles('**/package-lock.json') }}-
+```
+
+## Reusable Workflows
+
+### Define Reusable Workflow
+
+```yaml
+# .github/workflows/reusable-deploy.yml
+name: Reusable Deploy
+
+on:
+  workflow_call:
+    inputs:
+      environment:
+        required: true
+        type: string
+    secrets:
+      deploy_key:
+        required: true
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    environment: ${{ inputs.environment }}
+    steps:
+      - uses: actions/checkout@v4
+      - run: ./deploy.sh
+        env:
+          DEPLOY_KEY: ${{ secrets.deploy_key }}
+```
+
+### Use Reusable Workflow
+
+```yaml
+jobs:
+  deploy-staging:
+    uses: ./.github/workflows/reusable-deploy.yml
+    with:
+      environment: staging
+    secrets:
+      deploy_key: ${{ secrets.STAGING_DEPLOY_KEY }}
+```
+
+## Security Best Practices
+
+### Minimal Permissions
+
+```yaml
+permissions:
+  contents: read      # Only what's needed
+  pull-requests: write
+
+# Or per-job
+jobs:
+  build:
+    permissions:
+      contents: read
+```
+
+### Pin Action Versions
+
+```yaml
+# Good: pinned to commit SHA
+- uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11
+
+# Acceptable: pinned to major version
+- uses: actions/checkout@v4
+
+# Avoid: unpinned or mutable tags
+- uses: actions/checkout@main
+```
+
+### Secrets in Pull Requests
+
+```yaml
+# Don't expose secrets to PRs from forks
+jobs:
+  test:
+    if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository
+    steps:
+      - run: ./test.sh
+        env:
+          SECRET: ${{ secrets.MY_SECRET }}
+```
+
+## Debugging
+
+### Enable Debug Logging
+
+Set repository secret:
+- `ACTIONS_STEP_DEBUG` = `true`
+- `ACTIONS_RUNNER_DEBUG` = `true`
+
+### Debug Step
+
+```yaml
+- name: Debug info
+  run: |
+    echo "Event: ${{ github.event_name }}"
+    echo "Ref: ${{ github.ref }}"
+    echo "SHA: ${{ github.sha }}"
+    echo "Actor: ${{ github.actor }}"
+```
+
+## Workflow Checklist
+
+- [ ] Explicit `permissions` block (least privilege)
+- [ ] Actions pinned to specific versions
+- [ ] Dependency caching enabled
+- [ ] `fail-fast: false` for matrix if appropriate
+- [ ] Timeouts set for long-running jobs
+- [ ] Concurrency controls if needed
+- [ ] Secrets not exposed to fork PRs
diff --git a/skills/quiz-generator/SKILL.md b/skills/quiz-generator/SKILL.md
new file mode 100644
index 000000000..25d01c680
--- /dev/null
+++ b/skills/quiz-generator/SKILL.md
@@ -0,0 +1,281 @@
+---
+name: quiz-generator
+description: Generate quizzes, assessments, and decision-tree evaluations from content. Use when users need to create knowledge checks, certification tests, learning assessments, diagnostic decision trees, or interactive evaluations. Triggers on requests like "create a quiz", "make assessment questions", "build a knowledge check", "generate test questions", "create a decision tree", or "diagnostic flowchart".
+---
+
+# Quiz Generator
+
+Transform content into effective assessments using varied question types and decision-tree logic.
+
+## Assessment Types
+
+### Knowledge Checks
+Quick verification of understanding after learning content.
+
+### Certification Tests
+Formal assessments with scoring thresholds and documented outcomes.
+
+### Diagnostic Decision Trees
+Branching logic that guides users to conclusions based on responses.
+
+### Self-Assessments
+Reflective evaluations for personal development.
+
+## Question Types
+
+### Multiple Choice
+
+```markdown
+**Q1. [Question stem - clear, single concept]**
+
+A) [Plausible distractor]
+B) [Correct answer]
+C) [Common misconception]
+D) [Plausible distractor]
+
+*Correct: B*
+*Explanation: [Why B is correct and why others are wrong]*
+```
+
+Design principles:
+- Stem contains the full question; options complete it
+- All options grammatically consistent
+- Avoid "all of the above" / "none of the above"
+- Distractors based on real misconceptions
+
+### True/False with Justification
+
+```markdown
+**Q2. [Statement]**
+
+- [ ] True
+- [ ] False
+
+*Correct: [True/False]*
+*Justification required: Explain your reasoning in 1-2 sentences.*
+```
+
+### Matching
+
+```markdown
+**Q3. Match each [item type] with its [property]:**
+
+| Item | Property |
+|------|----------|
+| 1. [Item A] | A) [Property X] |
+| 2. [Item B] | B) [Property Y] |
+| 3. [Item C] | C) [Property Z] |
+
+*Answers: 1-B, 2-C, 3-A*
+```
+
+### Ordering/Sequencing
+
+```markdown
+**Q4. Arrange these steps in the correct order:**
+
+- [ ] Step C
+- [ ] Step A
+- [ ] Step D
+- [ ] Step B
+
+*Correct order: A, B, C, D*
+```
+
+### Scenario-Based
+
+```markdown
+**Q5. Scenario:**
+[Realistic situation with relevant details]
+
+**Question:** [What action/decision/analysis is needed?]
+
+A) [Option addressing scenario]
+B) [Option addressing scenario]
+C) [Option addressing scenario]
+D) [Option addressing scenario]
+
+*Correct: [Letter]*
+*Rationale: [Why this is the best response given the scenario]*
+```
+
+## Decision Tree Structure
+
+### Basic Flow
+
+```markdown
+# [Diagnostic Title]
+
+## Start
+
+**Question 1: [Initial assessment question]**
+
+→ If YES: Go to Question 2A
+→ If NO: Go to Question 2B
+→ If UNSURE: [Clarification or default path]
+
+---
+
+## Question 2A: [Follow-up for YES path]
+
+→ If [Condition]: **Result A** - [Conclusion/recommendation]
+→ If [Other condition]: Go to Question 3A
+
+---
+
+## Question 2B: [Follow-up for NO path]
+
+→ If [Condition]: **Result B** - [Conclusion/recommendation]
+→ If [Other condition]: Go to Question 3B
+```
+
+### Decision Tree with Scoring
+
+```markdown
+# [Assessment Title]
+
+Track your score as you proceed.
+
+## Q1: [Question]
+- Yes (+2 points) → Q2
+- Somewhat (+1 point) → Q2
+- No (0 points) → Q3
+
+## Q2: [Question]
+...
+
+## Results
+
+**Score 8-10**: [Category A outcome]
+**Score 5-7**: [Category B outcome]
+**Score 0-4**: [Category C outcome]
+```
+
+### Diagnostic Flowchart Format
+
+```
+┌─────────────────────────┐
+│    START: [Symptom]     │
+└───────────┬─────────────┘
+            │
+            ▼
+    ┌───────────────┐
+    │ [Question 1]? │
+    └───────┬───────┘
+       YES/ \NO
+         /   \
+        ▼     ▼
+   [Path A] [Path B]
+        │     │
+        ▼     ▼
+   [Result] [Next Q]
+```
+
+## Content-to-Quiz Workflow
+
+### 1. Analyze Source Material
+
+Extract:
+- Key concepts (definitions, principles)
+- Procedures (sequences, steps)
+- Relationships (cause-effect, compare-contrast)
+- Common errors/misconceptions
+
+### 2. Define Learning Objectives
+
+Map questions to objectives:
+
+| Objective | Bloom's Level | Question Type |
+|-----------|---------------|---------------|
+| Define terms | Remember | Multiple choice, matching |
+| Explain process | Understand | Ordering, short answer |
+| Apply procedure | Apply | Scenario-based |
+| Diagnose issues | Analyze | Decision tree |
+| Evaluate options | Evaluate | Case study |
+
+### 3. Generate Questions
+
+For each objective, create questions that:
+- Test ONE concept per question
+- Use vocabulary from source material
+- Include realistic distractors
+- Provide explanatory feedback
+
+### 4. Build Decision Logic
+
+For diagnostic assessments:
+- Identify the possible outcomes first
+- Work backward to discriminating questions
+- Ensure all paths lead to defined outcomes
+- Add escape routes for edge cases
+
+## Quality Standards
+
+### Question Quality
+- [ ] Clear, unambiguous stem
+- [ ] Single correct answer (or clearly defined criteria)
+- [ ] Distractors are plausible but clearly wrong
+- [ ] No trick questions or gotchas
+- [ ] Appropriate difficulty for audience
+
+### Assessment Quality
+- [ ] Covers all learning objectives
+- [ ] Balanced difficulty distribution
+- [ ] Clear instructions and scoring
+- [ ] Feedback explains correct answers
+- [ ] Time estimate provided
+
+### Decision Tree Quality
+- [ ] All paths lead to defined outcomes
+- [ ] No dead ends or loops
+- [ ] Clear, binary decision points
+- [ ] Edge cases handled
+- [ ] Can be followed without expert knowledge
+
+## Output Formats
+
+### Interactive HTML Quiz
+
+```html
+<!-- Quiz container with JavaScript for scoring -->
+<div class="quiz" data-passing-score="80">
+  <div class="question" data-correct="b">
+    <p>Question text</p>
+    <label><input type="radio" name="q1" value="a"> Option A</label>
+    <label><input type="radio" name="q1" value="b"> Option B</label>
+  </div>
+</div>
+```
+
+### Printable Assessment
+
+```markdown
+# [Assessment Title]
+**Time allowed**: [X minutes]
+**Passing score**: [X]%
+
+## Instructions
+[How to complete and submit]
+
+## Questions
+[Numbered questions with answer spaces]
+
+---
+## Answer Key (Instructor Copy)
+[Answers with point values and explanations]
+```
+
+### Decision Tree Document
+
+```markdown
+# [Diagnostic Name]
+
+## How to Use
+Start at Question 1. Follow the arrows based on your answers.
+
+## Flowchart
+[Visual or text-based decision tree]
+
+## Outcome Definitions
+[Detailed explanation of each possible result]
+```
diff --git a/skills/rfc-architect/SKILL.md b/skills/rfc-architect/SKILL.md
new file mode 100644
index 000000000..444b583fd
--- /dev/null
+++ b/skills/rfc-architect/SKILL.md
@@ -0,0 +1,292 @@
+---
+name: rfc-architect
+description: Design and structure technical RFCs, design documents, and decision records. Use when users need to write technical proposals, architecture decision records (ADRs), design docs, or technical specifications that require stakeholder input and approval. Triggers on requests like "write an RFC", "create a design doc", "architecture decision record", "technical proposal", or "document this design decision".
+---
+
+# RFC Architect
+
+Create structured technical decision documents that clearly communicate proposals, trade-offs, and rationale.
+
+## Document Types
+
+### RFC (Request for Comments)
+Formal proposal seeking feedback before implementation. Used for significant changes.
+
+### Design Doc
+Technical specification for how something will be built. More implementation-focused.
+
+### ADR (Architecture Decision Record)
+Lightweight record of a specific decision and its context. Good for building decision history.
+
+## RFC Template
+
+```markdown
+# RFC: [Title]
+
+**Status**: Draft | In Review | Accepted | Rejected | Superseded
+**Author(s)**: [Names]
+**Created**: [Date]
+**Last Updated**: [Date]
+**Reviewers**: [Names]
+
+## Summary
+
+[2-3 sentences describing what this RFC proposes]
+
+## Motivation
+
+### Problem Statement
+[What problem are we solving? Why now?]
+
+### Goals
+- [Goal 1]
+- [Goal 2]
+
+### Non-Goals
+- [Explicitly out of scope]
+
+## Proposal
+
+### Overview
+[High-level description of the proposed solution]
+
+### Detailed Design
+
+#### [Component/Aspect 1]
+[Technical details, diagrams if helpful]
+
+#### [Component/Aspect 2]
+[Continue for each major component]
+
+### API/Interface Changes
+[If applicable: new endpoints, function signatures, etc.]
+
+```python
+# Example code or pseudocode
+```
+
+## Alternatives Considered
+
+### Alternative 1: [Name]
+**Description**: [What this option looks like]
+**Pros**:
+- [Advantage]
+**Cons**:
+- [Disadvantage]
+**Why not chosen**: [Reason]
+
+### Alternative 2: [Name]
+[Same structure]
+
+## Trade-offs and Risks
+
+| Decision | Trade-off |
+|----------|-----------|
+| [Choice] | [What we give up for what we gain] |
+
+### Risks
+- **Risk 1**: [Description] — Mitigation: [How we'll address it]
+- **Risk 2**: [Description] — Mitigation: [How we'll address it]
+
+## Migration/Rollout Strategy
+
+### Phase 1: [Name]
+- [Steps]
+- Success criteria: [How we know it worked]
+
+### Phase 2: [Name]
+[Continue as needed]
+
+### Rollback Plan
+[How to undo if needed]
+
+## Dependencies
+
+- [System/team this depends on]
+- [External service]
+
+## Open Questions
+
+- [ ] [Question needing resolution before proceeding]
+- [ ] [Another question]
+
+## References
+
+- [Link to related doc]
+- [Prior art / inspiration]
+```
+
+## ADR Template (Lightweight)
+
+For recording decisions without full RFC process:
+
+```markdown
+# ADR-[NUMBER]: [Title]
+
+**Date**: [Date]
+**Status**: Proposed | Accepted | Deprecated | Superseded by ADR-XXX
+
+## Context
+
+[What situation led to this decision? What constraints exist?]
+
+## Decision
+
+[What did we decide? State it clearly.]
+
+## Consequences
+
+### Positive
+- [Benefit 1]
+- [Benefit 2]
+
+### Negative
+- [Trade-off 1]
+- [Trade-off 2]
+
+### Neutral
+- [Other implications]
+```
+
+## Decision Matrix
+
+When comparing options, use a decision matrix:
+
+```markdown
+## Evaluation Matrix
+
+| Criteria (weight) | Option A | Option B | Option C |
+|-------------------|----------|----------|----------|
+| Performance (3)   | 3 (9)    | 2 (6)    | 3 (9)    |
+| Simplicity (2)    | 2 (4)    | 3 (6)    | 1 (2)    |
+| Cost (2)          | 1 (2)    | 2 (4)    | 3 (6)    |
+| Team familiarity (1) | 3 (3) | 2 (2)    | 1 (1)    |
+| **Total**         | **18**   | **18**   | **18**   |
+
+Scoring: 1 = Poor, 2 = Adequate, 3 = Excellent
+Weighted score in parentheses
+```
+
+## Writing Effective Sections
+
+### Motivation
+
+Bad:
+> We should use Kafka.
+
+Good:
+> Our current message queue drops messages under peak load (3x in the past month),
+> causing data inconsistencies that require manual intervention. We need a more
+> reliable messaging system that can handle our projected 10x traffic growth.
+
+### Alternatives
+
+Always include at least:
+1. **Do nothing** - What happens if we don't act?
+2. **Minimal change** - Smallest intervention that might work
+3. **Proposed solution** - Your recommendation
+4. **Ambitious option** - If resources were unlimited
+
+### Trade-offs
+
+Make trade-offs explicit:
+
+```markdown
+## Trade-offs
+
+We're choosing **consistency over availability**: During network partitions,
+the system will reject writes rather than risk data inconsistency.
+
+We're choosing **simplicity over flexibility**: Using a fixed schema means
+less runtime configuration but requires code changes for new fields.
+```
+
+## Review Process Guidance
+
+### Before Review
+- [ ] All sections complete (mark unknowns explicitly)
+- [ ] Diagrams clear without explanation
+- [ ] Alternatives genuinely considered
+- [ ] Dependencies identified and owners notified
+- [ ] Open questions are real blockers, not padding
+
+### During Review
+Expect feedback on:
+- Missing alternatives
+- Underestimated risks
+- Unclear migration path
+- Missing stakeholder concerns
+
+### After Acceptance
+- Update status to "Accepted"
+- Create implementation tasks
+- Share final version widely
+- Archive for future reference
+
+## Common Patterns
+
+### The "Strangler Fig" Migration
+
+```markdown
+## Migration Strategy
+
+We'll incrementally replace the old system:
+
+1. **Proxy Phase**: New system proxies to old
+   - Duration: 2 weeks
+   - Rollback: Disable proxy
+
+2. **Parallel Phase**: Both systems process, compare results
+   - Duration: 4 weeks
+   - Success: <0.1% discrepancy
+
+3. **Cutover Phase**: New system primary, old as fallback
+   - Duration: 2 weeks
+   - Rollback: Swap traffic back
+
+4. **Retirement**: Decommission old system
+   - After 30 days of stable operation
+```
+
+### The "Feature Flag" Rollout
+
+```markdown
+## Rollout Strategy
+
+1. **Internal**: Enable for employees (1 week)
+2. **Canary**: 1% of production traffic (1 week)
+3. **Gradual**: 10% → 50% → 100% (2 weeks each)
+
+Rollback: Disable feature flag (immediate)
+```
+
+## Anti-Patterns to Avoid
+
+| Anti-Pattern | Problem | Instead |
+|--------------|---------|---------|
+| "Obviously we should..." | Assumes consensus | State reasoning explicitly |
+| No alternatives | Looks predetermined | Always show options considered |
+| Vague migration | Scares stakeholders | Break into concrete phases |
+| No rollback plan | Single point of failure | Always have an undo strategy |
+| Hidden trade-offs | Erodes trust | Make downsides explicit |
+
+## Naming Conventions
+
+### RFC Numbers
+- Sequential: RFC-001, RFC-002
+- Or date-based: RFC-2024-03-AUTH
+
+### ADR Numbers
+- Sequential: ADR-0001, ADR-0002
+- Keep a central index
+
+### File Organization
+```
+docs/
+├── rfcs/
+│   ├── RFC-001-new-auth-system.md
+│   └── RFC-002-database-migration.md
+└── adrs/
+    ├── 0001-use-postgresql.md
+    └── 0002-adopt-typescript.md
+```
diff --git a/skills/tutorial-builder/SKILL.md b/skills/tutorial-builder/SKILL.md
new file mode 100644
index 000000000..c43d42fac
--- /dev/null
+++ b/skills/tutorial-builder/SKILL.md
@@ -0,0 +1,211 @@
+---
+name: tutorial-builder
+description: Create step-by-step tutorials, operating manuals, and procedural documentation. Use when users need to document processes, create how-to guides, write operating procedures, build training materials, or develop equipment/software manuals. Triggers on requests like "create a tutorial", "write operating procedures", "document this process", "make a how-to guide", "build a training manual", or "step-by-step instructions".
+---
+
+# Tutorial Builder
+
+Create clear, actionable procedural documentation that guides users through tasks with precision and safety.
+
+## Document Types
+
+### Operating Manuals
+Equipment/system operation with safety protocols, startup/shutdown sequences, and troubleshooting.
+
+### Tutorials
+Learning-focused guides that build understanding progressively.
+
+### Standard Operating Procedures (SOPs)
+Formal procedures with compliance requirements and sign-off checkpoints.
+
+### Quick Reference Guides
+Condensed procedures for experienced users.
+
+## Creation Workflow
+
+### 1. Scope Definition
+
+Gather essential context:
+- **Audience**: Skill level, prior knowledge, role
+- **Objective**: What can they do after completing this?
+- **Environment**: Tools, equipment, software versions
+- **Constraints**: Safety requirements, compliance needs, time limits
+
+### 2. Task Analysis
+
+Break the procedure into components:
+
+```
+PROCEDURE: [Name]
+├── Prerequisites (what must be true before starting)
+├── Materials/Tools (what's needed)
+├── Phase 1: [Name]
+│   ├── Step 1.1
+│   ├── Step 1.2 (decision point?)
+│   └── Step 1.3
+├── Phase 2: [Name]
+│   └── ...
+├── Verification (how to confirm success)
+└── Troubleshooting (common issues)
+```
+
+### 3. Step Structure
+
+Each step follows this pattern:
+
+```markdown
+## Step N: [Action Verb] [Object]
+
+**Purpose**: Why this step matters
+
+**Action**:
+[Clear, imperative instruction]
+
+**Expected Result**:
+[What should happen when done correctly]
+
+**Checkpoint**: [ ] [Verification the user can perform]
+
+> **Warning**: [Safety/critical information if applicable]
+
+> **Tip**: [Helpful but non-essential information]
+```
+
+### 4. Decision Points
+
+When procedures branch, use decision trees:
+
+```markdown
+### Decision: [Question to answer]
+
+**If [Condition A]**:
+→ Proceed to Step N
+
+**If [Condition B]**:
+→ Proceed to Step M
+
+**If unsure**:
+→ See Troubleshooting section
+```
+
+## Writing Principles
+
+### Imperative Voice
+- Write: "Open the valve"
+- Not: "The valve should be opened"
+
+### One Action Per Step
+- Write: "1. Turn off power. 2. Unplug device."
+- Not: "1. Turn off power and unplug device."
+
+### Specific Over Vague
+- Write: "Wait 30 seconds"
+- Not: "Wait a moment"
+
+### Observable Verification
+- Write: "Green LED illuminates"
+- Not: "System is ready"
+
+## Safety Integration
+
+### Warning Hierarchy
+
+```markdown
+> **DANGER**: Immediate risk of death or serious injury
+> [Specific hazard and required action]
+
+> **WARNING**: Potential risk of injury or equipment damage
+> [Specific hazard and required action]
+
+> **CAUTION**: Risk of minor injury or operational issue
+> [Specific hazard and recommended action]
+
+> **NOTICE**: Important information, no safety risk
+> [Relevant information]
+```
+
+Place warnings BEFORE the step they apply to, not after.
+
+### Critical Checkpoints
+
+For safety-critical procedures, add mandatory verification:
+
+```markdown
+## HOLD POINT: [Name]
+
+Do not proceed until:
+- [ ] [Verification 1]
+- [ ] [Verification 2]
+- [ ] Supervisor sign-off (if required)
+```
+
+## Output Formats
+
+### Full Manual Structure
+
+```markdown
+# [Equipment/System] Operating Manual
+
+## Overview
+- Purpose and scope
+- Safety summary
+- Required qualifications
+
+## Quick Reference
+- Emergency procedures
+- Key specifications
+
+## Procedures
+### Startup
+### Normal Operation
+### Shutdown
+### Emergency Shutdown
+
+## Maintenance
+### Daily checks
+### Periodic maintenance
+
+## Troubleshooting
+### Symptom → Cause → Solution tables
+
+## Appendices
+- Specifications
+- Parts lists
+- Revision history
+```
+
+### Tutorial Structure
+
+```markdown
+# [Title]: [Outcome]
+
+## What You'll Learn
+- Objective 1
+- Objective 2
+
+## Prerequisites
+- Required knowledge
+- Required tools/materials
+
+## Steps
+[Numbered procedures with checkpoints]
+
+## Summary
+- Key takeaways
+- Next steps
+
+## Practice Exercises
+[Application tasks to reinforce learning]
+```
+
+## Quality Checklist
+
+Before finalizing:
+- [ ] Every step has a single, clear action
+- [ ] All warnings appear before relevant steps
+- [ ] Prerequisites are complete and specific
+- [ ] Verification points exist for critical steps
+- [ ] Technical terms are defined on first use
+- [ ] Illustrations/diagrams referenced where helpful
+- [ ] Troubleshooting covers common failure modes
+- [ ] Document tested by someone unfamiliar with procedure