Release v1.30.0: Add competitors-analysis skill

New Skill: competitors-analysis

Evidence-based competitor tracking and analysis. All analysis must be based on actual code, never assumptions.

Features

• Pre-analysis checklist to ensure repositories are cloned locally before any analysis
• Forbidden patterns to prevent assumptions ("推测...", "可能...", "应该...")
• Required patterns for source citation (file:line_number format)
• Tech stack analysis guides for Node.js, Python, Rust projects
• Directory structure conventions for organized competitor tracking
• Bundled templates: profile_template.md, analysis_checklist.md
• Management script: update-competitors.sh (clone/pull/status)

Installation

claude plugin marketplace update daymade-skills
claude plugin install competitors-analysis@daymade-skills

Usage

# Then ask Claude to analyze a competitor
"分析竞品 https://github.com/org/repo"
"添加竞品到 flowzero 产品的竞品列表"

Full Changelog

See CHANGELOG.md for complete changes.

---

🤖 Generated with Claude Code

Release v1.29.0: Enhance skill-creator with YAML frontmatter documentation

Enhanced Skill: skill-creator v1.4.0

This release significantly improves skill-creator documentation based on community contribution (PR #6 by @costa-marcello).

New Features

• Complete YAML Frontmatter Reference: Comprehensive table documenting all available fields (name, description, context, agent, disable-model-invocation, user-invocable, allowed-tools, model, argument-hint, hooks)

• context: fork Documentation: Critical guidance for creating skills accessible to subagents via Task tool

• Invocation Control Table: Clear comparison showing how different frontmatter combinations affect skill accessibility (user invocable, Claude invocable, subagent accessible)

• $ARGUMENTS Placeholder: Documented how skill content can receive user input via /skill-name arguments

• Enhanced Examples:

  • Wildcard syntax for allowed-tools: Bash(git *), Bash(npm *), Bash(docker compose *)
  • Inline hooks configuration example
  • Task-based skill with subagent execution
  • Reference skill that runs inline

• Updated init_skill.py Template: New skills now include commented optional frontmatter fields

Installation

claude plugin marketplace update daymade-skills
claude plugin install skill-creator@daymade-skills

Contributors

• @costa-marcello - PR #6: Initial frontmatter documentation

---

🤖 Generated with Claude Code

Release v1.28.0: Enhance meeting-minutes-taker with speaker identification

Enhanced Skill: meeting-minutes-taker v1.1.0

Add speaker identification and pre-processing pipeline for better transcript processing.

New Features

Speaker Identification

Analyze transcript features to identify anonymous speakers:

Feature	What to Look For
Word count	Total words (high = senior/lead, low = observer)
Segment count	Speaking frequency (frequent = active participant)
Avg segment length	Words per turn (long = presenter, short = responder)
Filler ratio	% of filler words - low = prepared speaker

Context File Template

New references/context_file_template.md for team directory mapping:

• Team members with roles and communication styles
• Project terminology and naming conventions
• Automatic speaker matching based on features

Intelligent File Naming

Auto-generate output filename: YYYY-MM-DD-<topic>-<type>.md

Examples:

• 2026-01-25-order-api-design-review.md
• 2026-01-20-sprint-planning.md

Pre-processing Pipeline

Integrated with other skills:

• markdown-tools - Convert .docx/.pdf to Markdown first
• transcript-fixer - Fix ASR/STT errors before processing

Full Changelog

https://github.com/daymade/claude-code-skills/blob/main/CHANGELOG.md

Release v1.27.0: Enhance markdown-tools with Heavy Mode

Enhanced Skill: markdown-tools v1.2.0

Multi-tool orchestration for best-quality document-to-markdown conversion.

New Features

Dual Mode Architecture

Mode	Speed	Quality	Use Case
Quick	Fast	Good	Drafts, simple documents
Heavy	Slower	Best	Final documents, complex layouts

Tool Selection Matrix

Format	Quick Mode	Heavy Mode
PDF	pymupdf4llm	pymupdf4llm + markitdown
DOCX	pandoc	pandoc + markitdown
PPTX	markitdown	markitdown + pandoc

New Scripts

• convert.py - Main orchestrator with Quick/Heavy mode
• merge_outputs.py - Segment-level multi-tool output merger
• validate_output.py - Quality validation with HTML reports

Enhanced Scripts

• extract_pdf_images.py - Now includes metadata (page, position, dimensions)

Quality Metrics

Metric	Pass	Warn	Fail
Text Retention	>95%	85-95%	<85%
Table Retention	100%	90-99%	<90%
Image Retention	100%	80-99%	<80%

Installation

# Install dependencies
pip install pymupdf4llm
uv tool install "markitdown[pdf]"
brew install pandoc

# Quick conversion
uv run --with pymupdf4llm --with markitdown scripts/convert.py doc.pdf -o out.md

# Heavy Mode (best quality)
uv run --with pymupdf4llm --with markitdown scripts/convert.py doc.pdf -o out.md --heavy

# Quality validation
uv run --with pymupdf scripts/validate_output.py doc.pdf out.md --report report.html

Full Changelog

https://github.com/daymade/claude-code-skills/blob/main/CHANGELOG.md

Release v1.26.0: Add deep-research

New Skill: deep-research

Generate format-controlled research reports with evidence tracking, citations, and iterative review.

Features:

• Report spec and format contract workflow
• Multi-pass parallel drafting with UNION merge
• Evidence table with source quality rubric
• Citation verification and conflict handling
• Bundled references: report template, formatting rules, research plan checklist, source quality rubric, completeness checklist

Installation:

claude plugin install deep-research@daymade-skills

Changelog: See CHANGELOG.md for full details.

Release v1.25.0: Add meeting-minutes-taker and sanitization workflow

New Skill: meeting-minutes-taker

Transform meeting transcripts into high-fidelity, structured meeting minutes with iterative human review.

Features:

• Multi-pass parallel generation with UNION merge strategy
• Evidence-based recording with speaker quotes
• Mermaid diagrams for architecture discussions
• Iterative human-in-the-loop refinement workflow
• Cross-AI comparison for bias reduction
• Completeness checklist for systematic review

Installation:

claude plugin install meeting-minutes-taker@daymade-skills

skill-creator v1.3.0

Added Step 5: Sanitization Review (Optional) for extracting skills from business projects:

• 8 categories of content to sanitize (product names, person names, entities, paths, jargon, etc.)
• Automated grep scan commands for detecting sensitive content
• 3-phase sanitization process with verification
• New references/sanitization_checklist.md with detailed guidance

Full Changelog

• New skill: meeting-minutes-taker v1.0.0
• Updated skill-creator: v1.2.2 → v1.3.0
• Updated marketplace: v1.24.0 → v1.25.0
• Total skills: 33

Release v1.24.0: Add claude-skills-troubleshooting

v1.24.0 (2026-01-22)

Added

• New Skill: claude-skills-troubleshooting - Diagnose and resolve Claude Code plugin and skill configuration issues
  • Plugin installation and enablement debugging
  • installed_plugins.json vs settings.json enabledPlugins diagnosis
  • Marketplace cache freshness detection
  • Plugin state architecture documentation
  • Bundled diagnostic script (diagnose_plugins.py)
  • Batch enable script for missing plugins (enable_all_plugins.py)
  • Known GitHub issues tracking (#17832, #19696, #17089, #13543, #16260)
  • Skills vs Commands architecture explanation

Changed

• Updated marketplace skills count from 31 to 32
• Updated marketplace version from 1.23.0 to 1.24.0
• Updated README.md badges (skills count, version)
• Updated README.md to include claude-skills-troubleshooting in skills listing
• Updated README.zh-CN.md badges (skills count, version)
• Updated README.zh-CN.md to include claude-skills-troubleshooting in skills listing
• Updated CLAUDE.md skills count from 31 to 32
• Added claude-skills-troubleshooting use case section to README.md
• Added claude-skills-troubleshooting use case section to README.zh-CN.md

Release v1.21.1: Update macos-cleaner to v1.1.0

Updated Skill: macos-cleaner v1.1.0

Major improvements based on real-world usage experience with tmux + Mole deep exploration workflow.

New Principles

• Value Over Vanity: Goal is identifying truly useless items, not maximizing cleanup numbers
• Network Environment Awareness: Consider slow internet (especially in China) when recommending cache deletion
• Impact Analysis Required: Every cleanup recommendation must explain consequences

New Sections

• Anti-Patterns: Comprehensive guide on what NOT to delete (Xcode DerivedData, npm _cacache, uv cache, Playwright, iOS DeviceSupport, Docker stopped containers, AI model caches)
• Multi-Layer Deep Exploration: Complete tmux + Mole TUI navigation workflow with recommended exploration path
• High-Quality Report Template: Proven 3-tier classification report format (🟢 Absolutely Safe / 🟡 Trade-off Required / 🔴 Do Not Delete)
• Report Quality Checklist: 8-point verification before presenting findings

Safety Improvements

• Explicit prohibition of docker volume prune -f - must confirm per-project
• Updated safety principles to emphasize cache value over cleanup metrics

Installation

claude plugin marketplace update daymade-skills
claude plugin install macos-cleaner@daymade-skills

---

🤖 Generated with Claude Code

v1.19.0 - Fact-Checker Skill

🎉 New Skill: Fact-Checker v1.0.0

Comprehensive fact-checking skill that verifies claims using web search and official sources, then proposes corrections with user confirmation.

✨ Features

• 5-Step Workflow: Identify → Search → Compare → Report → Apply
• Multi-Domain Support: AI models, technical docs, statistics, general facts
• Source Evaluation: Prioritizes official documentation and authoritative sources
• User Approval Gates: Never applies changes without explicit confirmation
• Temporal Context: Adds date markers to prevent information decay

🎯 Use Cases

• Update outdated AI model specifications
• Verify technical documentation claims
• Validate statistical data and benchmarks
• Check version numbers and release dates

📝 Real-World Example

Successfully updated AI model context window specifications:

• Claude 3.5 Sonnet → Claude Sonnet 4.5
• GPT-4o (128K) → GPT-5.2 (400K)
• Gemini 1.5 Pro (2M) → Gemini 3 Pro (1M)

🚀 Installation

```bash
ccpm install @daymade-skills/fact-checker
```

🔑 Trigger Keywords

• "fact-check this document"
• "verify these claims"
• "check if this is accurate"
• "update outdated information"

📦 What's Changed

New:

• fact-checker skill v1.0.0 with comprehensive workflow
• Source evaluation framework
• Auto-correction with approval gates

Updated:

• Marketplace version bumped to 1.19.0
• Metadata description updated

Full Changelog: v1.18.1...v1.19.0

Release v1.10.0: Add qa-expert - Comprehensive QA Testing Infrastructure

🎉 New Skill: qa-expert

Comprehensive QA testing infrastructure with autonomous LLM execution, Google Testing Standards, and OWASP security best practices.

💡 Key Innovation: Autonomous Execution

The master prompt enables LLM to auto-execute entire test suites 100x faster than manual execution, with zero human error in tracking. Perfect for third-party QA handoffs - just provide the master prompt and they can start testing immediately.

✨ Key Features

• One-command initialization: Complete QA infrastructure with templates, CSVs, and documentation
• Autonomous execution: Master prompt enables LLM to auto-execute all tests, auto-track results, auto-file bugs
• Google Testing Standards: AAA pattern compliance, 90% coverage targets, fail-fast validation
• OWASP security testing: 90% Top 10 coverage with specific attack vectors
• Quality gates enforcement: 100% execution, ≥80% pass rate, 0 P0 bugs, ≥80% code coverage
• Ground Truth Principle: Prevents doc/CSV sync issues (test docs = authoritative source)
• Bug tracking: P0-P4 classification with detailed repro steps
• Day 1 onboarding: 5-hour guide for new QA engineers
• 30+ LLM prompts: Ready-to-use prompts for specific QA tasks
• Metrics dashboard: Test execution progress, pass rate, bug analysis, quality gates status

📦 Installation

claude plugin marketplace add daymade/claude-code-skills
claude plugin install qa-expert@daymade/claude-code-skills

🚀 Quick Start

# Initialize QA project (creates full infrastructure)
python3 scripts/init_qa_project.py my-app ./

# Calculate quality metrics and gates status
python3 scripts/calculate_metrics.py tests/TEST-EXECUTION-TRACKING.csv

# For autonomous execution, copy master prompt from:
# references/master_qa_prompt.md → paste to LLM → auto-executes tests

📚 Documentation

See qa-expert/references/ for:

• master_qa_prompt.md - Single command for autonomous execution (100x speedup)
• google_testing_standards.md - AAA pattern, coverage thresholds, OWASP testing
• day1_onboarding.md - 5-hour onboarding timeline for new QA engineers
• ground_truth_principle.md - Preventing doc/CSV sync issues
• llm_prompts_library.md - 30+ ready-to-use QA prompts

---

🔧 SOP Improvements

Enhanced "Adding a New Skill to Marketplace" workflow in CLAUDE.md:

• Added mandatory Step 7: Update README.zh-CN.md (Chinese documentation)
• Added 6 new checklist items: Chinese documentation verification
• Updated Common Mistakes: 8 comprehensive error reminders
• Made Chinese docs MANDATORY: README.zh-CN.md is now required
• Added sync verification commands: Ensure EN/ZH versions match

---

📊 Marketplace Status

• Total Skills: 17 production-ready skills
• Version: v1.10.0
• Categories: developer-tools, document-conversion, documentation, customization, communication, utilities, assets, design, productivity, security, media

See full CHANGELOG for detailed changes.