Conversation
maheshmurag
approved these changes
Oct 16, 2025
chyax98
pushed a commit
to chyax98/skills
that referenced
this pull request
Oct 26, 2025
**问题**: 分隔符规则描述过于技术化,用户难以理解 **改进**: 1. 简化核心规则表述 - 技术算法 → 用户友好说明 - "标题 = 分页符" 核心理念 2. 添加 4 个实际示例 ✅ 标准场景: H2 章节 + H3 页面 ✅ 单层标题: 仅 H2 ❌ 无法分页: 标题仅出现 1 次 ❌ 层级跳跃: H2 → H4 3. 添加最佳实践指导 - 推荐结构示例 - 手动分页备选方案 - 常见问题解决表格 **影响**: 用户现在能清楚理解 md2ppt 自动分页机制 修复 anthropics#1 (分隔符规则不明确)
TyceHerrman
pushed a commit
to ulama-tech/skills
that referenced
this pull request
Oct 27, 2025
* Rename to document-skills * rearrange
Okeysir198
referenced
this pull request
in Okeysir198/P20251122-claude-skills
Nov 21, 2025
⚠️ PRODUCTION BLOCKER IDENTIFIED⚠️ After comprehensive execution flow analysis, discovered critical deadlock in streaming implementation that will cause hangs in production. Critical Bug #1: DEADLOCK in end_input() Flow --------------------------------------------- - When end_input() is called, client stops sending audio - Client does NOT notify server that streaming is complete - Server waits for more audio indefinitely - Client waits for final transcriptions indefinitely - MUTUAL DEADLOCK - both sides waiting forever Current Flow (BROKEN): 1. User calls stream.end_input() 2. _send_loop() receives None sentinel and exits 3. But _send_loop() does NOT send end-of-stream message to server 4. Server continues waiting for audio 5. _recv_loop() waits for server messages 6. User waits for async iteration to complete 7. DEADLOCK Impact: - Any code using end_input() will hang indefinitely - Tests only pass because they use timeouts + explicit aclose() - Will cause production outages Reproduction: ```python stream = stt.stream() # ... push frames ... await stream.end_input() async for event in stream: # HANGS FOREVER print(event) ``` Additional Bugs Found: --------------------- - Bug #2: Multiple None sentinels queued (end_input + aclose) - Bug #3: Frames accepted after end_input() (silent data loss) - Bug #5: Unnecessary None queued in aclose() before cancellation Files Added: - CRITICAL_BUGS.md - Detailed execution trace and bug analysis - FIXES_REQUIRED.md - Complete fix implementation with code Current Status: ❌ NOT PRODUCTION READY Next Steps: Implement fixes in FIXES_REQUIRED.md (~3 hours) Tests pass currently only due to timeout workarounds masking the deadlock.
Ashutosh0x
pushed a commit
to Ashutosh0x/skills
that referenced
this pull request
Feb 5, 2026
Support Goose, Roo, Amp, and Kilo
2SP2026
added a commit
to 2SP2026/skills
that referenced
this pull request
Feb 5, 2026
- NEW: Poly-Computing architecture as priority anthropics#1 audit item - UPDATED: Focus on hardware-aware optimization (CUDA/MPS/CPU) - UPDATED: Check for dynamic hardware dispatchers - UPDATED: Verify vectorized/GPU-accelerated compute loops - UPDATED: Ensure fallback paths for all hardware-optimized logic Reflects lessons learned from 2SP LiDAR Analysis v7.5.0 Poly-Computing implementation.
xjrmh
pushed a commit
to xjrmh/skills
that referenced
this pull request
Mar 3, 2026
panchoavila
added a commit
to panchoavila/skills
that referenced
this pull request
Mar 10, 2026
…ketplace-cgeiN
conorbronsdon
added a commit
to conorbronsdon/skills
that referenced
this pull request
Mar 27, 2026
Major changes since initial submission: - Tiered vocabulary system (103 entries across 3 severity tiers) - Severity tiers (P0/P1/P2) for triage prioritization - Context profiles with tolerance matrix (linkedin, blog, technical-blog, investor-email, docs, casual) - 13 new pattern categories (reasoning chain artifacts, sycophantic tone, acknowledgment loops, false concession, rhetorical questions, etc.) - Rhythm and uniformity detection (structure as anthropics#1 AI detection signal) - Rewrite-from-scratch threshold guidance - Self-reference escape hatch for meta-writing - agentskills.io and OpenClaw compatibility
seanphan
added a commit
to PixelML/skills
that referenced
this pull request
Apr 4, 2026
v1 skills were LLM-only (chat). v2 adds workflows that USE the platform: New workflows (web_scraping + LLM nodes): - competitor-scrape: scrape 3 competitor Amazon listings → AI analysis Uses web_scraping node (no connection needed) + LLM for comparison - listing-audit: scrape YOUR listing → audit + optimized replacements Real data, not guesswork about your current title/bullets - review-scrape-respond: scrape review page → sentiment + draft responses References actual customer quotes, not generic templates These workflows use AgenticFlow's web_scraping node to get REAL Amazon data, then LLM to analyze it. This was the anthropics#1 gap from the seller test — competitive analysis failed because agents had no data access. Now they do. Platform nodes leveraged: web_scraping, llm Available but not yet used: mcp_run_action (2674 integrations), firecrawl_scrape/extract, api_call, query_data
This was referenced Apr 8, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.