claude-code-skills-reference

firefrost-gaming/claude-code-skills-reference

Fork 0

Commit Graph

Author	SHA1	Message	Date
daymade	5c9eda4fbd	feat: optimize skills + add pipeline handoff chaining across 9 skills asr-transcribe-to-text: - Add local MLX transcription path (macOS Apple Silicon, 15-27x realtime) - Add bundled script transcribe_local_mlx.py with max_tokens=200000 - Add local_mlx_guide.md with benchmarks and truncation trap docs - Auto-detect platform and recommend local vs remote mode - Fix audio extraction format (MP3 → WAV 16kHz mono PCM) - Add Step 5: recommend transcript-fixer after transcription transcript-fixer: - Optimize SKILL.md from 289 → 153 lines (best practices compliance) - Move FALSE_POSITIVE_RISKS (40 lines) to references/false_positive_guide.md - Move Example Session to references/example_session.md - Improve description for better triggering (226 → 580 chars) - Add handoff to meeting-minutes-taker skill-creator: - Add "Pipeline Handoff" pattern to Skill Writing Guide - Add pipeline check reminder in Step 4 (Edit the Skill) Pipeline handoffs added to 8 skills forming 6 chains: - youtube-downloader → asr-transcribe-to-text → transcript-fixer → meeting-minutes-taker → pdf/ppt-creator - deep-research → fact-checker → pdf/ppt-creator - doc-to-markdown → docs-cleaner / fact-checker - claude-code-history-files-finder → continue-claude-work Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-05 14:27:23 +08:00
daymade	7ba893d837	feat: add fact-checker skill v1.0.0 Add 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 - Supports AI model specs, technical docs, statistics, general facts - Source evaluation framework prioritizing official documentation - Auto-correction with mandatory user approval gates - Temporal context to prevent information decay Real-world usage: - Successfully updated AI model specs (Claude, GPT, Gemini) - Corrected outdated version numbers and context windows - Added temporal markers for time-sensitive information Marketplace updates: - Bumped version to 1.19.0 - Added fact-checker to plugins list - Updated metadata description 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>	2026-01-05 23:31:44 +08:00

Author

SHA1

Message

Date

daymade

5c9eda4fbd

feat: optimize skills + add pipeline handoff chaining across 9 skills

asr-transcribe-to-text:
- Add local MLX transcription path (macOS Apple Silicon, 15-27x realtime)
- Add bundled script transcribe_local_mlx.py with max_tokens=200000
- Add local_mlx_guide.md with benchmarks and truncation trap docs
- Auto-detect platform and recommend local vs remote mode
- Fix audio extraction format (MP3 → WAV 16kHz mono PCM)
- Add Step 5: recommend transcript-fixer after transcription

transcript-fixer:
- Optimize SKILL.md from 289 → 153 lines (best practices compliance)
- Move FALSE_POSITIVE_RISKS (40 lines) to references/false_positive_guide.md
- Move Example Session to references/example_session.md
- Improve description for better triggering (226 → 580 chars)
- Add handoff to meeting-minutes-taker

skill-creator:
- Add "Pipeline Handoff" pattern to Skill Writing Guide
- Add pipeline check reminder in Step 4 (Edit the Skill)

Pipeline handoffs added to 8 skills forming 6 chains:
- youtube-downloader → asr-transcribe-to-text → transcript-fixer → meeting-minutes-taker → pdf/ppt-creator
- deep-research → fact-checker → pdf/ppt-creator
- doc-to-markdown → docs-cleaner / fact-checker
- claude-code-history-files-finder → continue-claude-work

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-05 14:27:23 +08:00

daymade

7ba893d837

feat: add fact-checker skill v1.0.0

Add 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
- Supports AI model specs, technical docs, statistics, general facts
- Source evaluation framework prioritizing official documentation
- Auto-correction with mandatory user approval gates
- Temporal context to prevent information decay

Real-world usage:
- Successfully updated AI model specs (Claude, GPT, Gemini)
- Corrected outdated version numbers and context windows
- Added temporal markers for time-sensitive information

Marketplace updates:
- Bumped version to 1.19.0
- Added fact-checker to plugins list
- Updated metadata description

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

2026-01-05 23:31:44 +08:00

2 Commits