- SKILL.md length driven by information density, not line count
- Factual dates (release dates, "last verified") should be kept — they help readers judge freshness
- Conditional date logic ("before X use old API") should be avoided
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
New skill: douban-skill
- Full export of Douban (豆瓣) book/movie/music/game collections via Frodo API
- RSS incremental sync for daily updates
- Python stdlib only, zero dependencies, cross-platform (macOS/Windows/Linux)
- Documented 7 failed approaches (PoW anti-scraping) and why Frodo API is the only working solution
- Pre-flight user validation, KeyboardInterrupt handling, pagination bug fix
skill-creator enhancements:
- Add development methodology reference (8-phase process with prior art research,
counter review, and real failure case studies)
- Sync upstream changes: improve_description.py now uses `claude -p` instead of
Anthropic SDK (no ANTHROPIC_API_KEY needed), remove stale "extended thinking" ref
- Add "Updating an existing skill" guidance to Claude.ai and Cowork sections
- Restore test case heuristic guidance for objective vs subjective skills
README updates:
- Document fork advantages vs upstream with quality comparison table (65 vs 42)
- Bilingual (EN + ZH-CN) with consistent content
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Improvements to the YAML frontmatter documentation merged from PR #6:
- Add explanation of $ARGUMENTS placeholder and how it works with skill invocation
- Add inline example showing /deep-research invocation with arguments
- Expand allowed-tools field with more wildcard examples (npm, docker compose)
- Add hooks field example showing pre-invoke configuration
- Update init_skill.py template with wildcard examples and $ARGUMENTS hint
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add documentation for all available YAML frontmatter fields, with special
emphasis on `context: fork` which is critical for skills that subagents
should be able to use via the Task tool.
Changes:
- Add YAML Frontmatter Reference section to SKILL.md with complete field table
- Document when to use `context: fork` for subagent-accessible skills
- Add invocation control comparison table
- Update init_skill.py template with commented optional frontmatter fields
This addresses a gap where skills created without `context: fork` could not
be used by subagents, limiting the skill's usefulness in multi-agent workflows.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
skill-creator v1.2.0 → v1.2.1:
- Add critical warning about not editing skills in cache directory
- Cache location (~/.claude/plugins/cache/) is read-only
- Changes there are lost on cache refresh
transcript-fixer v1.0.0 → v1.1.0:
- Add Chinese/Japanese/Korean domain name support (火星加速器, 具身智能)
- Add [CLAUDE_FALLBACK] signal for Claude Code to take over when GLM unavailable
- Add Prerequisites section requiring uv for Python execution
- Add Critical Workflow section for dictionary iteration
- Add AI Fallback Strategy and Database Operations sections
- Add Stages table (Dictionary → AI → Full pipeline)
- Add ensure_deps.py script for shared virtual environment
- Add database_schema.md and iteration_workflow.md references
- Update domain validation from whitelist to pattern matching
- Update tests for Chinese domains and security bypass attempts
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add find_path_references() to scan SKILL.md for bundled resource paths
- Add validate_path_references() to verify referenced files exist
- Smart filtering for example/documentation contexts
- Update SKILL.md Step 6 with validation details
- Bump version to 1.2.0
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add security_scan.py script with gitleaks integration
- Detect hardcoded secrets, personal info, and unsafe code patterns
- Add content-based hash validation in package_skill.py
- BLOCK packaging if security scan not run or content changed
- Add reference file naming guidelines in SKILL.md
- Create .gitignore for security marker files
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
Critical guideline added:
- Skills should NOT have version sections in SKILL.md
- Version numbers belong in marketplace.json only (plugins[].version)
- SKILL.md should be timeless content focused on functionality
- Marketplace infrastructure manages versioning, not individual skills
Rationale:
- Discovered during ppt-creator development where version history was incorrectly added
- Verified against Anthropic's official skills repository (no version sections found)
- Aligns with marketplace architecture where versions are tracked centrally
Location: Added to "Versioning" subsection under "Privacy and Path References"
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Step 2: Add "Match specificity to task risk" framework (high/medium/low freedom)
- Step 6: Add refinement filter to avoid duplicate/speculative improvements
These 5 lines help Claude choose between agentic (text instructions) vs scripted (exact code) approaches based on task characteristics.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
