Restrict auto-apply to trusted review comments so spoofed issue comments
cannot write optimized SKILL.md content into pull request branches.
Reject activation symlinks that escape the source root and add
regression coverage for both security checks.
Add a Unix activation script, Antigravity-specific installer guidance,
and cross-platform recovery documentation so users can reduce the
live skill set when truncation or context overload appears.
Regenerate the canonical bundle/catalog artifacts after merging the
stale goldrush-api removal so main stays release-ready.
Refs #381
Harden batch activation, dev refresh gating, Microsoft sync path
handling, and Jetski skill loading against command injection,
symlink traversal, and client-side star tampering.
Add regression coverage for the security-sensitive paths and
update the internal triage addendum for the Jetski loader fix.
* Implemented scripts and a Python utility to optimize agent skills, preventing context window overload, and document their usage.
* feat(infra): add skills optimization scripts with bundle support and fixed archive logic
* Removed Linux / Mac optimize-skills
* Removed the Linux Section
* feat(infra): final robust skill optimization suite with Library Mode
* Removed
* Updated the read me changed the optimisation to activation-skills
* Updated ReadMe
* docs: trim activation script README diff
---------
Co-authored-by: sck_0 <samujackson1337@gmail.com>
Consolidate the repository into clearer apps, tools, and layered docs areas so contributors can navigate and maintain it more reliably. Align validation, metadata sync, and CI around the same canonical workflow to reduce drift across local checks and GitHub Actions.
- Added `scripts/auto_categorize_skills.py` to analyze skill names and descriptions, auto-assigning categories based on keyword matching.
- Updated category distribution to show counts and sort categories by skill count in the Home page dropdown.
- Created documentation in `docs/CATEGORIZATION_IMPLEMENTATION.md` and `docs/SMART_AUTO_CATEGORIZATION.md` detailing the new categorization process and usage.
- Introduced `scripts/fix_year_2025_to_2026.py` to update all skill dates from 2025 to 2026.
- Enhanced user experience by moving "uncategorized" to the bottom of the category list and displaying skill counts in the dropdown.
- Added `date_added` field to all skills in frontmatter.
- Updated Home page to display skill addition date alongside risk level.
- Enhanced Skill Detail page to show date added in a badge format.
- Created scripts for managing skill dates, including adding missing dates and generating reports.
- Updated validators to enforce date format compliance.
- Added comprehensive documentation on date tracking implementation and usage.
- Introduced a new skill template including the `date_added` field.
- Align package.json description to 883+ skills
- Allow risk:unknown in validate_skills.py for legacy skills
- Add When to Use section to 6 skills; fix frontmatter in brainstorming, agents-v2-py, hosted-agents-v2-py
- Add scripts/validate_references.py for workflows, bundles, BUNDLES.md links
- Update QUALITY_BAR and SKILL_ANATOMY; add docs/AUDIT.md and MAINTENANCE note for data/
- Make YAML frontmatter test warn instead of fail; regenerate catalog and index
Co-authored-by: Cursor <cursoragent@cursor.com>
- Wrapped unquoted @scope/pkg values in double quotes across 19 SKILL.md files.
- Added 'package' to ALLOWED_FIELDS in JS validator.
- Added YAML validity regression test to test suite.
- Updated package-lock.json.
Fixes#79Closes#80
- Add find_github_skills() to discover skills in .github/skills/ not
reachable via the skills/ symlink tree (picks up 11 missing skills)
- Add collision protection: if a target directory exists and was not
from a previous Microsoft sync, append -ms suffix instead of overwriting
- Microsoft mcp-builder → mcp-builder-ms (community version preserved)
- Microsoft skill-creator → skill-creator-ms (community version preserved)
- Total skills: 856 (was 845, +11 newly discovered)
sync_microsoft_skills.py now reads docs/microsoft-skills-attribution.json
to identify previously synced skill directories and removes them before
re-populating. This handles upstream renames, removals, and moves without
leaving orphaned skill directories.
Rewrote sync_microsoft_skills.py (v4) to use each SKILL.md's frontmatter
'name' field as the flat directory name under skills/, replacing the nested
skills/official/microsoft/<lang>/<category>/<service>/ hierarchy.
This fixes CI failures caused by the indexing, validation, and catalog
scripts expecting skills/<id>/SKILL.md (depth 1).
Changes:
- Rewrite scripts/sync_microsoft_skills.py for flat output with collision detection
- Update scripts/tests/inspect_microsoft_repo.py for flat name mapping
- Update scripts/tests/test_comprehensive_coverage.py for name uniqueness checks
- Delete skills/official/ nested directory
- Add 129 Microsoft skills as flat directories (e.g. skills/azure-mgmt-botservice-dotnet/)
- Move attribution files to docs/ (LICENSE-MICROSOFT, microsoft-skills-attribution.json)
- Rebuild skills_index.json, CATALOG.md, README.md (845 total skills)
🚀 Impact
Significantly expands the capabilities of **Antigravity Awesome Skills** by integrating official skill collections from **Microsoft** and **Google Gemini**. This update increases the total skill count to **845+**, making the library even more comprehensive for AI coding assistants.
✨ Key Changes
1. New Official Skills
- **Microsoft Skills**: Added a massive collection of official skills from [microsoft/skills](https://github.com/microsoft/skills).
- Includes Azure, .NET, Python, TypeScript, and Semantic Kernel skills.
- Preserves the original directory structure under `skills/official/microsoft/`.
- Includes plugin skills from the `.github/plugins` directory.
- **Gemini Skills**: Added official Gemini API development skills under `skills/gemini-api-dev/`.
2. New Scripts & Tooling
- **`scripts/sync_microsoft_skills.py`**: A robust synchronization script that:
- Clones the official Microsoft repository.
- Preserves the original directory heirarchy.
- Handles symlinks and plugin locations.
- Generates attribution metadata.
- **`scripts/tests/inspect_microsoft_repo.py`**: Debug tool to inspect the remote repository structure.
- **`scripts/tests/test_comprehensive_coverage.py`**: Verification script to ensure 100% of skills are captured during sync.
3. Core Improvements
- **`scripts/generate_index.py`**: Enhanced frontmatter parsing to safely handle unquoted values containing `@` symbols and commas (fixing issues with some Microsoft skill descriptions).
- **`package.json`**: Added `sync:microsoft` and `sync:all-official` scripts for easy maintenance.
4. Documentation
- Updated `README.md` to reflect the new skill counts (845+) and added Microsoft/Gemini to the provider list.
- Updated `CATALOG.md` and `skills_index.json` with the new skills.
🧪 Verification
- Ran `scripts/tests/test_comprehensive_coverage.py` to verify all Microsoft skills are detected.
- Validated `generate_index.py` fixes by successfully indexing the new skills.
feat: update clean-code skill and stabilize registry
- Updated clean-code skill with Robert C. Martin's Clean Code principles
- Fixed invalid heading format
- Stabilized registry with SOURCE_DATE_EPOCH for deterministic CI builds
- Included in release v4.11.0
Co-authored-by: jackjin1997 <jackjin1997@users.noreply.github.com>
- Updated clean-code skill with Robert C. Martin's Clean Code principles
- Refined content: naming, functions, comments, error handling, class design
- Fixed invalid heading format (## ## When to Use -> ## When to Use)
- Stabilized registry: use SOURCE_DATE_EPOCH for deterministic CI builds
- Improved catalog sorting for cross-environment consistency
- Regenerated all catalog and index files
Co-authored-by: jackjin1997 <jackjin1997@users.noreply.github.com>
- VoltAgent repository analysis and validation reports
- Similar skills analysis and implementation tracking
- HTML to markdown conversion report
- Final skills count verification
- Remove Full Skill Registry and table logic; keep only count substitutions
- Add Browse N+ Skills and TOC link updates
- Always write README after substitutions so chain completes without error
- Add npm scripts: validate, validate:strict, index, readme, chain, catalog, build
- Align docs to V4 and 560 skills (GETTING_STARTED, FAQ, BUNDLES, MAINTENANCE, vietnamese)
- build-catalog: output to data/ for catalog, bundles, aliases; add to CI and drift check
- Add yaml dep, Node setup and catalog step in CI; extend auto-commit and drift msg
- Translate CI and MAINTENANCE to English; update CI_DRIFT_FIX and maintenance routine
- QUALITY_BAR/CONTRIBUTING: canonical validator npm run validate; legacy note in validate-skills.js
- Add validate_skills.py for skill format validation
- Add generate_index.py for generating skills_index.json
- Generate skills_index.json with metadata for all 58 skills
- Update README.md with categorization table and full skill registry
- Add Installation and How to Contribute sections
