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.
Update the maintainer and user walkthroughs so they reflect the
completed 8.2.0 release publication instead of the pre-release ready
state.
Capture the final PR merge set, issue closure state, and the exact
release commands that were executed on main.
Add the 8.2.0 changelog entry and align the release-facing user docs
with the current maintenance sweep so the release workflow has the
required notes and public version references in place.
Refresh README release messaging and contributor acknowledgements ahead
of the automated release commit and tag creation.
This commit adds documentation and a reference implementation for
integrating antigravity-awesome-skills with Jetski/Cortex agents
without hitting the context window truncation error (issue #269).
Changes:
- New integration guide: docs/integrations/jetski-cortex.md
- Example loader: examples/jetski-gemini-loader/loader.ts
- Example README: examples/jetski-gemini-loader/README.md
- Updated FAQ: docs/users/faq.md (added context overflow section)
- Updated usage: docs/users/usage.md (added "Can I load all skills?" FAQ)
The solution follows a manifest + lazy-loading pattern:
- Use data/skills_index.json as lightweight manifest
- Only load SKILL.md files for @skill-id references in messages
- Enforce maxSkillsPerTurn limit to prevent overflow
- Add docs/maintainers/merging-prs.md: policy to always use Squash and merge,
resolve conflicts on PR branch so PR shows Merged; Co-authored-by for rare
local integration
- Update .github/MAINTENANCE.md: merge via GitHub only, never close after
local integration; conflict resolution on branch then merge
- Update CONTRIBUTING.md Recognition: we always merge accepted PRs on GitHub,
never close after integrating locally
Addresses feedback from @sraphaz on #225 (attribution when PRs are integrated
locally). Going forward PRs will show as Merged so contributors get full credit.
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.
- Add 300+ new skills from 35+ community repositories
- Total collection now at 1,200+ skills
- New categories: UI/UX, Security, Data Science, Health, Quantum, Makepad
- Update package.json to v7.0.0
- Update README with new stats and 20k stars celebration banner
- Complete CHANGELOG with all new skills and community credits
- Add release_notes.md with detailed acknowledgments
Validation chain run, catalog regenerated.
Thank you to our incredible community for 20,000 GitHub stars!
- Update skill counts from 978/954/950/900 to 1006 across README.md,
GETTING_STARTED.md, FAQ.md, and package.json
- Add 3 missing contributors: devchangjun, raeef1001, 1bcMax
- Regenerated index, catalog, and README via npm run chain + npm run catalog
* feat: add 12 official Apify skills for web scraping and data extraction
Add the complete Apify agent-skills collection as official vendor skills,
bringing the total skill count from 954 to 966.
New skills:
- apify-actor-development: Develop, debug, and deploy Apify Actors
- apify-actorization: Convert existing projects into Apify Actors
- apify-audience-analysis: Audience demographics across social platforms
- apify-brand-reputation-monitoring: Track reviews, ratings, and sentiment
- apify-competitor-intelligence: Analyze competitor strategies and pricing
- apify-content-analytics: Track engagement metrics and campaign ROI
- apify-ecommerce: E-commerce data scraping for pricing intelligence
- apify-influencer-discovery: Find and evaluate influencers
- apify-lead-generation: B2B/B2C lead generation from multiple platforms
- apify-market-research: Market conditions and geographic opportunities
- apify-trend-analysis: Discover emerging trends across platforms
- apify-ultimate-scraper: Universal AI-powered web scraper
Existing skill fixes:
- design-orchestration: Add missing description, fix markdown list spacing
- multi-agent-brainstorming: Add missing description, fix markdown list spacing
Registry and documentation updates:
- Update skill count to 966+ across README.md, README.vi.md
- Add Apify to official sources in SOURCES.md and all README variants
- Register new skills in catalog.json, skills_index.json, bundles.json, aliases.json
- Update CATALOG.md category counts (data-ai: 152, infrastructure: 95)
Validation script improvements:
- Raise description length limit from 200 to 1024 characters
- Add empty description validation check
- Apply PEP 8 formatting (line length, spacing, trailing whitespace)
* refactor: truncate skill descriptions in SKILL.md files and revert description length validation to 200 characters.
* feat: Add `apify-ultimate-scraper` to data-ai and move `apify-lead-generation` from business to general categories.
* Update print statement from 'Hello' to 'Goodbye'
* Remove outdated skill descriptions from SEC_SKILLS.md
Removed several sections related to analytics tracking, SEO auditing, Slack bot building, and other skills from SEC_SKILLS.md.
- 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.
- README: update 'New Here' section from V6.2.0 to V6.3.1
- README: fix stale skill count from 927+ to 946+ in Bundles section
- docs/GETTING_STARTED.md: fix default install path from ~/.agent/skills to ~/.gemini/antigravity/skills (changed in v5.9.0); add --kiro flag
- CHANGELOG.md: add missing [5.2.0] header for dangling Podcast Generation & Azure AI Skills release content
- Add --kiro flag to installer for ~/.kiro/skills installation
- Update README with Kiro in compatibility table and installation examples
- Add Kiro CLI badge and documentation
- Create comprehensive KIRO_INTEGRATION.md guide with:
- Installation instructions
- Usage examples and workflows
- AWS-specific skill recommendations
- Troubleshooting and best practices
- MCP integration details
Kiro is AWS's agentic AI IDE with autonomous coding capabilities,
MCP support, and native AWS service integration. This contribution
enables 883+ skills to enhance Kiro's capabilities across serverless,
infrastructure, security, and full-stack development.
- 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>
