Regenerate canonical registry artifacts after removing the synthetic
merge-batch end-to-end fixture.
This drops the remaining bundle, catalog, plugin, and skills index
references so validate:references passes again on main.
Add the missing When to Use sections for the new psychology skill pack and refresh the canonical generated artifacts required by the release workflow so the repository passes the warning budget and consistency gates.
Add installer filters for risk, category, and tags so maintainers and
users can ship smaller skill surfaces to context-sensitive runtimes.
Document the reduced-install flow for OpenCode-style hosts, add the
humanize-chinese community skill, and sync the generated catalog and
plugin-safe artifacts that now reflect the release batch.
Refs #437
Refs #440
Refs #443
Import the official Hugging Face ecosystem skills and sync the\nexisting local coverage with upstream metadata and assets.\n\nRegenerate the canonical catalog, plugin mirrors, docs, and release\nnotes after the maintainer merge batch so main stays in sync.\n\nFixes #417
Document the new Claude Code and Codex plugin distributions and explain how root plugins, bundle plugins, and plugin-safe filtering relate to the full library install.\n\nSync the catalog, plugin compatibility artifacts, and generated plugin-safe subsets so main stays consistent before the v9.0.0 release flow.
Add fourteen skills from Dimillian/Skills, integrate the merged Snowflake and WordPress updates into the maintainer sync, and refresh registry metadata, attributions, walkthrough notes, and the 8.9.0 release notes while keeping validation warnings within budget.
Refresh maintainer-owned artifacts after the PR merge batch, convert the\nJetski loader example to a directly importable Node ESM module, and add\nthe 8.7.0 changelog entry before release preparation.\n\nRefs #382\nRefs #388
Align public docs and maintainer guidance with the current 1,304-skill catalog state and v8.4.0 release copy.
Refresh README credits for newly imported external sources, update user-facing count references, and document the post-release docs realignment in the changelog and walkthrough.
* chore: implement ESM standardization and security attestation
Aligning root infrastructure with Node.js v24.14.0 standards.
- Set type: module in package.json to eliminate re-parsing overhead.
- Migrated Jetski Loader tests to .cjs to maintain legacy security audit compatibility.
- Verified path traversal and symlink protections with clean attestation.
* chore(ci): update pr_preflight path to .cjs for ESM compatibility
* feat(infra): surgical ESM modernization for Gemini suite
Resolved Codex P1 by reverting global root ESM shift to preserve installer stability.
- Implemented scoped 'type: module' in /docs/integrations/jetski-gemini-loader/ to eliminate re-parsing overhead.
- Updated test runner (run-test-suite.js) and CI (ci.yml) to track .cjs transitions.
- Verified zero-warning execution in Node v24.14.0.
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.
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
