antigravity-awesome-skills

Distributes 1,431+ validated skills across heterogeneous AI coding platforms (Claude Code, Cursor, Gemini CLI, Kiro, Antigravity) through a unified NPM-based installer CLI that detects platform context and deploys skills to platform-specific directories. Uses platform-agnostic SKILL.md format with YAML frontmatter that gets transpiled into platform-native configurations at install time, eliminating manual per-platform setup.

Enforces strict structural and semantic validation on all 1,431+ skills through a Python-based validation pipeline that runs on every commit and pull request. Validates YAML frontmatter schema, markdown structure, required metadata fields (title, category, tags, description), skill naming conventions, and content completeness. Blocks invalid skills from being indexed and published, maintaining catalog integrity.

Manages skill library versions via semantic versioning (v10.4.0 as of latest release) with changelog tracking (CHANGELOG.md) and release notes. Each release bundles validated skills, updated catalog, and documentation. Versions are tagged in git and published to npm registry for distribution via npx. Release process includes automated changelog generation, version bumping, and publication to npm. Skills themselves don't have individual versions — entire library is versioned as a unit.

Provides comprehensive documentation including getting-started guides (docs/users/getting-started.md), usage instructions (docs/USAGE.md), bundle documentation (docs/BUNDLES.md), FAQ (docs/FAQ.md), and example skills showcase (docs/EXAMPLES.md). Documentation covers installation methods, platform-specific setup, skill invocation syntax, bundle usage, and troubleshooting. Each skill includes inline examples and prerequisites in its SKILL.md body. Web app provides skill previews with metadata and direct links to full documentation.

Provides an interactive browser-based UI (Vite React SPA) for discovering, searching, and filtering 1,431+ skills across 9 categories. Implements full-text search, faceted filtering by category/tags/platform, skill preview with metadata display, and direct installation links. The web app indexes skills from the generated skills_index.json catalog and serves as the primary discovery interface for developers.

Enables grouping of related skills into named bundles (defined in data/bundles.json) that can be installed together as a unit. Bundles represent common workflows (e.g., 'security-audit', 'data-pipeline', 'api-design') and reference multiple skills by name. Installers resolve bundle names to constituent skills and deploy them atomically, allowing developers to install entire workflows with a single command.

Automatically generates a searchable skill catalog (skills_index.json) from raw SKILL.md files by parsing YAML frontmatter and extracting metadata (title, category, tags, description, platform compatibility). The generate_index.py script walks the skills/ directory, validates each skill, extracts metadata, and produces a JSON index that powers the web UI, CLI search, and platform-specific installations. Catalog is regenerated on every commit to keep it synchronized with skill definitions.

Enables AI coding assistants to load and invoke skills on-demand by name (e.g., @brainstorming, @security-audit) without pre-loading all skills into context. Skills are loaded only when explicitly invoked, preventing context window overflow while giving agents access to specialized expertise across 1,431+ domains. Integration points include Claude Code context files, Cursor skill definitions, Gemini CLI prompts, and Kiro skill registries. Each platform has native bindings that handle skill loading and prompt injection.

Defines a standardized SKILL.md format with YAML frontmatter (title, category, tags, description, platform compatibility, aliases) followed by markdown body containing structured instructions. All 1,431+ skills conform to this format, enabling consistent parsing, validation, and platform-agnostic distribution. Format includes optional sections for examples, prerequisites, and platform-specific notes. Standardization allows tooling (validators, indexers, installers) to work uniformly across all skills without custom parsing logic.

Organizes 1,431+ skills into 9 primary categories (Architecture, Business, Data & AI, Development, General, Infrastructure, Security, Testing, Workflow) with hierarchical tagging and aliases. Categories are defined in CATALOG.md and enforced via validation. Each skill is tagged with primary category + optional secondary tags for fine-grained discovery. Aliases enable skill discovery by alternative names (e.g., 'security-audit' can be invoked as 'audit' or 'security-check'). Taxonomy is maintained in data/aliases.json and enforced during indexing.

Implements a structured contribution workflow where new skills are submitted as pull requests, automatically validated against schema and quality standards, and merged only after passing validation gates. The workflow includes skill anatomy templates, contribution guidelines (docs/CONTRIBUTION.md), automated validation on every PR, and maintainer review. GitHub Actions runs validate_skills.py and generate_index.py on every PR to ensure new skills meet quality standards before merging.

Transpiles platform-agnostic SKILL.md files into platform-native configurations at install time. For Claude Code, generates context files; for Cursor, creates skill definitions; for Gemini CLI, produces prompt templates; for Kiro, populates skill registries. Transpilation handles platform-specific syntax, context injection patterns, and API differences. Each platform has a dedicated adapter that reads SKILL.md metadata and body, then generates platform-native output without requiring separate skill definitions per platform.