{"id":48498723,"url":"https://github.com/flitzrrr/agent-skills","last_synced_at":"2026-04-07T13:32:37.583Z","repository":{"id":344460645,"uuid":"1181529658","full_name":"flitzrrr/agent-skills","owner":"flitzrrr","description":"Curated collection of AI agent skills for Antigravity, Claude Code, OpenCode \u0026 similar AI coding assistants","archived":false,"fork":false,"pushed_at":"2026-04-06T07:49:23.000Z","size":1058,"stargazers_count":1,"open_issues_count":1,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-06T08:39:22.012Z","etag":null,"topics":["agent-skills","ai-agent","ai-coding","automation","claude-code","codex","cursor","developer-tools","prompt-engineering","skills"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/flitzrrr.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-03-14T09:08:20.000Z","updated_at":"2026-04-06T07:49:27.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/flitzrrr/agent-skills","commit_stats":null,"previous_names":["flitzrrr/agent-skills"],"tags_count":5,"template":false,"template_full_name":null,"purl":"pkg:github/flitzrrr/agent-skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flitzrrr%2Fagent-skills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flitzrrr%2Fagent-skills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flitzrrr%2Fagent-skills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flitzrrr%2Fagent-skills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/flitzrrr","download_url":"https://codeload.github.com/flitzrrr/agent-skills/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/flitzrrr%2Fagent-skills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31515144,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-07T03:10:19.677Z","status":"ssl_error","status_checked_at":"2026-04-07T03:10:13.982Z","response_time":105,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-skills","ai-agent","ai-coding","automation","claude-code","codex","cursor","developer-tools","prompt-engineering","skills"],"created_at":"2026-04-07T13:32:37.511Z","updated_at":"2026-04-07T13:32:37.576Z","avatar_url":"https://github.com/flitzrrr.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Agent Skills Hub\n\n[![npm version](https://img.shields.io/npm/v/@flitzrrr/agent-skills?style=flat-square\u0026color=cb3837)](https://www.npmjs.com/package/@flitzrrr/agent-skills)\n[![npm downloads](https://img.shields.io/npm/dm/@flitzrrr/agent-skills?style=flat-square)](https://www.npmjs.com/package/@flitzrrr/agent-skills)\n[![Skills](https://img.shields.io/badge/skills-524-blue?style=flat-square)](skills/)\n[![Sources](https://img.shields.io/badge/sources-20-green?style=flat-square)](vendor/)\n[![License: MIT](https://img.shields.io/badge/license-MIT-blue?style=flat-square)](LICENSE)\n[![Weekly Discovery](https://img.shields.io/badge/auto--discovery-weekly-purple?style=flat-square)](.github/workflows/skill-discovery.yml)\n\n**504 curated AI agent skills** from **19 verified sources**. One install, every major coding assistant.\n\n[Full catalog](https://flitzrrr.github.io/agent-skills/) | [Decision guide](CHEATSHEET.md)\n\n---\n\n## Quick Start\n\n```bash\nnpx @flitzrrr/agent-skills install\n```\n\nDetects installed platforms and provisions skills for each. Target a single platform with:\n\n```bash\nnpx @flitzrrr/agent-skills install \u003cplatform\u003e\n```\n\nWhere `\u003cplatform\u003e` is one of: `vscode`, `codex`, `antigravity`, `opencode`.\n\n\u003cdetails\u003e\n\u003csummary\u003eManual setup (git clone)\u003c/summary\u003e\n\n```bash\ngit clone --recurse-submodules git@github.com:flitzrrr/agent-skills.git\ncd agent-skills\n\n# Symlink into target platform(s):\nln -sf $(pwd)/skills/* ~/.copilot/skills/         # VS Code / GitHub Copilot\nln -sf $(pwd)/skills/* ~/.codex/skills/            # Codex\nln -sf $(pwd)/skills/* ~/.gemini/antigravity/skills/ # Antigravity\nln -sf $(pwd)/skills/* ~/.config/opencode/skills/  # OpenCode\n\n# Pull upstream updates:\ngit submodule update --remote --merge\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003eAll CLI commands\u003c/summary\u003e\n\n| Command | Description |\n| --- | --- |\n| `npx @flitzrrr/agent-skills install` | Install for all detected platforms |\n| `npx @flitzrrr/agent-skills install \u003cplatform\u003e` | Install for a single platform |\n| `npx @flitzrrr/agent-skills update` | Pull latest upstream skills |\n| `npx @flitzrrr/agent-skills list` | List all available skills |\n\n\u003c/details\u003e\n\n---\n\n## Platform Support\n\n| Platform | Discovery Mechanism | Install Method |\n| --- | --- | --- |\n| VS Code (GitHub Copilot) | `.github/copilot-instructions.md` + `~/.copilot/skills/` | `install vscode` |\n| Claude Code | `CLAUDE.md` (project-level) | Clone into project |\n| Codex | `AGENTS.md` | `install codex` |\n| Cursor | `.cursorrules` (project-level) | Clone into workspace |\n| Lovable | `.lovable` | Clone into workspace |\n| Windsurf | `AGENTS.md` | Clone into workspace |\n| Antigravity | `~/.gemini/antigravity/skills/` | `install antigravity` |\n| OpenCode | `AGENTS.md` + `skills/` | `install opencode` |\n| Any agent | Read `skills/\u003cname\u003e/SKILL.md` directly | Manual |\n\n---\n\n## Skill Categories\n\n| Category | Examples | Sources |\n| --- | --- | --- |\n| Security and code review | `security-review`, `code-review`, `find-bugs`, `gha-security-review` | Sentry, Trail of Bits |\n| Git workflow | `commit`, `create-branch`, `pr-writer`, `iterate-pr` | Sentry |\n| Project planning | `create-plan`, `resume-plan`, `execute-work-package`, `generate-handover` | DasDigitaleMomentum |\n| Document generation | `anthropic-pdf`, `anthropic-docx`, `anthropic-pptx`, `anthropic-xlsx` | Anthropic |\n| Frontend and React | `vercel-react-best-practices`, `vercel-web-design-guidelines`, `anthropic-frontend-design` | Vercel, Anthropic |\n| Infrastructure | `aws-lambda`, `terraform-code-generation`, `cloudflare-wrangler` | AWS, HashiCorp, Cloudflare |\n| Finance | `finance-equity-research`, `finance-ib-advisory`, `finance-wealth-mgmt` | Anthropic |\n| Science and ML | `scientific-bioinformatics`, `scientific-alphafold`, `scientific-chembl` | K-Dense-AI |\n| Marketing and SEO | `content-strategy`, `seo-audit`, `product-description-seo` | Coreyhaines, Bhanunamikaze |\n| Developer tools | `anthropic-mcp-builder`, `anthropic-webapp-testing`, `systematic-debugging` | Anthropic, Sentry |\n| Django | `django-access-review`, `django-perf-review` | Sentry |\n| Deployment | `vercel-deploy-to-vercel`, `stitch-shadcn-ui` | Vercel, Google |\n\nSee [CHEATSHEET.md](CHEATSHEET.md) for a decision guide on which skill to use for a given task.\n\n---\n\n## Sources\n\n| Source | Skills | Focus |\n| --- | ---: | --- |\n| [K-Dense-AI/claude-scientific-skills](https://github.com/K-Dense-AI/claude-scientific-skills) | 175 | Science, bioinformatics, ML, chemistry |\n| [trailofbits/skills](https://github.com/trailofbits/skills) | 60 | Security auditing, static analysis, smart contracts |\n| [anthropics/financial-services-plugins](https://github.com/anthropics/financial-services-plugins) | 56 | Finance: IB, equity research, PE, wealth mgmt |\n| [MoizIbnYousaf/Ai-Agent-Skills](https://github.com/MoizIbnYousaf/Ai-Agent-Skills) | 48 | Database design, debugging, code patterns |\n| [coreyhaines31/marketingskills](https://github.com/coreyhaines31/marketingskills) | 33 | Marketing: SEO, email, content, analytics |\n| [getsentry/skills](https://github.com/getsentry/skills) | 24 | Security, code review, Git workflow, Django |\n| [itsmostafa/aws-agent-skills](https://github.com/itsmostafa/aws-agent-skills) | 18 | AWS infrastructure and services |\n| [anthropics/skills](https://github.com/anthropics/skills) | 17 | Document gen, creative design, MCP |\n| [hashicorp/agent-skills](https://github.com/hashicorp/agent-skills) | 14 | Terraform generation |\n| [expo/skills](https://github.com/expo/skills) | 11 | Expo design and deployment |\n| [cloudflare/skills](https://github.com/cloudflare/skills) | 9 | Workers, Durable Objects, MCP |\n| [DasDigitaleMomentum/opencode-processing-skills](https://github.com/DasDigitaleMomentum/opencode-processing-skills) | 9 | Multi-session planning |\n| [google-labs-code/stitch-skills](https://github.com/google-labs-code/stitch-skills) | 7 | Design-to-code, shadcn/ui, Remotion |\n| [vercel-labs/agent-skills](https://github.com/vercel-labs/agent-skills) | 5 | React, Next.js, web design |\n| [callstackincubator/agent-skills](https://github.com/callstackincubator/agent-skills) | 5 | React Native, GitHub workflows |\n| [JackyST0/awesome-agent-skills](https://github.com/JackyST0/awesome-agent-skills) | 5 | General-purpose agent patterns |\n| [stripe/ai](https://github.com/stripe/ai) | 2 | Stripe best practices |\n| [Bhanunamikaze/Agentic-SEO-Skill](https://github.com/Bhanunamikaze/Agentic-SEO-Skill) | 1 | SEO auditing (16 sub-skills) |\n| [supabase/agent-skills](https://github.com/supabase/agent-skills) | 1 | Postgres best practices |\n\nNew sources are discovered weekly via [GitHub Actions](.github/workflows/skill-discovery.yml) and security-scanned before integration.\n\n---\n\n## Architecture\n\n```\nagent-skills/\n  skills/            504 entries (symlinks to vendor + local forks)\n  vendor/          20 Git submodules (upstream sources)\n  bin/               CLI and build scripts\n  docs/              GitHub Pages catalog and project documentation\n  .github/           CI workflows and copilot-instructions.md\n```\n\nSkills are exposed as a flat directory under `skills/`. Most entries are symlinks into `vendor/` submodules. Skills with local extensions (e.g., `execute-work-package` with multi-transport support) are maintained as real directories alongside the symlinks.\n\n### Naming Convention\n\nSkills are namespaced by source to avoid collisions: `anthropic-pdf`, `tob-static-analysis`, `cloudflare-wrangler`, `terraform-code-generation`, `scientific-bioinformatics`, `aws-lambda`, `finance-equity-research`, `callstack-react-native-best-practices`. Sentry and marketing skills are un-prefixed (`code-review`, `content-strategy`).\n\n### Automation\n\n| Workflow | Trigger | Purpose |\n| --- | --- | --- |\n| [Skill Discovery](.github/workflows/skill-discovery.yml) | Weekly | Find trending skill repos, security-scan, auto-add |\n| [Submodule Update](.github/workflows/submodule-update.yml) | Weekly | Pull upstream changes, open PR |\n| [MegaLinter](.github/workflows/megalinter.yml) | Push / PR | Lint markdown, YAML, JSON |\n| [npm Publish](.github/workflows/npm-publish.yml) | Tag `v*` | Publish to npm, create GitHub Release |\n\n---\n\n## MCP Execution Backend (l4l-oci)\n\nThe [execute-work-package](skills/execute-work-package) skill supports three transport modes for delegating implementation to a sub-agent:\n\n| Transport | Mechanism | When to use |\n| --- | --- | --- |\n| **MCP via l4l-oci** (default) | [l4l-oci](https://github.com/DasDigitaleMomentum/l4l-oci) exposes 10 MCP tools for the gated blueprint-gate-execute lifecycle | Any IDE with MCP support |\n| **Fresh Agent** | IDE spawns a new sub-agent per step (no external server) | Fallback when l4l-oci is not configured |\n| **Stateful Session** | Sub-agent session resumed across steps | OpenCode only |\n\nWhen l4l-oci MCP tools are available (`create_handle`, `generate_blueprint`, `submit_gate`, `execute_handle`, `get_digest`), the skill uses them automatically. The bundled `scripts/start-l4l-oci.sh` auto-starts the server if needed. See the [l4l-oci setup guide](https://github.com/DasDigitaleMomentum/l4l-oci/blob/main/docs/setup.md) for configuration.\n\n### Lifecycle\n\n```mermaid\nsequenceDiagram\n    participant User\n    participant Primary as Primary Agent\u003cbr/\u003e(IDE)\n    participant MCP as l4l-oci MCP Server\n    participant Sub as Sub-LLM\u003cbr/\u003e(configurable)\n\n    User-\u003e\u003ePrimary: Task with scope and DoD\n\n    rect rgb(240, 245, 250)\n    Note over Primary,Sub: Blueprint Phase\n    Primary-\u003e\u003eMCP: create_handle(project_root)\n    MCP--\u003e\u003ePrimary: handle_id\n    Primary-\u003e\u003eMCP: generate_blueprint(handle_id, prompt)\n    MCP-\u003e\u003eSub: Generate Execution Blueprint\n    Sub--\u003e\u003eMCP: Blueprint (ordered steps)\n    Primary-\u003e\u003eMCP: get_blueprint(handle_id)\n    MCP--\u003e\u003ePrimary: Blueprint for review\n    end\n\n    Primary-\u003e\u003eUser: Present Blueprint for review\n\n    User-\u003e\u003ePrimary: Approve\n\n    rect rgb(240, 250, 240)\n    Note over Primary,Sub: Gate\n    Primary-\u003e\u003eMCP: submit_gate(handle_id, \"accept\")\n    MCP--\u003e\u003ePrimary: Gated\n    end\n\n    rect rgb(250, 245, 240)\n    Note over Primary,Sub: Execute Phase\n    Primary-\u003e\u003eMCP: execute_handle(handle_id)\n    MCP-\u003e\u003eSub: Implement Blueprint steps\n    Sub-\u003e\u003eSub: Edit files, run verification\n    Sub--\u003e\u003eMCP: Execution Digest\n    Primary-\u003e\u003eMCP: get_digest(handle_id)\n    MCP--\u003e\u003ePrimary: Digest (outcome, files, verify result)\n    end\n\n    Primary-\u003e\u003eUser: Report results\n```\n\n---\n\n## License\n\nMIT -- applies to the CLI, workflows, and documentation in this repository.\nEach vendored submodule in `vendor/` retains its own original license.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflitzrrr%2Fagent-skills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fflitzrrr%2Fagent-skills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fflitzrrr%2Fagent-skills/lists"}