{"id":49008355,"url":"https://github.com/permanu/superskill","last_synced_at":"2026-05-08T07:02:36.134Z","repository":{"id":345579348,"uuid":"1186524080","full_name":"permanu/superskill","owner":"permanu","description":"One plugin, every skill. The package manager for AI coding agents — 90+ expert methodologies from 9 repos, fetched on demand, works across Claude Code, Cursor, Codex, and more.","archived":false,"fork":false,"pushed_at":"2026-03-25T08:42:28.000Z","size":484,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-18T21:29:46.219Z","etag":null,"topics":["ai-coding","claude-code","codex","cursor","mcp","mcp-server","package-manager","skills"],"latest_commit_sha":null,"homepage":null,"language":"TypeScript","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/permanu.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","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":"2026-03-19T18:03:30.000Z","updated_at":"2026-03-25T08:42:30.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/permanu/superskill","commit_stats":null,"previous_names":["gopherine/obsidian-mcp","permanu/superskill"],"tags_count":9,"template":false,"template_full_name":null,"purl":"pkg:github/permanu/superskill","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/permanu%2Fsuperskill","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/permanu%2Fsuperskill/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/permanu%2Fsuperskill/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/permanu%2Fsuperskill/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/permanu","download_url":"https://codeload.github.com/permanu/superskill/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/permanu%2Fsuperskill/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32770544,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-08T02:36:36.067Z","status":"ssl_error","status_checked_at":"2026-05-08T02:36:07.210Z","response_time":54,"last_error":"SSL_read: 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":["ai-coding","claude-code","codex","cursor","mcp","mcp-server","package-manager","skills"],"created_at":"2026-04-18T21:18:34.694Z","updated_at":"2026-05-08T07:02:35.909Z","avatar_url":"https://github.com/permanu.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# SuperSkill\n\nThe runtime intelligence layer for AI agent skills.\n\n[![npm](https://img.shields.io/npm/v/superskill)](https://www.npmjs.com/package/superskill)\n[![license](https://img.shields.io/badge/license-AGPL--3.0-blue)](https://www.gnu.org/licenses/agpl-3.0)\n[![skills](https://img.shields.io/badge/built--in_skills-87-purple)](https://github.com/permanu/superskill)\n[![tools](https://img.shields.io/badge/AI%20tools-11-green)](https://github.com/permanu/superskill)\n\n## The Problem\n\n[skills.sh](https://skills.sh) solved skill discovery and installation — 90,000+ skills, 40+ agents, one standard. But installation is static. You browse, pick, install, and hope you chose right.\n\nWhen you have 15 skills installed and say \"write tests for my Go API\" — which one loads? What about the three competing TDD skills? What if the model's context window can't fit them all?\n\n**skills.sh is where you find skills. SuperSkill is what loads the right one at the right time.**\n\n## How It Works\n\n1. **Install skills however you want** — `npx skills add`, manual download, or use the 87 built-in skills\n2. **Describe your task** — \"write tests for my Go API\"\n3. **SuperSkill scores, resolves, and loads** — trigger-based matching picks the best skill, resolves collisions, respects your context budget\n\nSuperSkill scans your installed skills (from `~/.claude/skills/`, `~/.cursor/skills/`, etc.), merges them with its built-in catalog, and routes tasks to the best match at runtime.\n\n## What SuperSkill Adds\n\n| Layer | What it does | Why you need it |\n|-------|-------------|----------------|\n| **Router** | Task description → best matching skill | No manual browsing or memorizing skill names |\n| **Arbiter** | 3 TDD skills installed? Profile picks the winner | Prevents collision chaos and token waste |\n| **Scanner** | Discovers installed skills from any source | Works with skills.sh, manual installs, or built-in |\n| **Memory** | Remembers activations within a session | No redundant fetches for similar tasks |\n| **Vault** | ADRs, learnings, sessions, project context | Persistent knowledge that survives across sessions |\n\n## Quick Start\n\n### Claude Code Plugin (recommended)\n\n```bash\n/plugin marketplace add permanu/superskill\n/plugin install superskill\n```\n\n### Any MCP-compatible tool\n\n```bash\nnpm install -g superskill\n```\n\nThen add as an MCP server:\n\n```bash\n# Claude Code\nclaude mcp add superskill -e VAULT_PATH=~/Vaults/ai -- npx -y superskill\n\n# Cursor, Claude Desktop, Codex, Gemini CLI — add to MCP config:\n```\n\n```json\n{\n  \"mcpServers\": {\n    \"superskill\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"superskill\"],\n      \"env\": { \"VAULT_PATH\": \"~/Vaults/ai\" }\n    }\n  }\n}\n```\n\n### Works with skills.sh\n\nInstall skills from the ecosystem, SuperSkill routes to them automatically:\n\n```bash\nnpx skills add anthropics/skills          # Anthropic's official skills\nnpx skills add affaan-m/everything-claude-code  # ECC skill suite\n# SuperSkill discovers and scores these on next activation\n```\n\n## Supported AI Tools\n\n| Tool | Setup | Status |\n|------|-------|--------|\n| **Claude Code** | Plugin or MCP | Verified |\n| **Claude Desktop** | MCP config | Verified |\n| **Cursor** | MCP config | Verified |\n| **Codex CLI** | MCP config | Verified |\n| **Gemini CLI** | MCP config | Verified |\n| **OpenCode** | MCP config | Community |\n| **Crush CLI** | MCP config | Community |\n| **Droid** | MCP config | Community |\n| **Windsurf** | MCP config | Community |\n| **Aider** | MCP config | Community |\n| **Continue** | MCP config | Community |\n\n## Built-in Skill Catalog\n\n\u003cdetails\u003e\n\u003csummary\u003e87 skills across 28 domains from 9 repos (click to expand)\u003c/summary\u003e\n\n**Core Workflow** — loaded for every project:\n\n| Domain | Skills | Description |\n|--------|--------|-------------|\n| TDD | 8 | Red-green-refactor, Go/Python/Django/Spring/C++ testing, E2E |\n| Planning | 3 | Implementation planning, CEO/eng review, execution |\n| Code Review | 4 | PR review, Go review, Python review, feedback workflow |\n| Debugging | 2 | Systematic debugging, investigation |\n| Verification | 4 | Build/lint/type gates, Django/Spring verification |\n| Brainstorming | 2 | Structured ideation, office hours |\n| Agent Orchestration | 5 | Autonomous loops, RFC pipelines, subagents, parallel dispatch |\n| Security | 5 | OWASP review, AgentShield scanning, Django/Spring security |\n| Shipping | 2 | CI/CD, deployment patterns |\n| Frontend Design | 5 | Anthropic official, Design Taste, Bencium UX, FDP, UI/UX Pro Max |\n| Git Workflow | 2 | Worktrees, branch management |\n\n**Language \u0026 Framework** — loaded when your stack matches:\n\n| Domain | Skills | Description |\n|--------|--------|-------------|\n| Go | 2 | Idiomatic patterns, conventions |\n| Python | 2 | Pythonic idioms, PEP 8 |\n| Django | 3 | Architecture, DRF, ORM, security, TDD |\n| Spring Boot | 4 | Architecture, security, TDD, verification |\n| Swift | 4 | SwiftUI, concurrency, actors, protocol DI |\n| C++ | 2 | Core Guidelines, GoogleTest |\n| Java | 2 | Standards, JPA/Hibernate |\n| Database | 3 | PostgreSQL, migrations, ClickHouse |\n| Docker | 1 | Compose, container security |\n\n**Infrastructure \u0026 Patterns:**\n\n| Domain | Skills | Description |\n|--------|--------|-------------|\n| API Design | 1 | REST patterns, pagination, versioning |\n| Frontend Patterns | 1 | React/Next.js state and performance |\n| Backend Patterns | 1 | Node/Express server patterns |\n| Coding Standards | 1 | Universal TS/JS/React standards |\n\n**Specialized:**\n\n| Domain | Skills | Description |\n|--------|--------|-------------|\n| Content \u0026 Business | 6 | Articles, investor materials, outreach, market research |\n| 3D Animation | 5 | Three.js, GSAP, React Three Fiber, Framer Motion, Babylon.js |\n| Agent Engineering | 4 | Agent harness, eval, cost optimization |\n| Meta/Tooling | 5 | Skill management, compaction, learning, browsing |\n\n\u003c/details\u003e\n\n## MCP Tools\n\n| Tool | Description |\n|------|-------------|\n| `superskill` | Route to the best skill by task description, domain, or skill ID |\n| `vault_skill` | Skill catalog, collisions, resolution, generation |\n| `vault_project_context` | Auto-detected project context from CWD |\n| `vault_init` | Generate draft context.md from a git repo |\n| `vault_task` | Task management (add/list/update/board) |\n| `vault_decide` | Log architecture decisions |\n| `vault_learn` | Capture and list learnings |\n| `vault_resume` | Resume context — recent sessions, interrupted work, next steps |\n| `vault_session` | Multi-agent session coordination |\n| `vault_read` | Read file or directory from vault |\n| `vault_write` | Write/append/prepend content |\n| `vault_search` | Full-text search across vault |\n| `vault_prune` | Archive stale content |\n| `vault_stats` | Vault content statistics |\n| `vault_deprecate` | Mark items as deprecated |\n\n## Configuration\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `VAULT_PATH` | `~/Vaults/ai` | Path to knowledge vault |\n| `MAX_INJECT_TOKENS` | `1500` | Max tokens for context injection |\n| `SESSION_TTL_HOURS` | `2` | Session heartbeat TTL |\n\n## Roadmap\n\nSee [GitHub Milestones](https://github.com/permanu/superskill/milestones) for planned work.\n\n## Contributing\n\nSee [CONTRIBUTING.md](./CONTRIBUTING.md).\n\n## License\n\nAGPL-3.0-or-later — See [LICENSE](./LICENSE)\n\nCopyright 2026 Permanu (Atharva Pandey)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpermanu%2Fsuperskill","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpermanu%2Fsuperskill","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpermanu%2Fsuperskill/lists"}