# skills-hub.ai

> The open registry for AI coding skills — install, version, and compose 4,400+ SKILL.md files in one command. Works with Claude Code, Cursor, Codex CLI, Windsurf, GitHub Copilot, and any MCP-compatible tool.

## Get started

- [Get started in 60 seconds](https://skills-hub.ai/docs/getting-started): Install your first skill with `npx @skills-hub-ai/cli install code-review`.
- [Organizations](https://skills-hub.ai/docs/organizations): Private team registries — invites, onboarding, scoped visibility, and publishing org skills.
- [Organization administration](https://skills-hub.ai/docs/organizations/admin): Departments, teams, roles, bulk invitations, install policy, and analytics.
- [Organization governance](https://skills-hub.ai/docs/organizations/governance): Approval workflow, audit trail, and a recommended starting configuration.
- [CLI reference](https://skills-hub.ai/docs/cli): Every command, flag, and config option for the `skills-hub` CLI.
- [Integrations](https://skills-hub.ai/docs/integrations): How to wire skills-hub into Claude Code, Cursor, Codex, Windsurf, and MCP clients.
- [Automated workflows](https://skills-hub.ai/docs/workflows): Compose multiple skills into pipelines and deploy as agents.

## Pillar concepts

- [Claude skills](https://skills-hub.ai/claude-skills): What Claude skills are, the best ones, and how to install them.
- [Cursor rules](https://skills-hub.ai/cursor-rules): Open library of `.cursorrules` and `.mdc` files; how rules differ from skills.
- [Codex CLI skills](https://skills-hub.ai/codex-skills): Skills for OpenAI Codex CLI via the open Agent Skills standard.
- [MCP skills](https://skills-hub.ai/mcp-skills): Search the catalog from any MCP-compatible client via `@skills-hub-ai/mcp`.
- [SKILL.md format](https://skills-hub.ai/skill-md): The open Agent Skills standard — write your own portable skill in Markdown.

## Per-tool landings

- [Claude skills](https://skills-hub.ai/claude-skills): Skills for Claude Code & Claude Desktop.
- [Cursor rules](https://skills-hub.ai/cursor-rules): .cursorrules and .mdc files for Cursor IDE.
- [Codex CLI skills](https://skills-hub.ai/codex-skills): Skills for OpenAI Codex CLI.
- [MCP skills](https://skills-hub.ai/mcp-skills): Skills via Model Context Protocol.
- [Windsurf skills](https://skills-hub.ai/windsurf-skills): Skills for Codeium Windsurf IDE.
- [GitHub Copilot skills](https://skills-hub.ai/copilot-skills): Custom instructions for Copilot Chat.
- [Cline skills](https://skills-hub.ai/cline-skills): Skills for the open-source Cline coding agent.
- [Antigravity skills](https://skills-hub.ai/antigravity-skills): Skills for Google Antigravity 2.0 (launched May 19, 2026).
- [Kiro skills](https://skills-hub.ai/kiro-skills): Skills for AWS Kiro — the spec-driven AI IDE.

## Concept landings (new in 2026)

- [Agent teams](https://skills-hub.ai/agent-teams): Multi-agent / subagents pattern guide — Claude Code, Antigravity, Cursor.
- [Spec-driven skills](https://skills-hub.ai/spec-driven-skills): Spec-first AI coding pattern, native in AWS Kiro.
- [MCP servers](https://skills-hub.ai/mcp-servers): Browse the best Model Context Protocol servers in 2026 (9,400+).
- [Best AI coding tools](https://skills-hub.ai/best-ai-coding-tools): Ranked roundup of 11 best AI coding tools — Claude, Cursor, Antigravity, more.

## SDLC by phase

- [AI code review](https://skills-hub.ai/ai-code-review): AI-powered PR review and code review tools.
- [AI testing tools](https://skills-hub.ai/ai-testing-tools): AI for unit, integration, E2E, contract, and load tests.
- [AI deployment skills](https://skills-hub.ai/ai-deployment-skills): AI for Docker, Kubernetes, CI/CD, Terraform, mobile publishing.
- [AI security tools](https://skills-hub.ai/ai-security-tools): OWASP, pentest, dependency CVEs, HIPAA, GDPR, SOC 2 audits with AI.

## By language and framework (/skills-for)

- [AI skills for TypeScript](https://skills-hub.ai/skills-for/typescript)
- [AI skills for Python](https://skills-hub.ai/skills-for/python)
- [AI skills for React](https://skills-hub.ai/skills-for/react)
- [AI skills for Next.js](https://skills-hub.ai/skills-for/nextjs)
- [AI skills for Rust](https://skills-hub.ai/skills-for/rust)
- [AI skills for Go](https://skills-hub.ai/skills-for/go)
- [All languages](https://skills-hub.ai/skills-for): Browse all language and framework landings.

## Reference

- [For every tool (hub)](https://skills-hub.ai/for-every-tool): One page listing every supported AI tool with its dedicated landing.
- [AI coding glossary](https://skills-hub.ai/glossary): Definitions for skill, MCP, subagent, agent teams, slash command, hook, scheduled tasks, vibe coding, spec-driven development, and 15+ more 2026 AI coding terms.

## Interactive

- [AI coding tool quiz](https://skills-hub.ai/quiz/best-ai-tool): 5-question quiz that recommends the right AI coding tool (Claude Code, Cursor, Antigravity 2.0, Copilot, Windsurf, Codex, Cline, Kiro, or Gemini CLI). Shareable result with custom-generated OG image.

## Compare

- [Claude Code vs Cursor](https://skills-hub.ai/compare/claude-code-vs-cursor): Side-by-side comparison of the two leading AI coding tools.
- [Claude Code vs Codex CLI](https://skills-hub.ai/compare/claude-code-vs-codex): Anthropic's terminal agent vs OpenAI's open-source terminal agent.
- [Cursor vs Windsurf](https://skills-hub.ai/compare/cursor-vs-windsurf): The two leading AI-first IDEs, head to head.
- [Claude skills vs Cursor rules](https://skills-hub.ai/compare/claude-skills-vs-cursor-rules): Two different paradigms for codifying AI behavior.
- [MCP vs Agent Skills](https://skills-hub.ai/compare/mcp-vs-skills): When to use each open standard.
- [Claude Code vs GitHub Copilot](https://skills-hub.ai/compare/claude-code-vs-copilot): Agent vs autocomplete — which fits which workflow.
- [Cline vs Cursor](https://skills-hub.ai/compare/cline-vs-cursor): Open-source agent vs proprietary AI-first IDE.
- [Claude Desktop vs Claude Code](https://skills-hub.ai/compare/claude-desktop-vs-claude-code): Chat app with MCP vs terminal coding agent.
- [Gemini CLI vs Claude Code](https://skills-hub.ai/compare/gemini-cli-vs-claude-code): Google's terminal agent vs Anthropic's terminal agent.
- [Claude Code vs Antigravity 2.0](https://skills-hub.ai/compare/claude-code-vs-antigravity): Anthropic's agent vs Google's new multi-agent IDE+CLI.
- [Cursor vs Windsurf vs Claude Code](https://skills-hub.ai/compare/cursor-vs-windsurf-vs-claude-code): The three-way AI coding showdown.
- [Opus 4.7 vs GPT-5.5 vs Gemini 3.1 Pro](https://skills-hub.ai/compare/opus-4-7-vs-gpt-5-5-vs-gemini-3-1-pro): Which 2026 flagship model codes best.
- [Kiro vs Cursor](https://skills-hub.ai/compare/kiro-vs-cursor): Spec-driven IDE vs vibe-coding.
- [Anthropic vs OpenAI for coding](https://skills-hub.ai/compare/anthropic-vs-openai-for-coding): Which AI stack to build on.
- [All comparisons](https://skills-hub.ai/compare): Full list of AI tool comparisons.

## Alternatives

- [Best Cursor alternatives](https://skills-hub.ai/alternatives/cursor): Side-by-side roundup of Windsurf, Claude Code, Cline, Copilot, Codex CLI, Continue.dev.
- [Best Claude Code alternatives](https://skills-hub.ai/alternatives/claude-code): Side-by-side roundup of Codex CLI, Cursor, Gemini CLI, Cline, Aider.
- [Best GitHub Copilot alternatives](https://skills-hub.ai/alternatives/copilot): Side-by-side roundup of Cursor, Codeium, Windsurf, Claude Code, Cline, Continue.dev.
- [All alternatives](https://skills-hub.ai/alternatives): Full list of alternative roundups.

## Discover

- [Browse 4,400+ skills](https://skills-hub.ai/browse): Filter by category, platform, source, tag, SDLC phase, quality score, or security grade.
- [Blog](https://skills-hub.ai/blog): Articles on Claude skills, SKILL.md format, AI agent infrastructure.
- [Kimi K2.7 Code in GitHub Copilot: The First Open-Weight Model in a Mainstream AI Coding Assistant](https://skills-hub.ai/blog/kimi-k2-7-code-github-copilot-2026): Moonshot AI's Kimi K2.7 Code landed in GitHub Copilot July 1 2026 — first open-weight, MIT-licensed model in the five-lab model picker. 81.1% MCPMark, 32B active params (1T total MoE), GPT-5.4 mini tier pricing, hosted on Azure. Task routing guide, admin setup for Business/Enterprise, open-weight compliance checklist.
- [GPT-5.6 Sol, Terra, and Luna: The Developer's Tier-Selection Guide](https://skills-hub.ai/blog/gpt-5-6-sol-terra-luna-coding-guide-2026): OpenAI's GPT-5.6 (June 26, 2026) ships as Sol ($5/$30), Terra ($2.50/$15), and Luna ($1/$6) per 1M tokens — with Sol ultra mode for agentic subagent reasoning and explicit cache breakpoints for 80%+ input cost savings. Tier-selection decision tree, pricing math, and Codex CLI wiring guide.
- [Claude Code's July Pivot: Background Agents Deliver PRs, Manual Mode Is the New Default](https://skills-hub.ai/blog/claude-code-auto-pr-manual-mode-july-2026): Six releases in eight days (v2.1.197–204, July 1–8 2026) — background agents now auto-commit, push, and open draft PRs when worktree tasks finish; Manual is the enforced default permission mode; dynamic workflow sizing added; 25+ background-agent reliability fixes.
- [X Ships an Official MCP Server: What XMCP Means for Your AI Coding Workflow](https://skills-hub.ai/blog/x-xmcp-official-mcp-server-2026): X launched XMCP on June 30 2026 — a hosted MCP server at api.x.com/mcp with 200+ tools auto-generated from the X API OpenAPI spec. Setup guide for Claude Code and Cursor, what you can query, pricing, and four production-ready agentic workflows.
- [claude mcp login & /rewind: The Two Claude Code June 2026 Features Worth Your Attention](https://skills-hub.ai/blog/claude-code-mcp-login-rewind-2026): Claude Code v2.1.185–v2.1.193 (June 22–26) shipped OAuth-native MCP server auth with `claude mcp login` and session context recovery with `/rewind`. Setup guide, token lifecycle, and daily workflow patterns.
- [MCP 2026-07-28: Six Breaking Changes and the New MCP Apps Primitive](https://skills-hub.ai/blog/mcp-spec-july-28-apps-migration-2026): The largest MCP revision since launch ships July 28. Sessions are gone, six things will break in production servers, and MCP Apps (SEP-1865) lets tools ship interactive HTML UIs to any host. Migration checklist and MCP Apps primer inside.
- [Claude Sonnet 5: The Agentic Upgrade That Changes Your Daily Workflow](https://skills-hub.ai/blog/claude-sonnet-5-agentic-coding-2026): Claude Sonnet 5 (June 30 2026) — 80.5% on Terminal-bench 2.1 (+13.5pp over Sonnet 4.6), configurable reasoning effort levels, $2/M input introductory pricing. What changes for Claude Code users, how to configure effort levels, and when to keep Opus 4.8.
- [Claude Enterprise-Managed Auth: Zero-Touch MCP Connectors via Okta](https://skills-hub.ai/blog/claude-mcp-enterprise-auth-okta-2026): Anthropic's June 18 2026 feature — admin provisions Okta once, employees inherit Asana, Atlassian, Figma, Linear, and four more MCP connectors automatically across Claude Chat, Claude Code, and Cowork. No per-user OAuth.
- [Gemini 2.5 Pro Deep Think: What 2M Tokens Means for AI Coding](https://skills-hub.ai/blog/gemini-2-5-pro-deep-think-coding-2026): Google's June 22 2026 release — 87.6% on LiveCodeBench, 2M token context window, visible Deep Think reasoning chains. What actually changes for developers building with AI: whole-codebase analysis, security audits across hundreds of files, and how it stacks up against Claude Fable 5.
- [Cascade is Dead: Migrate to Devin Local Today Before Your CI Breaks](https://skills-hub.ai/blog/cascade-eol-devin-local-migration-2026): Cascade (the original Windsurf local agent) is EOL July 1 2026. In-editor migration is automatic; CI scripts calling Cascade by name will break silently. Migration playbook, grep commands, ACP integration guide, and what Devin Local (Rust rewrite, 30% more token-efficient, subagent support) adds over Cascade.
- [ACP Spec 1.0: Build Your AI Agent Once, Run It in Every IDE](https://skills-hub.ai/blog/acp-spec-1-open-standard-2026): ACP Spec 1.0 is the first stable, open-governance release of the Agent Client Protocol — the LSP for AI coding agents. 25+ compatible agents including Claude Code, Codex, Devin Local, and OpenCode. JSON-RPC 2.0 wire protocol, capability negotiation, and Spaces context sharing. Setup guide with agents.json examples.
- [Gemini CLI Enterprise Pivot 2026](https://skills-hub.ai/blog/gemini-cli-enterprise-pivot-2026): Google closed Gemini CLI's free tier on June 18 2026 after 6,000 community PRs — migration guide and alternatives.
- [Kiro 0.12: Parallel Tasks and Quick Plan Mode](https://skills-hub.ai/blog/kiro-parallel-tasks-quick-plan-2026): Kiro 0.12 (May 2026) ships parallel task execution (4x faster), Quick Plan Mode (spec-to-code in a single pass), and pre-implementation requirements analysis.
- [Kiro Requirements Analysis: SMT Solver for AI Slop-Free Specs](https://skills-hub.ai/blog/kiro-requirements-analysis-smt-2026): Deep dive on Kiro's neurosymbolic Requirements Analysis engine — three-stage pipeline (LLM rewrite → formal logic → SMT proof) that catches logical contradictions in specs before code generation begins.
- [OpenAI Codex and GPT-5.5 on Amazon Bedrock: The Developer Playbook](https://skills-hub.ai/blog/openai-codex-aws-bedrock-2026): GPT-5.5, GPT-5.4, and Codex went GA on Amazon Bedrock June 1 2026 — auth wiring, VPC isolation, Responses API migration, and per-token cost modeling.
- [Claude Code Dynamic Workflows 2026](https://skills-hub.ai/blog/claude-code-dynamic-workflows-2026): v2.1.152–154 (May 27–29) ships dynamic workflows for 100+ background agents, MessageDisplay hooks, and hot-reloadable skills.
- [GitHub Copilot Browser Tools Are GA: AI Agents Now Verify Their Own Front-End Work](https://skills-hub.ai/blog/github-copilot-browser-tools-ga-2026): Browser tools hit GA in Copilot for VS Code on July 1 2026 — agents navigate, interact, and screenshot the running app mid-task. What changed from research preview, how to enable it, and how to replicate the workflow in Claude Code and Cursor via the new browser-agent-verify SKILL.md.
- [Best Claude skills (2026)](https://skills-hub.ai/blog/best-claude-skills-2026): Top 25 most-installed Claude skills, ranked.
- [GitHub Copilot Flex Billing 2026](https://skills-hub.ai/blog/github-copilot-flex-billing-2026): Complete playbook for the June 1 AI Credits transition — plans, credit math, budget controls, and 10-day checklist.
- [Windsurf 2.0: Agent Command Center, Spaces & Devin Cloud](https://skills-hub.ai/blog/windsurf-2-agent-command-center-2026): Deep dive on Windsurf 2.0 (April 15, 2026) — Agent Command Center Kanban, Spaces for persistent task context, and one-click Devin cloud handoff.
- [Cursor Composer 2.5: Build in Parallel, 10x Cheaper](https://skills-hub.ai/blog/cursor-composer-2-5-2026): Deep dive on Cursor Composer 2.5 (May 18, 2026) — Agent Swarm parallel architecture, targeted RL training, 79.8% SWE-bench at one-tenth the cost of Opus 4.7.
- [Google Antigravity 2.0 SDK: Build Custom Agents on Your Own Infrastructure](https://skills-hub.ai/blog/google-antigravity-2-sdk-2026): Everything developers need to know about the Antigravity 2.0 SDK, agy CLI, Managed Agents API, and multi-agent orchestration launched at Google I/O 2026.
- [Amazon Kiro: The Spec-Driven IDE That Takes Prototypes to Production](https://skills-hub.ai/blog/amazon-kiro-spec-driven-ide-2026): How AWS Kiro's spec-first workflow, EARS notation, agent hooks, and AWS MCP Server GA change the AI IDE landscape in 2026.
- [Categories](https://skills-hub.ai/categories): 23 categories — code review, testing, deploy, security, marketing, healthcare, legal, more.
- [Sources](https://skills-hub.ai/sources): 90+ official sources — Anthropic, Microsoft, Google, Vercel, Stripe, Cloudflare, and more.
- [Bundles](https://skills-hub.ai/bundles): Curated skill collections — install an entire workflow in one command.
- [Collections](https://skills-hub.ai/collections): Community-curated skill lists.
- [Leaderboard](https://skills-hub.ai/leaderboard): Most-installed skills in the last 24h, 7d, 30d, all-time.
- [Tags](https://skills-hub.ai/tags): Filter by free-form tag.

## Build and publish

- [Publish a skill](https://skills-hub.ai/publish): Upload a SKILL.md or generate one from a description.
- [About](https://skills-hub.ai/about): The mission and why we built this.
- [Authors](https://skills-hub.ai/authors): Contributors writing about Claude skills, SKILL.md format, and AI agent infrastructure.

## API

- REST: `https://api.skills-hub.ai/api/v1/` — skills, sources, search, categories, tags, reviews, installs, organizations, agents.
- Public skill: `https://api.skills-hub.ai/api/v1/skills/<slug>`
- All sources: `https://api.skills-hub.ai/api/v1/external-sources`
- Skills filtered by source: `https://api.skills-hub.ai/api/v1/skills?source=<slug>`

## CLI

```bash
npx @skills-hub-ai/cli install <slug>
npx @skills-hub-ai/cli search "code review"
npx @skills-hub-ai/cli publish ./SKILL.md
npx @skills-hub-ai/cli suggest
```

## MCP Server

```bash
claude mcp add skills-hub -- npx @skills-hub-ai/mcp
```

## SKILL.md format example

```markdown
---
name: code-review
description: Thorough code review — checks correctness, security, performance, tests.
version: 1.0.0
category: review
platforms:
  - CLAUDE_CODE
  - CURSOR
  - CODEX_CLI
---

When the user asks you to review code, follow these steps...
```

## Optional

- [npm organization](https://www.npmjs.com/org/skills-hub-ai): `@skills-hub-ai/cli`, `@skills-hub-ai/mcp`, `@skills-hub-ai/shared`, `@skills-hub-ai/skill-parser` — all MIT-licensed.
- [Skills registry repository](https://github.com/tinh2/skills-hub-registry): Public registry of community-contributed SKILL.md files synced daily to skills-hub.ai.
- [Privacy](https://skills-hub.ai/privacy)
- [Terms](https://skills-hub.ai/terms)