Skills.

Give your AI a better way to work.

A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.

Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.

Category: AI & models

9,105 results · page 166 of 304

  • dspy-rag-pipelineSkillAI & models

    Use for RAG pipelines, retrieval augmented generation, ColBERTv2, context retrieval, multi-hop RAG, and grounded DSPy answers.

    Ready to connect★ 123

    github.com/omidzamani/dspy-skills123 stars

    View details
  • dspy-react-agent-builderSkillAI & models

    Use for ReAct agents, tool-calling agents, dspy.ReAct, multi-step reasoning and acting, and GEPA agent optimization.

    Ready to connect★ 123

    github.com/omidzamani/dspy-skills123 stars

    View details
  • incubateSkillAI & models

    Clone or create repos for active development — the right hand of /learn. Use when user says "incubate [repo]", "work on [repo]", "clone for dev", or wants to set up a dev workflow. Use --wt SLUG to give each agent its own git worktree body when several agents develop the same repo in parallel. Do NO

    Ready to connect★ 123

    github.com/soul-brews-studio/arra-oracle-skills-cli121 stars

    View details
  • oracle-prismSkillAI & models

    Multi-perspective analysis — one agent transforms through 5 lenses (Archaeologist, Bug Hunter, Skeptic, Architect, Auditor) inline, no subagents. Use when user says "prism", "oracle-prism", "multi-perspective", "มองหลายมุม", "did we miss anything", "analyze from all angles", or before closing a sess

    Ready to connect★ 123

    github.com/soul-brews-studio/arra-oracle-skills-cli121 stars

    View details
  • oracle-title-forgeSkillAI & models

    Forge a title + subtitle (or reframe) for a BOOK, article, talk, or any technical piece, then hand off to a cover so it has LIFE and honesty — not clinical/dated. The method that produced 'Claude Code Channel ปะทะ Hermes Gateway'. Describe-before-you-name, find the real tension, prism the candidates

    Ready to connect★ 123

    github.com/soul-brews-studio/arra-oracle-skills-cli121 stars

    View details
  • rrrSkillAI & models

    Create a session retrospective with an AI diary and reusable lessons. Supports foreground, background, and combined execution across compatible agent hosts.

    Ready to connect★ 123

    github.com/soul-brews-studio/arra-oracle-skills-cli121 stars

    View details
  • wayfinder-mapsSkillAI & models

    Plan a huge chunk of work — more than one agent session can hold — as a shared map of investigation tickets, and resolve them one at a time until the way to the destination is clear.

    Ready to connect★ 123

    github.com/rengwu/wayfinder-maps123 stars

    View details
  • who-are-youSkillAI & models

    Know ourselves — show current AI identity, model info, session stats, and Oracle philosophy. Use when user asks "who are you", "who", "who we are", "what model", or wants to check current AI identity and session context. Do NOT trigger for "what is oracle" (use /about-oracle), "philosophy" or "princ

    Ready to connect★ 123

    github.com/soul-brews-studio/arra-oracle-skills-cli121 stars

    View details
  • agentburnSkillAI & models

    Answer questions about this agent's own token spend, usage limits and burn. Use when the user asks "how much am I spending", "where do my tokens go", "why do I keep hitting my limit", "what ate my 5-hour window", "what did you burn while I slept", "почему так дорого", "сколько я трачу", "почему упёр

    Ready to connect★ 119

    github.com/socialpranker/agentburn122 stars

    View details
  • game-modeSkillAI & models

    Track your Claude Code feature usage, earn levels, and see your stats. Gamified learning mode.

    Ready to connect★ 122

    github.com/orinachum/claude-code-guide122 stars

    View details
  • introspectSkillAI & models

    Introspect your project — audit lifecycle coverage, find gaps, and improve your development environment.

    Ready to connect★ 122

    github.com/orinachum/claude-code-guide122 stars

    View details
  • level-upSkillAI & models

    See your feature roadmap and get a personalized hint on what to try next.

    Ready to connect★ 122

    github.com/orinachum/claude-code-guide122 stars

    View details
  • migrate-to-claudeSkillAI & models

    Migrate your AI coding assistant config (Cursor, Windsurf, Copilot, Continue, Aider, Cody, Codex) to Claude Code. Discovers existing configs, trims bloat, and proposes a clean migration plan.

    Ready to connect★ 122

    github.com/orinachum/claude-code-guide122 stars

    View details
  • update-claudeSkillAI & models

    Summarize the current session and propose improvements to CLAUDE.md, rules, docs, and skills, applying them after user confirmation. Use only when explicitly invoked.

    Ready to connect★ 122

    github.com/millenniumdawn/millennium-dawn113 stars

    View details
  • visualize-setupSkillAI & models

    Generate an HTML dashboard visualizing all installed Claude Code skills, plugins, and MCP servers with usage statistics and martial arts belt levels.

    Ready to connect★ 122

    github.com/orinachum/claude-code-guide122 stars

    View details
  • write-egma-testsSkillAI & models

    Write or edit tests for a voice agent that can run on the Egma platform.

    Ready to connect★ 122

    github.com/egma-ai/egma102 stars

    View details
  • ai-system-testingSkillAI & models

    Test AI/LLM features that ship in your product. Covers prompt regression testing, response quality evaluation, tool-call validation, hallucination and RAG grounding checks, nondeterministic-output strategies, red-team/safety scans, eval frameworks, and agent-as-target injection (indirect injection v

    Ready to connect★ 121

    github.com/petrkindlmann/qa-skills121 stars

    View details
  • bug-reproductionSkillAI & models

    Turn a vague bug report into a VERIFIED minimal reproduction and then a failing regression test, agent-driven end to end. Covers extracting the implicit repro from a thin report (env, build, steps, data), the reproduce-minimize-isolate-capture loop, git bisect to find the introducing commit, buildin

    Ready to connect★ 121

    github.com/petrkindlmann/qa-skills121 stars

    View details
  • modelsSkillAI & models

    How to use Colin to compile agent skills from live sources. Use when working with Colin projects, templates, compilation, or skill management.

    Ready to connect★ 121

    github.com/prefecthq/colin121 stars

    View details
  • shift-left-testingSkillAI & models

    Move quality earlier in the development lifecycle. Covers dev/QA pairing patterns, Three Amigos sessions, TDD facilitation (Red-Green-Refactor), PR review checklists for testability, and Definition of Done with quality gates. Includes shift-left maturity model for team assessment. Use when: "shift l

    Ready to connect★ 121

    github.com/petrkindlmann/qa-skills121 stars

    View details
  • architecture-implementation-reviewSkillAI & models

    Reviews architecture-bearing production changes, not general implementation correctness. Must be invoked as a sub-agent: the main agent should ask a sub-agent to perform the review using this skill, rather than loading the skill directly in the main agent context. Run that sub-agent with a medium-in

    Ready to connect★ 120

    github.com/sesori-ai/sesori_apps_monorepo115 stars

    View details
  • architecture-plan-reviewSkillAI & models

    Reviews an architecture-bearing development plan against strict Sesori architectural rules. Must be invoked as a sub-agent: the main agent should ask a sub-agent to perform the review using this skill, rather than loading the skill directly in the main agent context. Run that sub-agent with a medium

    Ready to connect★ 120

    github.com/sesori-ai/sesori_apps_monorepo115 stars

    View details
  • capability-experimentsSkillAI & models

    Experiment with model capabilities — HTML reports, embedded questionnaires, proactive research, multi-step reasoning

    Ready to connect★ 120

    github.com/jellydn/my-ai-tools119 stars

    View details
  • claude-improve-configSkillAI & models

    Self-reflect on the current session to identify mistakes and propose improvements to .claude configuration (CLAUDE.md, hooks, skills).

    Ready to connect★ 120

    github.com/anam-org/metaxy119 stars

    View details
  • cookSkillAI & models

    Implement, build, create, or add any feature, endpoint, page, component, or functionality. Use this skill whenever the user asks you to write new code or make code changes — whether it's adding an API endpoint, building a UI page, creating an export feature, wiring up a webhook, implementing a searc

    Ready to connect★ 120

    github.com/avibebuilder/claude-prime120 stars

    View details
  • discussSkillAI & models

    Brainstorms and debates approaches, then drives toward an actionable decision. Use whenever someone needs a thinking partner for a decision they're facing: 'discuss', 'debate', 'brainstorm', 'weigh options', 'tradeoffs', 'should I do X or Y', 'help me decide', 'I'm torn between', 'sanity check my th

    Ready to connect★ 120

    github.com/avibebuilder/claude-prime120 stars

    View details
  • give-planSkillAI & models

    Use when the user wants a written, reviewable plan or spec produced before coding starts. Triggers on: mapping out changes without implementing, thinking through risks of upgrades or migrations, evaluating approaches before committing to one, writing specs for team review, phasing work into stages,

    Ready to connect★ 120

    github.com/avibebuilder/claude-prime120 stars

    View details
  • gpt6-astra-skill-optimizerSkillAI & models

    Audit one selected project and its explicitly related Skills for GPT-6 Astra compatibility, then propose evidence-backed improvements. Use when the user asks to audit a project and its Skills, check Astra readiness, diagnose repeated Skill failures, or apply an approved Skill fix. Read-only by defau

    Ready to connect★ 120

    github.com/adand-91/gpt-6-astra-skill120 stars

    View details
  • humanizerSkillAI & models

    Rewrite existing text so it stops sounding AI-generated. Triggers on "humanize this", "un-ChatGPT it", "doesn't scream LLM", "strip the AI voice", or naming specific AI tells (em dashes, "it's not just X it's Y", "stands as a testament", "thrilled to announce", emoji-headed bullets, LinkedIn cringe)

    Ready to connect★ 120

    github.com/avibebuilder/claude-prime120 stars

    View details
  • monorepoSkillAI & models

    MUST use for ANY query mentioning packages, monorepo, workspace, catalog, turbo, turborepo, or pnpm in a multi-package context. MUST use when sharing config (ESLint, tsconfig, prettier) across packages, fixing build order between packages, adding new packages, scoping CI installs/caching to changed

    Ready to connect★ 120

    github.com/avibebuilder/claude-prime120 stars

    View details

What is a skill?

A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.

55,111 of the 55,543 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.

Install one and every AI you use gets it

Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.

Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.

See how to connect your AI