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

9,019 results · page 124 of 301

  • celltypistSkillAI & models

    "Use CellTypist for single-cell RNA-seq cell type annotation, model

    Ready to connect★ 278

    github.com/vectorspacelab/arex-skill85 stars

    View details
  • chatglm2-6bSkillAI & models

    "Guides ChatGLM2-6B Transformers inference, local demos,

    Ready to connect★ 278

    github.com/vectorspacelab/arex-skill85 stars

    View details
  • chinese-bert-wwmSkillAI & models

    "Route Chinese-BERT-wwm model loading, model selection, benchmark

    Ready to connect★ 278

    github.com/vectorspacelab/arex-skill85 stars

    View details
  • chinese-llama-alpacaSkillAI & models

    "Route Chinese-LLaMA-Alpaca model reconstruction,

    Ready to connect★ 278

    github.com/vectorspacelab/arex-skill85 stars

    View details
  • chinese-llama-alpaca-2SkillAI & models

    "Routes Chinese-LLaMA-Alpaca-2 training, inference, serving,

    Ready to connect★ 278

    github.com/vectorspacelab/arex-skill85 stars

    View details
  • claude-code-reverseSkillAI & models

    Performs read-only static reverse engineering of local executables, application binaries, and version artifacts that the user owns or is explicitly authorized to analyze, including Claude Code and other CLIs, Mach-O, ELF, PE, Wasm, or packaged apps. Use only when the user explicitly asks to 'reverse

    Ready to connect★ 278

    github.com/majiayu000/spellbook278 stars

    View details
  • clawbioSkillAI & models

    "Use ClawBio for local-first bioinformatics agent workflows:

    Ready to connect★ 278

    github.com/vectorspacelab/arex-skill85 stars

    View details
  • codex-retrospectiveSkillAI & models

    Use when you want Codex to review its own recent history (last N days or specific period) and improve its behavior. Produces minimal, high-signal updates to AGENTS.md and tiny reusable skills. The goal is long-term fluency — Codex gradually becomes better at your specific style, constraints, and wor

    Ready to connect★ 278

    github.com/majiayu000/spellbook278 stars

    View details
  • colossal-aiSkillAI & models

    "Use ColossalAI for distributed PyTorch training, large-model

    Ready to connect★ 278

    github.com/vectorspacelab/arex-skill85 stars

    View details
  • coremltoolsSkillAI & models

    "Operate Core ML Tools workflows for model conversion, Core ML

    Ready to connect★ 278

    github.com/vectorspacelab/arex-skill85 stars

    View details
  • crewaiSkillAI & models

    "Routes agents using or contributing to CrewAI, including crews,

    Ready to connect★ 278

    github.com/vectorspacelab/arex-skill85 stars

    View details
  • harmonyos-appSkillAI & models

    HarmonyOS application development expert. Use when building HarmonyOS apps with ArkTS, ArkUI, Stage model, and distributed capabilities. Covers HarmonyOS NEXT (API 12+) best practices.

    Ready to connect★ 278

    github.com/majiayu000/spellbook278 stars

    View details
  • multi-ai-researchSkillAI & models

    Parallel multi-AI cross-validation research workflow (大版本). Dispatch N internal sub-agents + grok + gemini in parallel, automatically cross-validate findings, tier by confidence (strong consensus / partial / conflict / insufficient), generate tiered action items with arbitration. Use when user says

    Ready to connect★ 278

    github.com/majiayu000/spellbook278 stars

    View details
  • product-discoverySkillAI & models

    Product discovery and market research expert. Use when validating product ideas, conducting market research, user interviews, competitive analysis, or opportunity assessment. Covers JTBD, Kano model, and Value Proposition Canvas.

    Ready to connect★ 278

    github.com/majiayu000/spellbook278 stars

    View details
  • recapSkillAI & models

    Review your Claude Code usage from the last N days — scans raw session data, groups and summarizes "what I've been doing" by topic, and outputs patterns, risks, and add/remove suggestions from a personal operating system perspective. Use when the user says /recap, "see what I've done these past few

    Ready to connect★ 278

    github.com/majiayu000/spellbook278 stars

    View details
  • repo-agent-context-auditSkillAI & models

    Audit and recommend improvements for a repository's agent-readable context, including AGENTS.md, CLAUDE.md, WARP.md, CONTRIBUTING.md, .agents/skills, and specs/ PRODUCT.md and TECH.md contracts. Use when asked to review, score, assess, or standardize repo instructions, agent onboarding, spec workflo

    Ready to connect★ 278

    github.com/majiayu000/spellbook278 stars

    View details
  • skill-usage-statsSkillAI & models

    Read-only statistics of Skill usage evidence for Claude/Codex and agent configuration health checks. Use only for explicit health checks, configuration diagnostics, usage rankings, or low-usage candidate requests; it identifies enabled plugins and lists batch audit reads separately. Do not use for c

    Ready to connect★ 278

    github.com/majiayu000/spellbook278 stars

    View details
  • address-pr-review-commentsSkillAI & models

    Use when fetching, triaging, or addressing PR review comments from GitHub, copied text, cloud AI reviewers, or other coding agents in the MindRoom repository.

    Ready to connect★ 277

    github.com/mindroom-ai/mindroom257 stars

    View details
  • market-to-devs-sell-to-buyersSkillAI & models

    Turn developer love into revenue by enabling champions and choosing a GTM model. Use when developers adopt the free tier but nobody pays, when the user is cold-selling the VP instead of arming the developer, or when picking between open-source, PLG, inbound, and sales-led.

    Ready to connect★ 277

    github.com/aidevgtm/gtm-cofounder277 stars

    View details
  • native-subagent-pr-loopSkillAI & models

    Use when the user asks for native Codex sub-agents, parallel PR review agents, unbiased re-review loops, or main-thread fixes after agent findings in the MindRoom repository.

    Ready to connect★ 277

    github.com/mindroom-ai/mindroom257 stars

    View details
  • review-the-workSkillAI & models

    Before showing the user any substantive GTM deliverable (positioning, value prop, homepage, launch post, pricing, sales script, the brief or roadmap), stress-test it against the standard as an independent critic, because the agent that wrote it is the worst judge of whether it is good. Use as a gate

    Ready to connect★ 277

    github.com/aidevgtm/gtm-cofounder277 stars

    View details
  • start-hereSkillAI & models

    Interview the user once and write a docs/gtm-cofounder/founder-brief.md that every other skill reads first, so the advice is about their real business, not a textbook. Use this before anything else, or whenever the agent lacks context on the user's product, ICP, market, or stage, or is giving generi

    Ready to connect★ 277

    github.com/aidevgtm/gtm-cofounder277 stars

    View details
  • ruminateSkillAI & models

    Mine past Claude Code and Codex conversations for uncaptured patterns, corrections, and knowledge. Cross-references with existing brain content. Triggers: "ruminate", "mine my history", "what have I been working on", "review past sessions", "extract learnings".

    Ready to connect★ 275

    github.com/poteto/noodle268 stars

    View details
  • worktreeSkillAI & models

    Use for concurrent sessions, agent team isolation, or any work needing a separate branch. Critical for multi-agent workflows. Triggers: "worktree", "new worktree", "clean up worktrees", "need isolation", or when spawning agent teams.

    Ready to connect★ 275

    github.com/poteto/noodle268 stars

    View details
  • engineering-journalSkillAI & models

    Use when starting or picking up a non-trivial effort (feature, investigation, perf probe, refactor, migration) in a shared repo where teammates or future agents must coordinate or hand off; when a repo has no durable in-tree record of decisions and dead-ends; when you're about to drop a well-measure

    Ready to connect★ 274

    github.com/iopsystems/rezolus272 stars

    View details
  • code-transformSkillAI & models

    Code transformation tools for repairing, simplifying, and extracting Lean proofs

    Ready to connect★ 273

    github.com/project-numina/numina-lean-agent271 stars

    View details
  • sorrifierSkillAI & models

    Isolates failing proof steps by replacing them with `sorry` and extracting them into standalone lemmas to modularize and decouple complex Lean 4 proofs.

    Ready to connect★ 273

    github.com/project-numina/numina-lean-agent271 stars

    View details
  • bashkitSkillAI & models

    Use when a user wants to run Bashkit, write scripts for Bashkit, use Bashkit as an LLM tool/runtime, call Bashkit from Rust/Python/JavaScript/TypeScript, use its CLI, understand supported builtins/languages, or find practical Bashkit examples, docs, packages, and resources.

    Ready to connect★ 272

    github.com/everruns/bashkit262 stars

    View details
  • building-native-uiSkillAI & models

    Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.

    Ready to connect★ 270

    github.com/ruizrica/agent-pi267 stars

    View details
  • expo-dev-clientSkillAI & models

    Build and distribute Expo development clients locally or via TestFlight

    Ready to connect★ 270

    github.com/ruizrica/agent-pi267 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.

54,764 of the 55,196 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