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 161 of 304

  • agent-sync-coordinatorSkillAI & models

    Agent skill for sync-coordinator - invoke with $agent-sync-coordinator

    Ready to connect★ 132

    github.com/henryalouf/ruflow123 stars

    View details
  • agent-tdd-london-swarmSkillAI & models

    Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm

    Ready to connect★ 132

    github.com/henryalouf/ruflow123 stars

    View details
  • agent-test-long-runnerSkillAI & models

    Agent skill for test-long-runner - invoke with $agent-test-long-runner

    Ready to connect★ 132

    github.com/henryalouf/ruflow123 stars

    View details
  • agent-testerSkillAI & models

    Agent skill for tester - invoke with $agent-tester

    Ready to connect★ 132

    github.com/henryalouf/ruflow123 stars

    View details
  • agent-topology-optimizerSkillAI & models

    Agent skill for topology-optimizer - invoke with $agent-topology-optimizer

    Ready to connect★ 132

    github.com/henryalouf/ruflow123 stars

    View details
  • agent-user-toolsSkillAI & models

    Agent skill for user-tools - invoke with $agent-user-tools

    Ready to connect★ 132

    github.com/henryalouf/ruflow123 stars

    View details
  • agent-v3-integration-architectSkillAI & models

    Agent skill for v3-integration-architect - invoke with $agent-v3-integration-architect

    Ready to connect★ 132

    github.com/henryalouf/ruflow123 stars

    View details
  • agent-v3-performance-engineerSkillAI & models

    Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer

    Ready to connect★ 132

    github.com/henryalouf/ruflow123 stars

    View details
  • agent-v3-queen-coordinatorSkillAI & models

    Agent skill for v3-queen-coordinator - invoke with $agent-v3-queen-coordinator

    Ready to connect★ 132

    github.com/henryalouf/ruflow123 stars

    View details
  • agent-worker-specialistSkillAI & models

    Agent skill for worker-specialist - invoke with $agent-worker-specialist

    Ready to connect★ 132

    github.com/henryalouf/ruflow123 stars

    View details
  • agent-workflow-automationSkillAI & models

    Agent skill for workflow-automation - invoke with $agent-workflow-automation

    Ready to connect★ 132

    github.com/henryalouf/ruflow123 stars

    View details
  • agentic-jujutsuSkillAI & models

    Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

    Ready to connect★ 132

    github.com/henryalouf/ruflow123 stars

    View details
  • audit-claude-settingsSkillAI & models

    Use when auditing Claude Code settings and env vars against the latest docs and suggest tailored changes

    Ready to connect★ 130

    github.com/vinta/hal-9000132 stars

    View details
  • krypton-planningSkillAI & models

    Use when a user has a feature request, bugfix, refactor, migration, architecture change, or product goal and needs an implementation plan before coding. Use especially when wrong ownership, duplicate paths, stale contracts, weak evidence, or unclear cutover would make plausible agent work dangerous.

    Ready to connect★ 132

    github.com/jturntdev/krypton132 stars

    View details
  • refactor-agents-mdSkillAI & models

    Use when about to refactor or refine a user-level or project-level AGENTS.md

    Ready to connect★ 130

    github.com/vinta/hal-9000132 stars

    View details
  • refactor-claude-mdSkillAI & models

    Use when about to refactor or refine a user-level or project-level CLAUDE.md

    Ready to connect★ 130

    github.com/vinta/hal-9000132 stars

    View details
  • debug-agentSkillAI & models

    Investigate a reported bug using source, tests, or runtime evidence to establish its cause.

    Ready to connect★ 131

    github.com/bitsocialnet/5chan131 stars

    View details
  • academic-research-publishing-masterSkillAI & models

    科研方法与论文发表 (Academic Research and Publishing) Master OS — automated mastery of Academic Research and Publishing: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. Trigger this skill when the user works on Academic Research and Publishing problems and wants indu

    Ready to connect★ 130

    github.com/swaylq/master-skill130 stars

    View details
  • cory-doctorow-effSkillAI & models

    Master skill — input an industry and it automatically researches 6 tracks [industry leaders / tool map / workflows / knowledge canon / information sources / terminology standards] → distills them into a runnable industry Master OS skill; install it on any Claude Code / OpenClaw / Codex / Hermes agen

    Ready to connect★ 130

    github.com/swaylq/master-skill130 stars

    View details
  • erich-ferrari-ofacSkillAI & models

    大师.skill — Input an industry, automatically research 6 tracks [industry leaders / tool map / workflows / knowledge canon / information sources / terminology standards] → distill them into a runnable industry Master OS skill; install it on any Claude Code / OpenClaw / Codex / Hermes agent to put it i

    Ready to connect★ 130

    github.com/swaylq/master-skill130 stars

    View details
  • haxcms-lrs-raterSkillAI & models

    Run BookLooky's Looky Rating System (LRS) content rating and minimum-age recommendation on a HAXcms site's aggregated content — either a local site checkout or a live published URL like btopro.com — entirely through the invoking agent's own reasoning, no API key or network call to an LLM required. U

    Ready to connect★ 130

    github.com/haxtheweb/haxcms-php129 stars

    View details
  • john-gottman-perspectiveSkillAI & models

    John Gottman (Gottman Institute) perspective. Representative of evidence-based marriage research. Four Horsemen + 5:1 Magic Ratio + Cascade Model. When invoking this skill, use the Gottman framework to assess relationship health.

    Ready to connect★ 130

    github.com/swaylq/master-skill130 stars

    View details
  • lawrence-lessig-code-is-lawSkillAI & models

    大师.skill — Input an industry and it automatically researches 6 tracks [industry leaders / tool map / workflows / knowledge canon / information sources / terminology standards] → distills them into a runnable industry Master OS skill; install it on any Claude Code / OpenClaw / Codex / Hermes agent to

    Ready to connect★ 130

    github.com/swaylq/master-skill130 stars

    View details
  • python-aiSkillAI & models

    Build and troubleshoot Python AI applications involving model APIs, local LLMs, retrieval, tools, agents, prompts, evaluation, or AI dependencies.

    Ready to connect★ 130

    github.com/christitustech/titus-ai120 stars

    View details
  • bootstrap-iosSkillAI & models

    Bootstrap agents for iOS, iPadOS, macOS, Swift, SwiftUI, SwiftData/Core Data, Swift Testing, Xcode build/test/debug, Simulator, App Intents, or XcodeBuildMCP work. Use before building, fixing, refactoring, QAing, or setting up Apple-platform repos, and when asked to load/install Ray's iOS skills or

    Ready to connect★ 129

    github.com/rayfernando1337/rayfernando-skills129 stars

    View details
  • check-skillSkillAI & models

    Generate and run a coder-eval activation suite for a Claude Code skill. Use when the user asks whether a skill triggers, wants to test skill activation, or worries a skill has silently stopped firing.

    Ready to connect★ 128

    github.com/uipath/coder_eval129 stars

    View details
  • svmSkillAI & models

    Explore Solana's architecture and protocol internals. Covers the SVM execution engine, account model, consensus, transactions, validator economics, data layer, development tooling, and token extensions using the Helius blog, SIMDs, and Agave/Firedancer source code.

    Ready to connect★ 128

    github.com/sendaifun/skills129 stars

    View details
  • wallet-analysisSkillAI & models

    Analyze Solana wallets and multichain portfolios with Zerion API. Use for Solana portfolio value, token positions, transaction history, wallet charts, and PnL. Prefer direct REST API integration, with hosted MCP and x402 on Solana as no-key alternatives for agent workflows.

    Ready to connect★ 128

    github.com/sendaifun/skills129 stars

    View details
  • wangjianshuo-perspectiveSkillAI & models

    Wang Jianshuo's thinking framework and expression style. Distilled from 7 in-depth research sources (approx. 1 million words of English blog posts + approx. 1.09 million Chinese characters of blog posts, 2002–2022, all first-hand) into 7 core mental models, 10 decision heuristics, and a complete bil

    Ready to connect★ 129

    github.com/jianshuo/claude-skills129 stars

    View details
  • waves-codexSkillAI & models

    WAVES - Workers, Aggregate, Verify, Extend - wave-based orchestration for Codex. Decompose a big goal into independent slices, verify coverage, spawn Codex subagents in parallel as a bounded wave, collect evidence-backed handoffs, verify important claims, synthesize one deliverable, and extend into

    Ready to connect★ 129

    github.com/rayfernando1337/rayfernando-skills129 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