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

8,867 results · page 277 of 296

  • release-engineSkillAI & models

    Use when preparing a versioned Rails engine release (SemVer, changelog). Trigger words: release engine, version bump, publish gem, changelog.

    Ready to connect

    github.com/igmarin/rails-agent-skills25 stars

    View details
  • review-engineSkillAI & models

    Use when reviewing a Rails engine for isolation, API surface, and host contract. Trigger words: review engine, engine quality, engine audit.

    Ready to connect

    github.com/igmarin/rails-agent-skills25 stars

    View details
  • review-guidelinesSkillAI & models

    Additional code review guidelines specific to this codebase. Auto-loaded by the review agent during PR reviews to enforce project conventions.

    Ready to connect

    github.com/youdotcom-oss/dx-toolkit25 stars

    View details
  • review-migrationSkillAI & models

    Use when planning or reviewing a production Rails migration. Never mix schema change and backfill. Trigger words: migration, add column, index, backfill, zero-downtime.

    Ready to connect

    github.com/igmarin/rails-agent-skills25 stars

    View details
  • robot-talksSkillAI & models

    Run a multi-agent parallel investigation to identify cross-layer tensions

    Ready to connect

    github.com/cyberalchemyai/arcanum23 stars

    View details
  • skill-evolveSkillAI & models

    A meta skill that automatically improves the corresponding SKILL.md based on feedback received after skill execution. Use it when a skill is wrong or missing something, or to record newly learned pitfalls.

    Ready to connect

    github.com/leeyudok/agents-scaffold25 stars

    View details
  • skill-transcriptorSkillAI & models

    Use when: converting a complete, coherent skill, prompt, command, or workflow into an Arcanum-compliant sigil package.

    Ready to connect

    github.com/cyberalchemyai/arcanum23 stars

    View details
  • snippetsSkillAI & models

    Create and manage prompt snippets — reusable text blocks referenced inside config variation prompts. Keeps common instructions, personas, and guardrails consistent across multiple configs.

    Ready to connect

    github.com/launchdarkly/ai-tooling25 stars

    View details
  • subagent-strategySkillAI & models

    Use when deciding whether work merits a governed multi-agent dispatch and, when it does, proposing, tension-checking, confirming, registering, running, closing, and observing that dispatch through repository-local bindings.

    Ready to connect

    github.com/cyberalchemyai/arcanum23 stars

    View details
  • sync-ceSkillAI & models

    Check for compound-engineering plugin updates and sync skills/agents into the project

    Ready to connect

    github.com/jesusfilm/core25 stars

    View details
  • tandem-agentic-engineeringSkillAI & models

    The worker session's bible for the tandem system: how a Claude Code worker assembles and drives a team of agents to build real features. Trigger on any real development, debugging, or feature work — build, create, implement, fix, add, develop, code, debug, ship, refactor — or when agents, a plan, a

    Ready to connect

    github.com/maxmedawar/tandem25 stars

    View details
  • tandem-engineering-workflowSkillAI & models

    Engineering discipline for development work orchestrated through Tandem, regardless of whether the worker is Claude, Codex, or another supported engine. Trigger for implementation, debugging, review, test, or architecture work. Begin the first response with 📋📋📋📋📋 when active.

    Ready to connect

    github.com/maxmedawar/tandem25 stars

    View details
  • tandem-orchestrationSkillAI & models

    Operate Tandem as a multi-agent, multi-device MCP orchestrator. Use it when an MCP-capable caller needs to start, inspect, steer, interrupt, or coordinate Claude, Codex, shell, or Hermes sessions on the local hub or another enrolled device. Also covers the optional Claude-only relay. Begin the first

    Ready to connect

    github.com/maxmedawar/tandem25 stars

    View details
  • test-derivationSkillAI & models

    Deterministically derive a test-obligation spec from a DomainSpec feature's aspect docs (no LLM in the derivation path).

    Ready to connect

    github.com/cyberalchemyai/arcanum23 stars

    View details
  • test-engineSkillAI & models

    Use when setting up or reviewing dummy-app and engine specs. Trigger words: test engine, dummy app, engine specs.

    Ready to connect

    github.com/igmarin/rails-agent-skills25 stars

    View details
  • test-serviceSkillAI & models

    Use when writing RSpec for a service object under spec/services/. Test the public .call contract. Trigger words: service spec, test service object, spec/services.

    Ready to connect

    github.com/igmarin/rails-agent-skills25 stars

    View details
  • ui-prototyping-studioSkillAI & models

    Operate the ui-prototyping-studio as Claude Code — generate UI variants and drive the explore/annotate/mutate loop through the studio CLI. Every change is reversible; the human owns the one irreversible edge (export). Use when a human asks to explore, annotate, or revise UI prototypes in this projec

    Ready to connect

    github.com/cyberalchemyai/arcanum23 stars

    View details
  • upgrade-engineSkillAI & models

    Use when checking a Rails engine across Rails versions (Zeitwerk, compatibility). Trigger words: Zeitwerk, Rails upgrade, cross-version, engine compatibility.

    Ready to connect

    github.com/igmarin/rails-agent-skills25 stars

    View details
  • version-apiSkillAI & models

    Use when versioning a Rails REST API (v1/v2, deprecation, Sunset headers). Never break a public version in place. Trigger words: API version, v1, v2, versioning, deprecation.

    Ready to connect

    github.com/igmarin/rails-agent-skills25 stars

    View details
  • zh-CNSkillAI & models

    A decision protocol for AI agents — critical thinking, evidence verification, and structured review. Less confident advice, more testable decisions.

    Ready to connect

    github.com/kimyx0207/kim_decision25 stars

    View details
  • add-agent-targetSkillAI & models

    Use when adding support for a new AI agent target to agentsmesh. Covers official format research, canonical mapping, importer/generator/linter work, realistic fixtures, unit/integration/e2e coverage, matrix/docs updates, and final verification. Includes both project and global mode from day one.

    Ready to connect

    github.com/samplexbro/agentsmesh24 stars

    View details
  • agentic-repo-discoverySkillAI & models

    Use when an existing repository contains agents, prompts, workflows, playbooks, commands, or Skills and you need to identify which capabilities are worth converting into a ChatGPT/Codex Plugin.

    Ready to connect

    github.com/immamdouhaboammar/chatgpt-codex-plugin-autopilot24 stars

    View details
  • ai-infrastructure-ollamaSkillAI & models

    Local LLM inference with the Ollama JavaScript client -- chat, streaming, tool calling, vision, embeddings, structured output, model management, and OpenAI-compatible endpoint

    Ready to connect

    github.com/agents-inc/skills24 stars

    View details
  • ai-orchestration-llamaindexSkillAI & models

    LlamaIndex.TS data framework for RAG, indexing, retrieval, query engines, chat engines, and agentic workflows in TypeScript

    Ready to connect

    github.com/agents-inc/skills24 stars

    View details
  • ai-patterns-tool-use-patternsSkillAI & models

    Provider-agnostic patterns for LLM function calling, tool loops, and agentic workflows

    Ready to connect

    github.com/agents-inc/skills24 stars

    View details
  • ai-provider-cohere-sdkSkillAI & models

    Official Cohere TypeScript SDK patterns -- CohereClientV2, chat, embeddings, rerank, RAG with citations, tool use, streaming, and model selection

    Ready to connect

    github.com/agents-inc/skills24 stars

    View details
  • ai-provider-mistral-sdkSkillAI & models

    Official Mistral AI TypeScript SDK patterns — client setup, chat completions, streaming, function calling, structured outputs, embeddings, vision, Codestral FIM, and production best practices

    Ready to connect

    github.com/agents-inc/skills24 stars

    View details
  • am-agent-code-debuggerSkillAI & models

    Systematically identify, diagnose, and resolve bugs using advanced debugging techniques. Specializes in root cause analysis and complex issue resolution. Use PROACTIVELY for troubleshooting and bug investigation.

    Ready to connect

    github.com/samplexbro/agentsmesh24 stars

    View details
  • am-agent-code-refactorSkillAI & models

    Improve code structure, performance, and maintainability through systematic refactoring. Specializes in legacy modernization and technical debt reduction. Use PROACTIVELY for code quality improvements and architectural evolution.

    Ready to connect

    github.com/samplexbro/agentsmesh24 stars

    View details
  • am-agent-code-reviewerSkillAI & models

    Code review specialist that analyzes diffs and suggests improvements

    Ready to connect

    github.com/samplexbro/agentsmesh24 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.

53,583 of the 54,015 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