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

8,992 results · page 200 of 300

  • naming-refactorSkillAI & models

    Refactor naming and repository structure exhaustively while preserving behavior and external contracts.

    Ready to connect★ 71

    github.com/paulrberg/agent-skills73 stars

    View details
  • node-deps-bumperSkillAI & models

    Use for dependency updates: bump npm/pnpm/yarn/bun packages, check outdated, or run taze.

    Ready to connect★ 71

    github.com/paulrberg/agent-skills73 stars

    View details
  • prepare-package-for-claudeSkillAI & models

    Prepare a Datagrok package so that Claude (or any coding agent) can work on it effectively from a naive prompt

    Ready to connect★ 73

    github.com/datagrok-ai/public72 stars

    View details
  • product-marketingSkillAI & models

    Belastbaren Produktmarketing-Kontext für Positionierung, Zielgruppen, Botschaften, Einwände und Nachweise erstellen, prüfen und aktualisieren. Nutze diesen Skill, wenn die gemeinsame Grundlage fehlt, auf die sich Texte, Content, Vergleiche und Kampagnen stützen sollen: ICP, Jobs-to-be-Done, Nutzenve

    Ready to connect★ 73

    github.com/login-tb/claude-skills73 stars

    View details
  • recruit-initSkillAI & models

    Initialize the recruiting workspace: check prerequisites (boss-cli / liepin-cli / lark-cli), create the standard directory skeleton (CONTEXT.md source of truth + AGENTS.md collaboration conventions + the 01-jd to 05-onboarding funnel directories + a ledger), copy the workflow docs into the workspace

    Ready to connect★ 73

    github.com/viy1204/recruiting-copilot73 stars

    View details
  • release-bumperSkillAI & models

    Cut a release: bump versions, write changelogs, commit, tag.

    Ready to connect★ 71

    github.com/paulrberg/agent-skills73 stars

    View details
  • repo-harmonizationSkillAI & models

    Audit multiple interdependent repositories for alignment, then plan and apply surgical fixes for drift and duplication.

    Ready to connect★ 71

    github.com/paulrberg/agent-skills73 stars

    View details
  • repo-renameSkillAI & models

    "Preview or rename a GitHub upstream repo and matching local project folder, update origin, and preserve Codex CLI and Claude Code continuity references."

    Ready to connect★ 71

    github.com/paulrberg/agent-skills73 stars

    View details
  • skill-harmonizationSkillAI & models

    Harmonize a repository's skill portfolio across catalog and user-installed skills.

    Ready to connect★ 71

    github.com/paulrberg/agent-skills73 stars

    View details
  • skill-mapSkillAI & models

    "Use to find agent skill installs, repository skill portfolios, duplicate skills, cross-dependencies, invocations, and cross-references across the local machine."

    Ready to connect★ 71

    github.com/paulrberg/agent-skills73 stars

    View details
  • skill-writingSkillAI & models

    Create/scaffold/init a project-local agent skill under `.agents/skills` in an ordinary repository; defer to repository instructions that define a source catalog and lifecycle.

    Ready to connect★ 71

    github.com/paulrberg/agent-skills73 stars

    View details
  • stale-comments-auditSkillAI & models

    Audit and fix JavaScript, TypeScript, and Go comments that are verified as stale, orphaned, misleading, or redundant.

    Ready to connect★ 71

    github.com/paulrberg/agent-skills73 stars

    View details
  • tailwind-cssSkillAI & models

    "Use for Tailwind v4 styling: add/fix classes, configure or migrate Tailwind, use tailwind-variants, or tw-animate-css."

    Ready to connect★ 71

    github.com/paulrberg/agent-skills73 stars

    View details
  • vitestSkillAI & models

    "Use for Vitest in TypeScript projects (Node, bun, React/Next.js, Effect): write, run, or debug unit/component tests, mocks, testing utilities, and coverage."

    Ready to connect★ 71

    github.com/paulrberg/agent-skills73 stars

    View details
  • add-stack-contextSkillAI & models

    Audit and establish current agent context for the technologies that define a project's stack. Use when setting up a project for agent work, after selecting or adding a framework, library, developer tool, or hosted service, or when entering an existing project whose agent context has not been audited

    Ready to connect★ 72

    github.com/toy-crane/claude-code-playbook-template60 stars

    View details
  • agent-styleSkillAI & models

    Provides the vendored agent-style v0.3.5 prose rule pack as a portable Claude skill. Use when installing, syncing, applying, or auditing SDD Agent-Style support in another project, or when a style-review workflow needs the bundled rules.

    Ready to connect★ 72

    github.com/tranhieutt/software_development_department72 stars

    View details
  • android-compose-patternsSkillAI & models

    Compose UI, ViewModels, navigation, state, and app-module theming.

    Ready to connect★ 72

    github.com/po4yka/ripdpi68 stars

    View details
  • build-prototypeSkillAI & models

    Build a self-contained dummy-data HTML prototype covering every screen and relevant state of a web, mobile-web, or native-app surface. Use when the user wants to review and settle a complete screen-based product or feature before implementation, especially when prose or isolated variants cannot reso

    Ready to connect★ 72

    github.com/toy-crane/claude-code-playbook-template60 stars

    View details
  • decision-recordsSkillAI & models

    Creates, supersedes and validates decision records (ADRs) against the convention a collection already follows, instead of imposing a published one. Use when the user wants to record a decision, write an ADR, supersede an existing decision, audit or lint a decisions folder, check that an ADR index is

    Ready to connect★ 72

    github.com/fvadicamo/dev-agent-skills72 stars

    View details
  • define-pieceSkillAI & models

    Turn one topic and a rough direction into a confirmed brief for a single piece of writing, such as a blog post, newsletter issue, or page of copy, at docs/briefs/<slug>/brief.md. Use when the user wants to settle a piece's thesis, reader, scope, outline, or reader questions before any prose is writt

    Ready to connect★ 72

    github.com/toy-crane/claude-code-playbook-template60 stars

    View details
  • define-productSkillAI & models

    Interview the user to define or revise the app's overall product direction, then preserve the confirmed meaning in root PRODUCT.md. Always use for a new app direction or any app-wide change to users, usage situations, problem, promised change, core loop, durable boundaries, experience principles, su

    Ready to connect★ 72

    github.com/toy-crane/claude-code-playbook-template60 stars

    View details
  • define-publicationSkillAI & models

    Interview the user to define or revise the standing premise of one writing medium, such as a product blog, newsletter, or brand site, then preserve it in docs/publications/<slug>.md. Always use for a new publication or any change to its readers, promised change, voice, coverage, medium conventions,

    Ready to connect★ 72

    github.com/toy-crane/claude-code-playbook-template60 stars

    View details
  • draft-pieceSkillAI & models

    Draft or resume a piece from a selected docs/briefs/SLUG/ folder, or apply user corrections to an existing article. Verify reader understanding, embedded code, and confirmed writing criteria; preserve reusable feedback and preview locally when supported. Do not use to change the brief, define a publ

    Ready to connect★ 72

    github.com/toy-crane/claude-code-playbook-template60 stars

    View details
  • git-commitSkillAI & models

    Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.

    Ready to connect★ 72

    github.com/fvadicamo/dev-agent-skills72 stars

    View details
  • github-pr-mergeSkillAI & models

    Merges GitHub Pull Requests after validating pre-merge checklist. Use when user wants to merge PR, close PR, finalize PR, complete merge, approve and merge, or execute merge. Runs pre-merge validation (tests, lint, CI, comments), confirms with user, merges with proper format, handles post-merge clea

    Ready to connect★ 72

    github.com/fvadicamo/dev-agent-skills72 stars

    View details
  • github-pr-reviewSkillAI & models

    Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess rev

    Ready to connect★ 72

    github.com/fvadicamo/dev-agent-skills72 stars

    View details
  • human-reviewSkillAI & models

    Turn a completed repository change into a minimal visual handoff for human judgment. Use when the user explicitly asks to inspect the actual outcome of substantial or consequential AI-authored repository work and decide how to handle unresolved product commitments or material consequences, including

    Ready to connect★ 72

    github.com/toy-crane/claude-code-playbook-template60 stars

    View details
  • maintain-project-contextSkillAI & models

    Clean, compact, and reconcile durable project context without changing established meaning. Always use this skill whenever a request cleans, audits, or checks consistency across two or more durable context sources, even when they are called product docs, glossary, decisions, specs, or agent instruct

    Ready to connect★ 72

    github.com/toy-crane/claude-code-playbook-template60 stars

    View details
  • mergeSkillAI & models

    Carry the current repository change through a verified GitHub pull request merge into the requested base, or the repository's remote default branch when none is named, then clean up only the merged worktree and its owned development processes. Always use this skill for an actual PR merge or its post

    Ready to connect★ 72

    github.com/toy-crane/claude-code-playbook-template60 stars

    View details
  • merge-executorSkillAI & models

    Execute delta merges by generating MERGE_PROMPT.md from change proposals. Use when an approved change proposal needs to be applied to the codebase.

    Ready to connect★ 72

    github.com/miniidealab/openlogos71 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.

54,624 of the 55,055 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