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.
Filter by category
55,196 results · page 87 of 1,840
- View details
potion-yjs-dev-browser-testSkillWeb & browsing
Lets your agent test suspicious Slate Yjs collaboration behavior by comparing it against Potion in a dev browser.
Ready to connect★ 17k
- View details
product-lens-reviewerSkillDocs & knowledge
Lets your agent critique planning documents like a senior product leader, checking goals against proposed work.
Ready to connect★ 17k
- View details
project-standards-reviewerSkillAI & models
Lets your agent review code changes against your project's own written standards and conventions.
Ready to connect★ 17k
- View details
promote-betaSkillDev tools
Lets your agent promote builds to the beta release lane.
Ready to connect★ 17k
- View details
reactSkillDev tools
Gives your agent up-to-date React coding patterns for props, Effects, and Tailwind v4 syntax.
Ready to connect★ 17k
- View details
react-useeffectSkillDev tools
Gives your agent best-practice guidance for writing and reviewing React useEffect code.
Ready to connect★ 17k
- View details
registry-changelogSkillDev tools
Lets your agent write and check changelog entries for registry and UI changes.
Ready to connect★ 17k
- View details
release-lanesSkillDev tools
Lets your agent manage release lanes by promoting, syncing, and verifying npm and GitHub releases.
Ready to connect★ 17k
- View details
repo-research-analystSkillDocs & knowledge
Lets your agent research a codebase's structure, docs, and conventions to help you understand a new repository.
Ready to connect★ 17k
- View details
reproduce-bugSkillDev tools
Systematically reproduce and investigate a bug from a GitHub issue. Use when the user provides a GitHub issue number or URL for a bug they want reproduced or investigated.
Ready to connect★ 17k
- View details
resolve-pr-feedbackSkillDev tools
Lets your agent resolve GitHub pull request review comments by triaging feedback, applying fixes, and replying in threads.
Ready to connect★ 17k
- View details
resolve-slate-issueSkillProductivity
Lets your agent work a GitHub issue end to end and post a verified resolution comment using gh.
Ready to connect★ 17k
- View details
review-sweepSkillDev tools
Lets your agent group code review comments into broader fixes across the whole diff instead of one line at a time.
Ready to connect★ 17k
- View details
scope-guardian-reviewerSkillDocs & knowledge
Reviews your planning documents for scope creep and unnecessary complexity.
Ready to connect★ 17k
- View details
shadcn-paritySkillDev tools
Lets your agent copy shadcn's code patterns and architecture into its own implementations with matching source code.
Ready to connect★ 17k
- View details
slate-arSkillDev tools
Lets your agent run Slate v2 research loops by delegating packet, dashboard, and finalization steps to Codex Autoresearch.
Ready to connect★ 17k
- View details
slate-ar-fastSkillDev tools
Lets your agent speed up slow code by picking a performance target and optimizing it with automatic regression checks.
Ready to connect★ 17k
- View details
slate-ar-finalizeSkillDev tools
Lets your agent run a preview-only finalization step for Slate v2 Autoresearch with clear approval gates.
Ready to connect★ 17k
- View details
slate-ar-gateSkillWeb & browsing
Lets your agent rerun and log existing test, typecheck, and browser checks in a loop without writing new tests.
Ready to connect★ 17k
- View details
slate-ar-nextSkillDev tools
Lets your agent read your Slate v2 project state and automatically run one safe next research step.
Ready to connect★ 17k
- View details
slate-ar-perfSkillDev tools
Lets your agent run research loops with safe stopping rules and performance checks like pagination defaults.
Ready to connect★ 17k
- View details
slate-ar-perfectSkillDev tools
Lets your agent automatically improve a chosen surface for quality, bugs, behavior proof, and performance.
Ready to connect★ 17k
- View details
slate-ar-qualitySkillDev tools
Lets your agent run automated research to find quality gaps in APIs, docs, architecture, and tests.
Ready to connect★ 17k
- View details
slate-ar-recipeSkillDocs & knowledge
Lets your agent pick and set up Slate Autoresearch recipes for tasks like test runtime, typechecks, and bundle size.
Ready to connect★ 17k
- View details
slate-ar-shipSkillDev tools
Lets your agent run a ship-readiness check and commit your work after you approve.
Ready to connect★ 17k
- View details
slate-ar-stabilizeSkillDev tools
Lets your agent re-run editor behavior tests repeatedly and route failures to a patcher until things stop breaking.
Ready to connect★ 17k
- View details
slate-ar-statusSkillFiles & storage
Lets your agent check the current status of a Slate v2 Autoresearch session, including state, blockers, and next steps.
Ready to connect★ 17k
- View details
slate-patchSkillDev tools
Lets your agent fix bugs in Slate v2 by writing tests, reproducing issues, and reviewing its own patches.
Ready to connect★ 17k
- View details
slate-planSkillDev tools
Lets your agent review Slate v2 architecture plans and produce a scored report with completion gates.
Ready to connect★ 17k
- View details
spec-flow-analyzerSkillDev tools
Analyzes specifications and feature descriptions for user flow completeness and gap identification. Use when a spec, plan, or feature description needs flow analysis, edge case discovery, or requirements validation.
Ready to connect★ 17k
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.