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
55,435 results · page 258 of 1,848
- View details
cy-final-verifySkillProductivity
Lets your agent check whether a completed task or delivery actually meets its stated requirements using available evidence.
Ready to connect★ 3k
- View details
cy-fix-reviewsSkillFiles & storage
Lets your agent resolve code review issues by updating review files, applying fixes, and verifying the results.
Ready to connect★ 3k
- View details
cy-issue-to-specSkillProductivity
Lets your agent publish a spec document to a specs repo and create matching GitHub and Linear issues for it.
Ready to connect★ 3k
- View details
cy-loop-tasksSkillProductivity
Lets your agent loop Claude skill deliveries through task checkpoints, scoped QA, review, and PR CI.
Ready to connect★ 3k
- View details
cy-orchestrate-tasksSkillFiles & storage
Lets your agent run a spec's tasks by spawning a worker session per task and tracking completion via task files on disk.
Ready to connect★ 3k
- View details
cy-orquestrate-issueSkillDev tools
Lets your agent investigate GitHub bugs and manage fix pull requests end to end.
Ready to connect★ 3k
- View details
cy-release-videoSkillMedia
Lets your agent create or revise CompozyOS release videos by capturing product screens and assembling them with Ultramock and Remotion.
Ready to connect★ 3k
- View details
cy-review-roundSkillFiles & storage
Lets your agent run a review Claude skill that audits code changes and writes issue files for fixes.
Ready to connect★ 3k
- View details
cy-spec-peer-reviewSkillDev tools
Lets your agent request an external peer review of an approved Compozy spec and track follow-ups in the same session.
Ready to connect★ 3k
- View details
cy-spec-preflightSkillProductivity
Lets your agent check a Compozy spec or task artifact for problems during authoring or when contracts change.
Ready to connect★ 3k
- View details
cy-tasks-tail-qa-pairSkillProductivity
Lets your agent add or fix the final QA planning/execution pair in a cy-loop-tasks graph.
Ready to connect★ 3k
- View details
cy-web-docs-impactSkillProductivity
Lets your agent check whether a backend task or spec covers impacts on web, site, agent interfaces, config, and extensibility.
Ready to connect★ 3k
- View details
cy-workflow-memorySkillFiles & storage
Lets your agent save and update task memory files so workflows remember context between runs.
Ready to connect★ 3k
- View details
eng-cleanup-failure-pathsSkillDev tools
Reviews changed Go functions to check they properly clean up resources when errors occur mid-way.
Ready to connect★ 3k
- View details
eng-code-guidelinesSkillFiles & storage
Guides your agent to follow Go coding rules when writing or editing non-test Go files in cmd or internal directories.
Ready to connect★ 3k
- View details
eng-consolidate-test-suitesSkillDev tools
Guides your agent to consolidate and audit Compozy tests by finding invariants, owning layers, and canonical suites.
Ready to connect★ 3k
- View details
eng-contract-codegen-coshipSkillDev tools
Guides your agent through safely updating public API contracts like DTOs, OpenAPI specs, and generated clients.
Ready to connect★ 3k
- View details
eng-data-boundariesSkillDev tools
Lets your agent audit how data boundaries are enforced in route loaders, query caches, and paginated data paths.
Ready to connect★ 3k
- View details
eng-designSkillMedia
Guides your agent to create and review UI designs with consistent typography, spacing, icons, and motion.
Ready to connect★ 3k
- View details
eng-qa-bootstrapSkillWeb & browsing
Lets your agent set up isolated QA environments and generate the manifest needed for downstream testing.
Ready to connect★ 3k
- View details
eng-real-scenario-qaSkillDev tools
Runs an autonomous end-to-end QA scenario with live providers and strict evidence checks for release testing.
Ready to connect★ 3k
- View details
eng-schema-migrationSkillDatabases & data
Lets your agent safely change SQLite database tables, columns, and indexes using step-by-step migration files.
Ready to connect★ 3k
- View details
eng-test-conventionsSkillDev tools
Lets your agent follow your team's Go test conventions when writing or editing Go test files.
Ready to connect★ 3k
- View details
eng-ui-screenshotSkillSecurity
Lets your agent capture screenshots of local web pages or Storybook components to check designs and spot visual changes.
Ready to connect★ 3k
- View details
eng-worktree-isolationSkillAI & models
Isolates the agent's runtime state so multiple worktrees or QA runs can run on one machine without conflicting.
Ready to connect★ 3k
- View details
fumadocsSkillSearch
Helps your agent set up and fix Fumadocs sites, covering MDX pages, navigation, search, layouts, and translations.
Ready to connect★ 3k
- View details
lesson-learnedSkillMonitoring & ops
Lets your agent write evidence-backed lessons from recent changes or incidents and update or retire workflow rules.
Ready to connect★ 3k
- View details
open-designSkillDocs & knowledge
Lets your agent create or refine interfaces, sites, HTML slides, and visual documents using the open design skill.
Ready to connect★ 3k
- View details
open-design-browserSkillWeb & browsing
Lets your agent open and test local HTML designs with screenshots and keyboard checks.
Ready to connect★ 3k
- View details
open-design-reviewSkillMedia
Lets your agent run an independent review-and-refine loop on OpenDesign HTML as an open claude skill.
Ready to connect★ 3k
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.
55,004 of the 55,435 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.