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
54,017 results · page 249 of 1,801
- View details
fdrSkillDocs & knowledge
Lets your agent write and update structured docs that record what each feature does and why design choices were made.
Ready to connect★ 3k
- View details
glossarySkillDev tools
Lets your agent look up, add, or check project terms in a shared glossary file.
Ready to connect★ 3k
- View details
loom-architectureSkillMonitoring & ops
Lets your agent follow the Loom event-sourcing architecture when building or reviewing NATS and JetStream applications.
Ready to connect★ 3k
- View details
session-wrap-upSkillAI & models
Lets your agent run a retrospective on a finished coding session to surface mistakes and suggest improvements.
Ready to connect★ 3k
- View details
svelte-code-writerSkillDev tools
Lets your agent check Svelte components and modules for errors using the Svelte CLI.
Ready to connect★ 3k
- View details
svelte-core-bestpracticesSkillDev tools
Gives your agent best-practice guidance for writing and reviewing Svelte components, from reactivity to styling.
Ready to connect★ 3k
- View details
svelte-docsSkillDocs & knowledge
Lets your agent look up official Svelte, SvelteKit, and Svelte CLI documentation.
Ready to connect★ 3k
- View details
update-project-dependenciesSkillDev tools
Lets your agent update project dependencies to newer compatible versions and run the tests.
Ready to connect★ 3k
- View details
browserSkillWeb & browsing
Lets your agent control Chrome to open pages, run JavaScript, take screenshots, and pick page elements.
Ready to connect★ 3k
- View details
codeagentSkillFiles & storage
Lets your agent run coding tasks through AI tools like Codex or Claude with file references and parallel execution.
Ready to connect★ 3k
- View details
harnessSkillProductivity
Lets your agent run long multi-step tasks with progress saving, pause/resume, and recovery from failures.
Ready to connect★ 3k
- View details
omoSkillProductivity
Lets your agent coordinate multiple helper agents to analyze code, investigate bugs, and plan or apply fixes.
Ready to connect★ 3k
- View details
product-requirementsSkillAI & models
Lets your agent gather project requirements through questions and write a product requirements document.
Ready to connect★ 3k
- View details
prototype-prompt-generatorSkillDocs & knowledge
Lets your agent write detailed, structured prompts for building UI and UX prototypes of web or mobile apps.
Ready to connect★ 3k
- View details
skill-installSkillSecurity
Lets your agent install new skills from GitHub repositories after running a security scan on them.
Ready to connect★ 3k
- View details
sparvSkillAI & models
Lets your agent plan and build tasks through a structured specify, plan, act, review workflow with built-in risk checks.
Ready to connect★ 3k
- View details
test-casesSkillDocs & knowledge
Lets your agent write detailed test cases from PRD documents or user requirements.
Ready to connect★ 3k
- View details
batuta-routingSkillDev tools
Lets your agent pick the cheapest capable AI model for each task based on its complexity.
Ready to connect★ 3k
- View details
combinedSkillDev tools
Lets your agent run Git commands in a repo and run a cleanup command after each session ends.
Ready to connect★ 3k
- View details
compozySkillDocs & knowledge
Lets your agent operate CompozyOS, managing its sessions, agents, tasks, memory, automation, and configuration.
Ready to connect★ 3k
- View details
cy-create-specSkillProductivity
Lets your agent create or update a CompozyOS spec with its companion contracts, reusing existing decisions and research.
Ready to connect★ 3k
- View details
cy-create-tasksSkillProductivity
Lets your agent create or refine task graphs from an existing Compozy spec, with outcomes, dependencies, and test ownership.
Ready to connect★ 3k
- View details
cy-execute-taskSkillProductivity
Lets your agent implement a CompozyOS spec task, verify it works, and update its tracking status.
Ready to connect★ 3k
- 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 run a delivery loop that takes tasks through checkpoints, 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-review-roundSkillFiles & storage
Lets your agent review code changes against a spec and save the issues as files for later fixing.
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.
53,585 of the 54,017 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.