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
54,680 results · page 609 of 1,823
- View details
- View details
business-opsSkillCommerce & finance
Lets your agent advise on business operations like finance, sales, HR, and strategy.
Ready to connect★ 419
- View details
cli-designSkillMedia
Helps your agent design a command-line tool's arguments, flags, help text, output, errors, and exit codes.
Ready to connect★ 419
- View details
code-cleanupSkillProductivity
Lets your agent find stale TODOs, unused imports, and dead code in your codebase.
Ready to connect★ 419
- View details
code-lintingSkillAI & models
Lets your agent check Python and JavaScript code for style and error issues.
Ready to connect★ 419
- View details
codebase-analyzerSkillAI & models
Lets your agent find statistical patterns and rules in a Go codebase.
Ready to connect★ 419
- View details
codebase-overviewSkillAI & models
Lets your agent explore a codebase and map out its structure and architecture.
Ready to connect★ 419
- View details
comment-qualitySkillAI & models
Lets your agent find and fix outdated time references in code comments.
Ready to connect★ 419
- View details
condenseSkillAI & models
Lets your agent rewrite text to be shorter while keeping every instruction intact.
Ready to connect★ 419
- View details
condition-based-waitingSkillAI & models
Lets your agent wait for things to be ready by polling and retrying with backoff.
Ready to connect★ 419
- View details
create-voiceSkillAI & models
Lets your agent create voice profiles that match a writing style from sample texts.
Ready to connect★ 419
- View details
cron-automationSkillAI & models
Lets your agent review existing cron jobs and create new scheduled tasks.
Ready to connect★ 419
- View details
cve-source-checkSkillSecurity
Lets your agent check whether the right vulnerability feeds cover each part of your software stack and flag gaps.
Ready to connect★ 419
- View details
dSkillAI & models
Routes your agent's incoming requests by classifying them and dispatching to the matching agent, skill, or pipeline.
Ready to connect★ 419
- View details
decision-helperSkillAI & models
Lets your agent score and compare architectural options using weighted criteria to help pick a design.
Ready to connect★ 419
- View details
dev-branch-deploySkillCloud & infra
Lets your agent run dev-branch deploys of the Hermes or Maia stacks to a lab for testing before merging.
Ready to connect★ 419
- View details
distinctive-frontend-designSkillMedia
Lets your agent explore distinctive visual designs and check them against a list of overused patterns.
Ready to connect★ 419
- View details
docs-sync-checkerSkillFiles & storage
Lets your agent compare your documentation with the actual files to find where the docs are out of date.
Ready to connect★ 419
- View details
endpoint-validatorSkillAI & models
Lets your agent check that API endpoints work and report a pass or fail result.
Ready to connect★ 419
- View details
explanation-tracesSkillAI & models
Lets your agent show a step-by-step record of why it picked certain actions, agents, or skills during a task.
Ready to connect★ 419
- View details
feature-lifecycleSkillMedia
Lets your agent manage a feature through design, planning, implementation, validation, and release phases.
Ready to connect★ 419
- View details
forensicsSkillAI & models
Lets your agent analyze failed workflows to find what went wrong.
Ready to connect★ 419
- View details
full-repo-reviewSkillFiles & storage
Lets your agent review every source file in a repo and produce a prioritized list of issues.
Ready to connect★ 419
- View details
game-designSkillMedia
Lets your agent review a game design repo, make design decisions, and validate changes against the codebase.
Ready to connect★ 419
- View details
game-sprite-pipelineSkillMedia
Lets your agent generate game character sprites, including animated sheets and video-to-sprite conversions.
Ready to connect★ 419
- View details
generate-claudemdSkillAI & models
Lets your agent create a project-specific CLAUDE.md file by analyzing the repository.
Ready to connect★ 419
- View details
github-notification-triageSkillCommunication
Lets your agent sort through GitHub notifications and issue/PR queues to surface what needs attention.
Ready to connect★ 419
- View details
gm-brilliant-implementationSkillAI & models
Runs an end-to-end workflow that turns gathered evidence into a live implementation plan for large multi-system GM programs.
Ready to connect★ 419
- View details
go-patternsSkillAI & models
Lets your agent follow common Go coding patterns for testing, concurrency, error handling, and code review.
Ready to connect★ 419
- View details
headless-cron-creatorSkillWeb & browsing
Lets your agent schedule recurring background jobs for Claude Code with safety checks.
Ready to connect★ 419
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.
54,249 of the 54,680 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.