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
55,055 results · page 682 of 1,836
- View details
Voice GenerateSkillAI & models
Lets your agent generate text that matches your personal writing style.
★ 335
- View details
Voice LearnSkillAI & models
Lets your agent learn your writing style by analyzing text you've manually edited.
★ 335
- View details
Voice ReviewSkillAI & models
Lets your agent check existing text against a defined voice profile.
★ 335
- View details
vow-enforcementSkillAI & models
Helps your agent design and audit rule enforcement by classifying project constraints into soft, hard, and validator layers.
Ready to connect★ 335
- View details
War RoomSkillAI & models
Lets your agent convene multiple AI models as an expert panel to critique and stress-test a decision.
★ 335
- View details
war-roomSkillAI & models
Lets your agent gather multiple AI models to debate and stress-test risky, hard-to-reverse decisions.
Ready to connect★ 335
- View details
war-room-checkpointSkillAI & models
Lets your agent score how hard a decision is to reverse and decide if it needs deeper deliberation at key workflow checkpoints.
Ready to connect★ 335
- View details
workflow-diagramSkillAI & models
Lets your agent draw a workflow diagram showing process steps, decisions, and state changes.
Ready to connect★ 335
- View details
workflow-monitorSkillFiles & storage
Lets your agent spot repeated workflow failures and inefficiencies and file GitHub issues about them.
Ready to connect★ 335
- View details
workflow-setupSkillCloud & infra
Lets your agent create GitHub Actions workflow files that run tests, linting, and deployment for Python, Rust, or TypeScript projects.
Ready to connect★ 335
- View details
writing-rulesSkillDocs & knowledge
Lets your agent write markdown rules that block dangerous commands or warn about risky file edits.
Ready to connect★ 335
- View details
dr-jskillSkillDatabases & data
Lets your agent generate Java Spring Boot projects with web frontends, PostgreSQL, REST APIs, and Docker setup.
Ready to connect★ 333
- View details
agent-business-canvasSkillAI & models
Helps your agent evaluate, design, and stress-test the business model of an AI agent product.
Ready to connect★ 332
- View details
architecture-decisionSkillAI & models
Lets your agent write architecture decision records documenting technical choices, alternatives, and consequences.
Ready to connect★ 332
- View details
asset-auditSkillAI & models
Lets your AI agent run a multi-agent workflow for indie game development with 48 specialized agents.
Ready to connect★ 332
- View details
balance-checkSkillAI & models
Lets your agent help manage indie game development tasks using a collaborative studio workflow.
Ready to connect★ 332
- View details
content-creator-launchpadSkillMedia
Guides your agent through launching a content brand, like a YouTube channel, podcast, newsletter, or blog.
Ready to connect★ 332
- View details
dotfile-auditSkillFiles & storage
Lets your agent review, fix, and validate pipeline DOT files and check they cover a full spec.
Ready to connect★ 332
- View details
dotfile-brainstormSkillWeb & browsing
Lets your agent turn a vague project idea into a design doc structured for a build pipeline.
Ready to connect★ 332
- View details
dotfile-from-specSkillWeb & browsing
Lets your agent turn a spec or plan into a Graphviz DOT file outlining the build pipeline phases.
Ready to connect★ 332
- View details
dotfile-honeSkillFiles & storage
Lets your agent deeply check a pipeline DOT file for flow issues and gaps against its original spec.
Ready to connect★ 332
- View details
estimateSkillProductivity
Lets your agent estimate how long a task will take using complexity, dependencies, and past team velocity.
Ready to connect★ 332
- View details
fleet-managerSkillAI & models
Lets your agent check the status of your AI agents and report what needs attention.
Ready to connect★ 332
- View details
genshijinSkillDev tools
Lets your agent reply in ultra-short caveman-style speech to cut token usage by about 75% while staying technically accurate.
Ready to connect★ 332
- View details
genshijin-commitSkillCommunication
Lets your agent write short, conventional commit messages in English or Japanese.
Ready to connect★ 332
- View details
genshijin-compressSkillFiles & storage
Lets your agent shrink memory files like CLAUDE.md into a compact form to save tokens, keeping a readable backup.
Ready to connect★ 332
- View details
genshijin-crewSkillFiles & storage
Guides your agent on when to delegate coding tasks to specialized caveman-style subagents for searching, editing, and reviewing code.
Ready to connect★ 332
- View details
genshijin-helpSkillDev tools
Shows a quick reference of all genshijin modes, skills, and commands.
Ready to connect★ 332
- View details
genshijin-reviewSkillDev tools
Lets your agent write terse, one-line pull request review comments in Japanese or English.
Ready to connect★ 332
- View details
genshijin-statsSkillMonitoring & ops
Shows your current session's real token usage and estimated cost savings from Claude Code session logs.
Ready to connect★ 332
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.