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
54,221 results · page 289 of 1,808
- View details
project-documentationSkillDocs & knowledge
Lets your agent follow strict step-by-step workflows so complex multi-step tasks stay on track.
Ready to connect★ 2k
- View details
qa-testingSkillProductivity
Lets your agent break complex tasks into steps and check its own work against defined requirements.
Ready to connect★ 2k
- View details
quality-checklistSkillDev tools
Lets your agent check code against a quality checklist and get scoring and fix recommendations.
Ready to connect★ 2k
- View details
quality-hooksSkillDev tools
Lets your agent automatically lint, format, and typecheck code in Python, TypeScript, or Go and auto-fix issues.
Ready to connect★ 2k
- View details
quick-flowSkillProductivity
Lets your agent break down and manage complex multi-step tasks with enforced step-by-step workflows.
Ready to connect★ 2k
- View details
requirements-interviewSkillDev tools
Lets your agent interview you with adaptive questions to gather project requirements.
Ready to connect★ 2k
- View details
research-first-devSkillDev tools
Makes your agent research existing solutions and weigh trade-offs before writing any code.
Ready to connect★ 2k
- View details
research-orchestrationSkillAI & models
Lets your agent run several research sub-agents in parallel and combine their findings into one validated report.
Ready to connect★ 2k
- View details
retrospect-external-babysitter-runSkillMedia
Lets your agent analyze a past babysitter run in a repo and report what went well, what failed, and how to improve.
Ready to connect★ 2k
- View details
roadmap-managementSkillDev tools
Lets your agent edit a ROADMAP.md file, adding, completing, or removing phases and milestones.
Ready to connect★ 2k
- View details
security-hardeningSkillSecurity
Adds a security layer to your agent that blocks prompt injection, validates inputs, and sanitizes outputs.
Ready to connect★ 2k
- View details
security-scanningSkillSecurity
Lets your agent run security audits with static analysis checks and optional simulated attacks on your code.
Ready to connect★ 2k
- View details
self-optimizationSkillDev tools
Lets your agent learn from its own past task performance and improve its behavior over time.
Ready to connect★ 2k
- View details
session-managementSkillAI & models
Lets your agent start, hand off, and restore AI agent sessions with a persistent identity.
Ready to connect★ 2k
- View details
session-memorySkillDocs & knowledge
Lets your agent save and reload its memory notes so it keeps context after a session reset.
Ready to connect★ 2k
- View details
smart-routingSkillProductivity
Lets your agent pick the best model and route each task automatically based on how complex it is.
Ready to connect★ 2k
- View details
spec-creationSkillDev tools
Lets your agent research a codebase and write feature specs with requirements, acceptance criteria, and plans.
Ready to connect★ 2k
- View details
specification-generationSkillDev tools
Lets your agent turn written requirements into structured technical specs with architecture decisions.
Ready to connect★ 2k
- View details
sprint-planningSkillProductivity
Lets your agent break down and manage complex multi-step tasks with strict, repeatable workflows.
Ready to connect★ 2k
- View details
story-decompositionSkillDev tools
Lets your agent break technical specs into small implementable stories ordered by dependencies.
Ready to connect★ 2k
- View details
story-developmentSkillProductivity
Lets your agent manage complex multi-step tasks by following strict, checked plans instead of guessing.
Ready to connect★ 2k
- View details
streaming-progressSkillProductivity
Lets your agent break big tasks into small steps and follow them in order with checks along the way.
Ready to connect★ 2k
- View details
strict-tddSkillDev tools
Makes your agent write code test-first, always creating a failing test before any production code.
Ready to connect★ 2k
- View details
swarm-orchestrationSkillCloud & infra
Lets your agent run several agents as a coordinated team with shared plans and drift checks.
Ready to connect★ 2k
- View details
task-decompositionSkillProductivity
Lets your agent turn a technical plan into ordered development tasks with dependencies, effort estimates, and parallelization hints.
Ready to connect★ 2k
- View details
tdd-enforcementSkillDev tools
Guides your agent to write failing tests first, then minimal code to pass them, with 80% coverage checks.
Ready to connect★ 2k
- View details
template-scaffoldingSkillDocs & knowledge
Lets your agent load templates and fill in variables to generate project documents automatically.
Ready to connect★ 2k
- View details
test-automationSkillProductivity
Lets your agent follow complex multi-step task plans deterministically instead of improvising.
Ready to connect★ 2k
- View details
test-enforcementSkillMonitoring & ops
Lets your agent run automated test validation, check coverage, and report code quality metrics.
Ready to connect★ 2k
- View details
ux-designSkillMedia
Lets your agent break complex tasks into steps and manage multi-agent workflows with enforced rules.
Ready to connect★ 2k
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.
53,789 of the 54,221 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.