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
55,196 results · page 19 of 1,840
- View details
frontend-ui-engineeringSkillProductivity
Guides your agent to build polished, accessible, responsive web interfaces that look professionally designed.
Ready to connect★ 94k
- View details
git-workflow-and-versioningSkillAI & models
Guides your agent to follow good git habits like clean commits, branching, pull requests, releases, and version bumps.
Ready to connect★ 94k
- View details
idea-refineSkillAI & models
Lets your agent turn a vague idea into a clear, structured plan through guided questioning, variation generation, and stress-testing.
Ready to connect★ 94k
- View details
incremental-implementationSkillFiles & storage
Guides your agent to build features in small tested steps instead of writing lots of code in one go.
Ready to connect★ 94k
- View details
interview-meSkillAI & models
Lets your agent interview you one question at a time to figure out what you actually want before building anything.
Ready to connect★ 94k
- View details
observability-and-instrumentationSkillMonitoring & ops
Guides your agent to add logging, metrics, tracing, and alerting to code so production behavior can be seen and diagnosed.
Ready to connect★ 94k
- View details
performance-optimizationSkillDatabases & data
Guides your agent to measure and fix slow apps, from page load times to slow database queries.
Ready to connect★ 94k
- View details
planning-and-task-breakdownSkillProductivity
Lets your agent break a large project or spec into small ordered tasks with acceptance criteria.
Ready to connect★ 94k
- View details
security-and-hardeningSkillFiles & storage
Guides your agent to write code that resists common security vulnerabilities like injection and unsafe data handling.
Ready to connect★ 94k
- View details
shipping-and-launchSkillCloud & infra
Lets your agent run a pre-launch checklist and plan staged rollouts, monitoring, and rollback for production deploys.
Ready to connect★ 94k
- View details
source-driven-developmentSkillDocs & knowledge
Makes your agent check official documentation before writing framework code and cite its sources.
Ready to connect★ 94k
- View details
spec-driven-developmentSkillDocs & knowledge
Lets your agent write a structured specification before coding, turning vague requirements into reviewed plans.
Ready to connect★ 94k
- View details
test-driven-developmentSkillAI & models
Guides your agent to write failing tests before writing code so changes and bug fixes are proven to work.
Ready to connect★ 94k
- View details
using-agent-skillsSkillAI & models
Helps your agent find and apply the right engineering workflow skill for whatever coding task it's working on.
Ready to connect★ 94k
- View details
babysitSkillMonitoring & ops
Lets your agent keep watching a pull request until its comments, reviews, and CI checks are all resolved.
Ready to connect★ 94k
- View details
cloud-syncSkillDatabases & data
Lets your agent set up and check cloud backup and syncing of its memory database to a cmem.ai account.
Ready to connect★ 94k
- View details
design-isSkillMedia
Lets your agent review a UI design against Dieter Rams' ten principles and suggest whether to build, refine, or redesign.
Ready to connect★ 94k
- View details
doSkillProductivity
Lets your agent execute a multi-step implementation plan by delegating work to subagents.
Ready to connect★ 94k
- View details
how-it-worksSkillDocs & knowledge
Explains how claude-mem captures observations, when memory injection happens, and where data is stored.
Ready to connect★ 94k
- View details
knowledge-agentSkillDocs & knowledge
Lets your agent build searchable knowledge bases from past observations and ask questions about past work.
Ready to connect★ 94k
- View details
learn-codebaseSkillFiles & storage
Lets your agent read every source file in a project to learn how the codebase works.
Ready to connect★ 94k
- View details
make-planSkillDocs & knowledge
Create a detailed, phased implementation plan with documentation discovery. Use when asked to plan a feature, task, or multi-step implementation — especially before executing with do.
Ready to connect★ 94k
- View details
mem-searchSkillSearch
Lets your agent search your saved memory from past sessions to recall decisions, files, and prior work.
Ready to connect★ 94k
- View details
mem-setupSkillAI & models
Lets your agent set up and connect the claude-mem memory plugin using your sync credentials.
Ready to connect★ 94k
- View details
mode-creatorSkillCommunication
Lets your agent create and activate custom memory modes for claude-mem, including alerts and startup checks.
Ready to connect★ 94k
- View details
oh-my-issuesSkillAI & models
Lets your agent group related GitHub issues by root cause into plan issues and link fix PRs.
Ready to connect★ 94k
- View details
openclawSkillAI & models
Lets your agent remember what happened in past sessions by saving and reusing context automatically.
Ready to connect★ 94k
- View details
pathfinderSkillAI & models
Lets your agent analyze a codebase, spot duplicated logic across features, and propose a unified architecture.
Ready to connect★ 94k
- View details
smart-exploreSkillSearch
Lets your agent explore a codebase's structure and find functions without reading whole files.
Ready to connect★ 94k
- View details
standupSkillAI & models
Lets your agent review changes across git branches, worktrees, or PRs and produce one consolidation plan.
Ready to connect★ 94k
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.
54,764 of the 55,196 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.