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
52,958 results · page 13 of 1,766
- View details
qaSkillWeb & browsing
Lets your agent test a website or web app in a real browser and score its quality from 1 to 5 with evidence.
Ready to connect★ 114k
- View details
remote-browserSkillWeb & browsing
Lets your agent open and control a cloud-hosted browser to visit sites, click, type, and take screenshots.
Ready to connect★ 114k
- View details
x402SkillWeb & browsing
Lets your agent set up and run Browser Use cloud browser tasks paid per request from a USDC crypto wallet instead of an API key.
Ready to connect★ 114k
- View details
firebase-security-rules-auditorSkillFiles & storage
Lets your agent review your Firebase database security rules and flag unsafe settings.
Ready to connect★ 439
- View details
firebase-ai-logic-basicsSkillSecurity
Lets your agent work with Firebase AI features like setting up and using AI models in your app.
Ready to connect★ 439
- View details
neonSkillDatabases & data
Lets your agent create and manage Neon Postgres databases and run queries on them.
Ready to connect★ 88
- View details
ad-creativeSkillDev tools
Lets your agent write and refine ad copy like headlines, descriptions, and full ad variations for paid platforms.
Ready to connect★ 49k
- View details
fmtSkillDev tools
Lets your agent automatically format all code in the repository before commits or pull requests.
Ready to connect★ 108k
- View details
issue-triageSkillDev tools
Lets your agent triage GitHub issues by reproducing bugs, classifying them, adding labels, and posting findings.
Ready to connect★ 108k
- View details
lint-allSkillDev tools
Lets your agent run lint checks across Rust and JavaScript/TypeScript code before you open a PR.
Ready to connect★ 108k
- View details
lint-jsSkillFiles & storage
Lets your agent check JavaScript and TypeScript code for style and error issues before a PR.
Ready to connect★ 108k
- View details
node-compatSkillDev tools
Lets your agent run Node.js compatibility tests and fix, skip, or ignore failing ones.
Ready to connect★ 108k
- View details
review-prSkillSecurity
Lets your agent review a Deno pull request for correctness, tests, security, and conventions.
Ready to connect★ 108k
- View details
browser-actSkillWeb & browsing
Lets your agent drive a real browser to open pages, fill forms, click buttons, and grab content JavaScript pages need.
Ready to connect★ 6k
- View details
xcode-project-setupSkillFiles & storage
Lets your agent set up and configure Xcode projects to work with Firebase services.
Ready to connect★ 439
- View details
caveman-discoverSkillAI & models
Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.
Ready to connect★ 105k
- View details
caveman-evidence-reviewSkillAI & models
Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.
Ready to connect★ 105k
- View details
caveman-exploreSkillSearch
Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main context.
Ready to connect★ 105k
- View details
caveman-learnSkillAI & models
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Ready to connect★ 105k
- View details
caveman-manageSkillDev tools
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
Ready to connect★ 105k
- View details
caveman-optimizeSkillDev tools
Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.
Ready to connect★ 105k
- View details
caveman-setupSkillMonitoring & ops
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.
Ready to connect★ 105k
- View details
investigate-firstSkillDev tools
Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.
Ready to connect★ 105k
- View details
lean-buildSkillDev tools
Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.
Ready to connect★ 105k
- View details
migrationSkillDev tools
Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.
Ready to connect★ 105k
- View details
safe-refactorSkillAI & models
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Ready to connect★ 105k
- View details
surgical-patchSkillProductivity
Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.
Ready to connect★ 105k
- View details
verify-and-stopSkillProductivity
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.
Ready to connect★ 105k
- View details
firecrawlSkillWeb & browsing
Lets your agent fetch and read web pages and search the web for current information.
Ready to connect★ 629
- View details
antd-commit-msgSkillCommunication
Generate a single-line commit message for ant-design by reading the project's git staged area and recent commit style. Use when the user asks for a commit message, says "msg", "commit msg", "写提交信息", or wants one-line text that covers all staged changes. Output should match the repository's existing
Ready to connect★ 99k
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.
52,524 of the 52,958 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.