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 599 of 1,823
- View details
anthropic-artSkillAI & models
Lets your agent create Anthropic-style hand-drawn blog and article illustrations with warm colors and bold black lines.
Ready to connect★ 436
- View details
pavedpath-codeSkillDocs & knowledge
Lets your agent find proven code solutions from GitHub repos, issues, PRs, and discussions to help solve engineering problems.
Ready to connect★ 435
- View details
swift-testing-proSkillAI & models
Lets your agent write, review, and improve Swift Testing test code using modern APIs.
Ready to connect★ 435
- View details
ai-tellsSkillDev tools
Reviews your draft for AI writing patterns and produces a cleaner rewrite.
Ready to connect★ 434
- View details
analyze-changesSkillDocs & knowledge
Analyzes git changes and generates a design document with diagrams, examples, and impact assessment.
Ready to connect★ 434
- View details
create-presentationSkillDocs & knowledge
Lets your agent create a PPTX presentation explaining the code changes on your current branch.
Ready to connect★ 434
- View details
edit-designSkillFiles & storage
Lets your agent safely edit design.md or design-mechanics.md with a review-then-revise workflow.
Ready to connect★ 434
- View details
execute-tracksSkillDev tools
Lets your agent carry out a saved implementation plan step by step, with reviews before, during, and after coding.
Ready to connect★ 434
- View details
fix-ci-failureSkillDev tools
Lets your agent diagnose and fix CI test failures from GitHub PRs or workflow runs and open a PR with the fix.
Ready to connect★ 434
- View details
migrate-workflowSkillDev tools
Lets your agent update stale workflow artifacts on a branch after workflow-format changes.
Ready to connect★ 434
- View details
profile-jmh-regressionsSkillDev tools
Lets your agent profile JMH benchmark regressions and find which methods caused the slowdown.
Ready to connect★ 434
- View details
profile-query-bottleneckSkillDatabases & data
Lets your agent measure why database queries run slowly and pinpoint the cause.
Ready to connect★ 434
- View details
readability-feedbackSkillDocs & knowledge
Lets your agent find hard-to-read paragraphs in a design doc and update writing rules so future docs stay clear.
Ready to connect★ 434
- View details
review-planSkillDev tools
Lets your agent re-check a work plan for consistency and structure before executing it.
Ready to connect★ 434
- View details
review-workflow-prSkillFiles & storage
Lets your agent review a workflow PR's design docs and post a GitHub review with comments on specific lines.
Ready to connect★ 434
- View details
run-jmh-benchmarks-hetznerSkillCloud & infra
Lets your agent spin up a Hetzner server, run JMH benchmarks on your project, collect results, and delete the server.
Ready to connect★ 434
- View details
arxiv-paper-writerSkillDev tools
Lets your agent write LaTeX ML/AI review papers for arXiv with an IEEE template and checked citations.
Ready to connect★ 433
- View details
collaborating-with-claudeSkillFiles & storage
Lets your agent consult Claude Code CLI for second opinions, debugging help, and code review via multi-turn sessions.
Ready to connect★ 433
- View details
collaborating-with-geminiSkillFiles & storage
Lets your agent consult the Gemini CLI for coding help like prototyping, debugging, and code review, with multi-turn sessions.
Ready to connect★ 433
- View details
latex-rhythm-refinerSkillDev tools
Lets your agent rewrite LaTeX prose to vary sentence rhythm and remove filler phrases while keeping citations intact.
Ready to connect★ 433
- View details
rlmSkillMedia
Lets your agent plan, design, and build a custom Recursive Language Model for a workflow.
Ready to connect★ 433
- View details
rlm-gepaSkillDev tools
Lets your agent set up, evaluate, and optimize RLM instruction projects using execution traces and optimization configs.
Ready to connect★ 433
- View details
yupi-skillSkillDev tools
Lets your agent answer programming questions in the voice and thinking style of Programmer Yupi.
Ready to connect★ 432
- View details
bikeshed-conversionSkillDev tools
Gives your agent guidelines for converting W3C specs to Bikeshed format, covering anchor IDs, definitions, and pitfalls.
Ready to connect★ 430
- View details
publish-wg-minutesSkillFiles & storage
Lets your agent turn WebPerfWG meeting minutes from Google Docs zip exports into published minutes.
Ready to connect★ 430
- View details
Blue Team Defense & HardeningSkillMonitoring & ops
Lets your agent review system settings, monitor security baselines, and suggest patches to close weak points.
Ready to connect★ 425
- View details
Cloud Security & Container HardeningSkillCloud & infra
Lets your agent check your cloud and container setups for security weaknesses and compliance gaps.
Ready to connect★ 425
- View details
Cryptographic Analysis & AssessmentSkillSecurity
Lets your agent check SSL/TLS security settings and find weak encryption in code.
Ready to connect★ 425
- View details
CSOC Operations & Playbook AutomationSkillMonitoring & ops
Lets your agent sort security alerts, follow incident steps, escalate issues, and track security metrics.
Ready to connect★ 425
- View details
Exploit Development & Payload EngineeringSkillSecurity
Lets your agent build proof-of-concept exploits, craft payloads, and analyze shellcode for authorized security testing.
Ready to connect★ 425
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.