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 680 of 1,836
- View details
progressive-loadingSkillAI & models
Lets your agent load only the skill modules it needs, cutting token use in large multi-part skills.
Ready to connect★ 335
- View details
Project InitSkillAI & models
Sets up a new project with git, CI/CD workflows, pre-commit hooks, Makefiles, and language tooling.
★ 335
- View details
project-brainstormingSkillAI & models
Lets your agent guide project brainstorming through structured questions to turn unclear ideas into a written project brief.
Ready to connect★ 335
- View details
project-executionSkillProductivity
Lets your agent carry out implementation plans step by step while tracking progress and checking quality.
Ready to connect★ 335
- View details
project-planningSkillAI & models
Lets your agent turn a finished specification into a phased, dependency-ordered implementation plan.
Ready to connect★ 335
- View details
project-specificationSkillAI & models
Turns a project brief into a testable specification with user stories and acceptance criteria.
Ready to connect★ 335
- View details
provider-setupSkillSecurity
Checks which delegation CLIs your agent has installed and logged in, sets up missing ones, and saves the result.
Ready to connect★ 335
- View details
pytest-configSkillAI & models
Lets your agent set up and audit Python pytest configurations, fixtures, and CI test patterns.
Ready to connect★ 335
- View details
qiaomu-cutSkillMedia
Lets your agent plan, edit, and render videos from a plain-language request.
Ready to connect★ 335
- View details
quality-gateSkillAI & models
Lets your agent run quality checks on code changes, including review, cleanup, and test updates before a PR.
Ready to connect★ 335
- View details
quota-managementSkillMonitoring & ops
Lets your agent track API usage and rate-limit budgets, checking quotas before calls to avoid hitting limits.
Ready to connect★ 335
- View details
qwen-delegationSkillProductivity
Lets your agent hand tasks like large-file analysis and batch summarization to the Qwen CLI.
Ready to connect★ 335
- View details
Record BrowserSkillWeb & browsing
Lets your agent record browser sessions as it navigates web pages.
★ 335
- View details
Record TerminalSkillAI & models
Lets your agent create terminal recordings by writing VHS tape scripts.
★ 335
- View details
Refine CodeSkillAI & models
Lets your agent analyze code quality across six dimensions and apply fixes.
★ 335
- View details
Reinstall All PluginsSkillAI & models
Lets your agent uninstall and reinstall all plugins to fix version mismatches and refresh the cache.
★ 335
- View details
Resolve ThreadsSkillAI & models
Lets your agent mark pull request review threads as resolved in bulk on GitHub or GitLab.
★ 335
- View details
response-compressionSkillAI & models
Lets your agent trim filler and fluff from its replies so answers are shorter and use fewer tokens.
Ready to connect★ 335
- View details
review-coreSkillAI & models
Gives your agent a step-by-step workflow for running reviews with logged evidence and verified findings.
Ready to connect★ 335
- View details
rigorous-reasoningSkillAI & models
Makes your agent question agreement and analyze contested claims rigorously instead of telling you what you want to hear.
Ready to connect★ 335
- View details
risk-classificationSkillProductivity
Lets your agent score each task's risk level (GREEN to CRITICAL) before acting, so risky changes get extra checks.
Ready to connect★ 335
- View details
rule-catalogSkillAI & models
Lets your agent browse and install pre-built safety and quality rules into a project.
Ready to connect★ 335
- View details
Rules EvalSkillAI & models
Lets your agent check the quality of Claude Code rules files in .claude/rules/ directories.
★ 335
- View details
rules-evalSkillAI & models
Lets your agent audit the quality of rules files in .claude/rules/, checking frontmatter, glob patterns, and clarity.
Ready to connect★ 335
- View details
scope-guardSkillAI & models
Lets your agent score proposed features for value versus cost and check whether they fit the current branch's scope.
Ready to connect★ 335
- View details
sem-integrationSkillAI & models
Lets your agent compare versions of code by detecting semantic differences in git diffs.
Ready to connect★ 335
- View details
service-registrySkillAI & models
Lets your agent register external services, check their health, and run commands through them from one central registry.
Ready to connect★ 335
- View details
skill-graph-auditSkillAI & models
Lets your agent audit skill references and find hubs, isolates, and broken links.
Ready to connect★ 335
- View details
skill-library-missionSkillAI & models
Lets your agent build a library of reusable project skills in .claude/skills/ by discovering, authoring, and reviewing them in parallel.
Ready to connect★ 335
- View details
Skills EvalSkillAI & models
Audits your agent skills for quality, formatting, token use, and activation reliability, then suggests fixes.
★ 335
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.