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
55,257 results · page 763 of 1,842
- View details
requirement-coverage-checkerSkillDocs & knowledge
Lets your agent check that designs, code, and tests fully cover your project's requirements.
Ready to connect★ 251
- View details
requirement-enhancerSkillDev tools
Lets your agent turn vague, informal requirements into clear, complete, actionable specifications.
Ready to connect★ 251
- View details
requirement-summarizerSkillDocs & knowledge
Lets your agent extract and summarize key features, constraints, and priorities from requirement documents.
Ready to connect★ 251
- View details
requirement-summarySkillDocs & knowledge
Lets your agent turn requirement documents and specs into short bullet-point summaries of features, dependencies and constraints.
Ready to connect★ 251
- View details
requirement-to-tlaplus-property-generatorSkillDocs & knowledge
Turns plain-language system requirements into TLA+ properties like invariants and safety checks.
Ready to connect★ 251
- View details
rollback-strategy-advisorSkillDatabases & data
Lets your agent suggest rollback plans for failed deployments, covering code, databases, infrastructure, and config.
Ready to connect★ 251
- View details
rtl-equivalence-checkerSkillMedia
Lets your agent check whether two Verilog hardware designs behave the same way.
Ready to connect★ 251
- View details
rtl-property-inferenceSkillAI & models
Lets your agent read Verilog RTL code and automatically write SystemVerilog Assertions checking correctness properties.
Ready to connect★ 251
- View details
rtl-specification-consistency-checkerSkillDev tools
Lets your agent check whether a hardware RTL implementation matches its high-level specification.
Ready to connect★ 251
- View details
runtime-error-explainerSkillDev tools
Lets your agent explain runtime errors and compile failures with clear debugging steps.
Ready to connect★ 251
- View details
scenario-generatorSkillDev tools
Lets your agent turn requirements into test scenarios, user stories, and acceptance criteria.
Ready to connect★ 251
- View details
security-patch-advisorSkillSecurity
Lets your agent suggest fixes and safer code patterns for security vulnerabilities like injection or buffer overflows.
Ready to connect★ 251
- View details
security-sensitive-path-instrumenterSkillMonitoring & ops
Lets your agent add monitoring and logging to login, permission-check, and input-handling code while the app runs.
Ready to connect★ 251
- View details
semantic-bug-detectorSkillDocs & knowledge
Lets your agent find logic bugs by checking whether code actually does what its names, comments, and docs say it should.
Ready to connect★ 251
- View details
semantic-equivalence-verifierSkillMonitoring & ops
Lets your agent check whether two pieces of code behave the same way by comparing their control flow, data flow, and behavior.
Ready to connect★ 251
- View details
semantic-szz-analyzerSkillDev tools
Lets your agent trace a bug fix back to the commit that first introduced the bug in your code history.
Ready to connect★ 251
- View details
smart-mutation-operator-generatorSkillDev tools
Lets your agent analyze a codebase and generate custom mutation operators for testing how well its tests catch bugs.
Ready to connect★ 251
- View details
wpp-api-referenceSkillDev tools
Helps your agent write Delphi/Lazarus code that sends messages and manages chats, groups, polls, and calls.
Ready to connect★ 250
- View details
wpp-buildSkillDev tools
Guides your agent through building and installing the WPP4Delphi package in Delphi or Lazarus.
Ready to connect★ 250
- View details
wpp-rag-indexSkillDatabases & data
Lets your agent build and update a local search index of WPP4Delphi docs and Pascal source for semantic queries.
Ready to connect★ 250
- View details
wpp-releaseSkillDev tools
Lets your agent publish a new version of the WPP4Delphi library by committing, pushing, and creating a GitHub release.
Ready to connect★ 250
- View details
wpp-updateSkillDev tools
Lets your agent update the WPP4Delphi component to the latest GitHub version, build and install it in Delphi, and summarize new commits.
Ready to connect★ 250
- View details
add-learningSkillFiles & storage
Lets your agent save a lesson or reusable insight to a learnings file for future use.
Ready to connect★ 250
- View details
analyze-comparison-testsSkillCloud & infra
Lets your agent collect comparison test run results and answer questions about how each run performed.
Ready to connect★ 250
- View details
analyze-skill-issuesSkillFiles & storage
Lets your agent look up stored test results to explain why a skill's tests are failing.
Ready to connect★ 250
- View details
analyze-test-runSkillCloud & infra
Lets your agent analyze a GitHub Actions test run and report why tests failed.
Ready to connect★ 250
- View details
build-vault-universeSkillCommerce & finance
Lets your agent update a notebook with the top 10 vaults ranked by one-year return.
Ready to connect★ 250
- View details
bump-rfcSkillDev tools
Lets your agent move an Incan RFC through its status stages like Draft to Planned or In Progress to Implemented.
Ready to connect★ 250
- View details
clear-backtesting-cacheSkillSearch
Lets your agent delete cached indicator data used by backtesting and optimisation notebooks.
Ready to connect★ 250
- View details
closeoutSkillProductivity
Lets your agent clean up after a merged pull request by syncing the base branch and deleting leftover branches and worktrees.
Ready to connect★ 250
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.
54,826 of the 55,257 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.