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 568 of 1,823
- View details
figure-it-outSkillMonitoring & ops
Lets your agent build a careful, logged step-by-step plan for big or unclear tasks and review its own reasoning as it works.
Ready to connect★ 461
- View details
interrogateSkillAI & models
Lets your agent get code and plans challenged by several AI reviewers looking for flaws and blind spots.
Ready to connect★ 461
- View details
maintain-verification-skillSkillAI & models
Lets your agent audit and update a project's verification skill and feature map, submitting corrections as one PR.
Ready to connect★ 461
- View details
make-pr-easy-to-reviewSkillAI & models
Lets your agent tidy up pull requests with cleaner commits, better descriptions, and notes to help reviewers.
Ready to connect★ 461
- View details
no-commentsSkillAI & models
Lets your agent spawn a subagent that fixes accepted code review findings and offers encodings for claimed constraints.
Ready to connect★ 461
- View details
poteto-modeSkillAI & models
Changes your agent's working style to give concise, detailed answers, simple code, and verified results.
Ready to connect★ 461
- View details
principle-attack-the-premiseSkillAI & models
Guides your agent to question shared assumptions when repeated fixes keep failing, and test the premise instead.
Ready to connect★ 461
- View details
principle-boundary-disciplineSkillAI & models
Guides your agent to put validation and error handling at system edges while keeping core logic as pure functions.
Ready to connect★ 461
- View details
principle-build-the-leverSkillAI & models
Guides your agent to build reusable scripts or tools instead of doing repetitive work by hand.
Ready to connect★ 461
- View details
principle-encode-lessons-in-structureSkillAI & models
Helps your agent turn repeated instructions and corrections into automated checks instead of repeating text.
Ready to connect★ 461
- View details
principle-exhaust-the-design-spaceSkillMedia
Guides your agent to build 2-3 competing prototypes of a design and compare them before choosing one.
Ready to connect★ 461
- View details
principle-experience-firstSkillAI & models
Guides your agent to put user experience first when making product or feature decisions.
Ready to connect★ 461
- View details
principle-fix-root-causesSkillAI & models
Guides your agent to debug by tracing symptoms to their root cause and fixing them there.
Ready to connect★ 461
- View details
principle-foundational-thinkingSkillAI & models
Guides your agent to plan core data structures and work order before writing code.
Ready to connect★ 461
- View details
principle-guard-the-context-windowSkillFiles & storage
Keeps your agent's memory from filling up by offloading large files and outputs to subagents and keeping only summaries.
Ready to connect★ 461
- View details
principle-laziness-protocolSkillAI & models
Lets your agent keep code changes minimal when refactoring, favoring deletion and simple fixes over new abstractions.
Ready to connect★ 461
- View details
principle-make-operations-idempotentSkillAI & models
Guides your agent to design commands and retry loops that safely produce the same result even after crashes or repeated runs.
Ready to connect★ 461
- View details
principle-migrate-callers-then-delete-legacy-apisSkillAI & models
Guides your agent to migrate code callers to a new API and delete the old one in one change instead of keeping shims.
Ready to connect★ 461
- View details
principle-minimize-reader-loadSkillAI & models
Helps your agent simplify hard-to-trace code by counting indirection layers and collapsing needless wrappers.
Ready to connect★ 461
- View details
principle-model-the-domainSkillFiles & storage
Guides your agent to encode business rules in a shared data structure instead of scattering if-statements across files.
Ready to connect★ 461
- View details
principle-never-block-on-the-humanSkillAI & models
Lets your agent proceed with reversible work on its own instead of stopping to ask you for confirmation.
Ready to connect★ 461
- View details
principle-outcome-oriented-executionSkillAI & models
Guides your agent to rewrite or migrate code straight to the target architecture instead of keeping temporary compatibility code.
Ready to connect★ 461
- View details
principle-prove-it-worksSkillProductivity
Makes your agent verify a finished task by checking the real result instead of just claiming it's done.
Ready to connect★ 461
- View details
principle-redesign-from-first-principlesSkillMedia
Guides your agent to redesign an existing design from scratch when adding a new requirement instead of patching it on.
Ready to connect★ 461
- View details
principle-separate-before-serializing-shared-stateSkillFiles & storage
Gives your agent a rule for handling shared state by removing concurrent writers before serializing access.
Ready to connect★ 461
- View details
principle-sequence-verifiable-unitsSkillAI & models
Guides your agent to break multi-step work into small, verifiable steps and order commits so each change is easy to check.
Ready to connect★ 461
- View details
principle-subtract-before-you-addSkillAI & models
Guides your agent to remove dead code and redundant pieces before adding or refactoring new features.
Ready to connect★ 461
- View details
principle-test-behavior-not-implementationSkillAI & models
Guides your agent to write software tests that check real behavior instead of internal implementation details.
Ready to connect★ 461
- View details
principle-type-system-disciplineSkillAI & models
Guides your agent to write safer type definitions and function signatures in statically-typed languages.
Ready to connect★ 461
- View details
setup-pstackSkillFiles & storage
Lets your agent detect your available models and write a config file mapping each pstack role to a model.
Ready to connect★ 461
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.