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 582 of 1,823
- View details
run-failing-tests-immediately-after-test-gate-failureSkillDev tools
Lets your agent rerun the failing tests right away after a test gate fails to see what broke.
Ready to connect★ 475
- View details
run-relevant-tests-after-adding-error-handling-wrappersSkillDev tools
Has your agent run the relevant tests after adding error-handling wrappers to code.
Ready to connect★ 475
- View details
run-relevant-tests-after-logic-changesSkillDev tools
Lets your agent run the tests relevant to the code logic it just changed.
Ready to connect★ 475
- View details
run-test-suite-after-registration-changesSkillDev tools
Lets your agent run the test suite after changes to registration code.
Ready to connect★ 475
- View details
run-tests-on-the-unmodified-codebase-before-starting-to-establisSkillDev tools
Lets your agent run tests on unchanged code first to record a baseline of which tests pass or fail.
Ready to connect★ 475
- View details
running-testsSkillFiles & storage
Lets your agent run and debug test suites safely, with per-file isolation and checks for failing or truncated output.
Ready to connect★ 475
- View details
rust-crate-ciSkillDev tools
Loads repo rules for editing Rust crates, covering formatting, lint, and Windows-specific checks CI enforces.
Ready to connect★ 475
- View details
safe-extractionSkillFiles & storage
Lets your agent split large code files into smaller modules without breaking imports or tests.
Ready to connect★ 475
- View details
safe-renameSkillDev tools
Lets your agent rename functions, types, or variables across a codebase and verify nothing breaks.
Ready to connect★ 475
- View details
skill-edit-validationSkillFiles & storage
Checks that tests still match after your agent edits skill or prompt files, catching stale assertions early.
Ready to connect★ 475
- View details
specifySkillDev tools
Lets your agent write and manage software requirement specifications, check them against the codebase, and run quality reviews.
Ready to connect★ 475
- View details
spread-real-module-exports-as-base-of-every-mock-module-return-oSkillDev tools
Lets your agent spread real module exports into every mock.module return object when writing test mocks.
Ready to connect★ 475
- View details
subprocess-safetySkillFiles & storage
Gives your agent safety guidelines for running subprocess calls in code with spawn or child_process.
Ready to connect★ 475
- View details
swarm-ci-monitorSkillMonitoring & ops
Lets your agent watch CI on an approved pull request, fix failures, and merge once tests pass.
Ready to connect★ 475
- View details
swarm-implementSkillFiles & storage
Lets your agent plan and implement multi-file code changes with review and validation steps.
Ready to connect★ 475
- View details
swarm-planSkillProductivity
Lets your agent create and manage detailed task plans, breaking work into small trackable steps.
Ready to connect★ 475
- View details
swarm-pr-feedbackSkillDev tools
Lets your agent work through and resolve known pull request feedback like review comments, CI failures, and merge conflicts.
Ready to connect★ 475
- View details
swarm-pr-reviewSkillMonitoring & ops
Lets your agent run a deep, multi-step review of a pull request, flagging risks across many areas.
Ready to connect★ 475
- View details
swarm-pr-subscribeSkillSearch
Lets your agent watch a pull request after it's opened and respond to its activity until it's merged.
Ready to connect★ 475
- View details
swarm-resumeSkillDev tools
Lets your agent safely continue an already-approved plan from where it left off.
Ready to connect★ 475
- View details
tech-debt-ci-reviewSkillDev tools
Lets your agent audit codebases for technical debt, flaky tests, and unstable CI pipelines, then suggest fixes in order.
Ready to connect★ 475
- View details
test-file-splitSkillFiles & storage
Lets your agent break large test files into smaller, organized ones so they stay under a set size limit.
Ready to connect★ 475
- View details
tool-connectorSkillDocs & knowledge
Connects your agent to your workplace tools like Slack, Jira, GitHub, or internal systems.
Ready to connect★ 475
- View details
unswarmSkillDev tools
Lets your agent turn off swarm-style multi-step workflow mode and return to a simpler single-agent mode.
Ready to connect★ 475
- View details
update-or-delete-tests-that-assert-intentionally-removed-behavioSkillDev tools
Lets your agent update or delete tests that check for code behavior you've intentionally removed.
Ready to connect★ 475
- View details
use-internals-di-seam-pattern-for-test-injectable-functionsSkillDev tools
Shows your agent how to write functions with a dependency injection seam so tests can swap in mock dependencies.
Ready to connect★ 475
- View details
verify-skill-mirror-pairs-exist-in-both-opencode-skills-and-clauSkillAI & models
Checks that each skill file in .opencode/skills/ has a matching copy in .claude/skills/.
Ready to connect★ 475
- View details
widen-return-typeSkillDev tools
Lets your agent widen a function's return type in code.
Ready to connect★ 475
- View details
worktree-retry-cleanupSkillProductivity
Lets your agent clean up old worktree lanes before retrying a failed or cancelled task.
Ready to connect★ 475
- View details
postizSkillCommunication
Lets your agent schedule and publish posts across 28+ social media and chat platforms like X, LinkedIn, Instagram, and Slack.
Ready to connect★ 472
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.