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.
Category: Dev tools
17,237 results · page 169 of 575
- View details
ensure-all-tests-pass-after-code-changesSkillDev tools
Lets your agent run the test suite and verify all tests pass after code changes.
Ready to connect★ 479
- View details
fork-pr-operationsSkillDev tools
Guides your agent through handling pull requests between forked repositories, including workflow approvals and force-pushes.
Ready to connect★ 479
- View details
git-revert-safetySkillDev tools
Guides your agent through git revert and merge-undo steps with a claude skill that checks for collateral damage.
Ready to connect★ 479
- View details
guardrail-patternsSkillDev tools
Lets your agent follow the repo's rules when changing the destructive-command guardrail code in opencode-swarm.
Ready to connect★ 479
- View details
isolate-the-specific-failure-mode-before-proposing-a-fixSkillDev tools
Guides your agent to pinpoint the exact cause of a bug before suggesting any fix.
Ready to connect★ 479
- View details
issue-ingestSkillDev tools
Lets your agent turn a GitHub issue into a root-cause analysis and a written spec for fixing it.
Ready to connect★ 479
- View details
issue-tracerSkillDev tools
Lets your agent investigate, root-cause, fix, and close bug reports, regressions, and failing tests.
Ready to connect★ 479
- View details
loopSkillDev tools
Lets your agent run a loop skill that iterates through brainstorm, plan, build, review and improve with resumable state.
Ready to connect★ 479
- View details
merge-queue-readinessSkillDev tools
Lets your agent simulate CI on a PR before adding it to a GitHub merge queue to avoid failed merges.
Ready to connect★ 479
- View details
mock-moduleSkillDev tools
Lets your agent create mock modules for testing code without real dependencies.
Ready to connect★ 479
- View details
mock-to-internals-migrationSkillDev tools
Lets your agent migrate Bun tests from mock.module to injectable internals seams to fix mock leakage.
Ready to connect★ 479
- View details
opt-in-tool-registrationSkillDev tools
Makes your agent ask you before enabling new tools during a session.
Ready to connect★ 479
- View details
phase-completeSkillDev tools
Lets your agent mark a development phase as complete when working with the opencode-swarm workflow.
Ready to connect★ 479
- View details
pr-readinessSkillDev tools
Redirects your agent to the swarm-pr-feedback skill, replacing this older pull-request feedback tool.
Ready to connect★ 479
- View details
propagation-testSkillDev tools
Lets your agent test event or data propagation across a swarm of code agents.
Ready to connect★ 479
- View details
qa-sweepSkillDev tools
Lets your agent run an independent QA review of code changes before publishing.
Ready to connect★ 479
- View details
restore-internals-seams-in-finally-blocks-after-each-testSkillDev tools
Lets your agent automatically restore internal code seams in finally blocks after each test runs.
Ready to connect★ 479
- View details
run-failing-tests-immediately-after-test-gate-failureSkillDev tools
Lets your agent run claude skill tests that failed, immediately after a test gate failure.
Ready to connect★ 479
- View details
run-relevant-tests-after-adding-error-handling-wrappersSkillDev tools
Lets your agent run the relevant tests after adding error-handling wrappers to code.
Ready to connect★ 479
- View details
run-relevant-tests-after-logic-changesSkillDev tools
Lets your agent run claude skill scripts that run the relevant tests after code logic changes.
Ready to connect★ 479
- View details
run-test-suite-after-registration-changesSkillDev tools
Lets your agent run claude skill test suites automatically after registration code changes.
Ready to connect★ 479
- View details
run-tests-on-the-unmodified-codebase-before-starting-to-establisSkillDev tools
Lets your agent run claude skill that runs tests on the unmodified codebase to set a failure baseline.
Ready to connect★ 479
- View details
rust-crate-ciSkillDev tools
Gives your agent a rust claude skill for validating Rust crate edits against CI checks before you commit.
Ready to connect★ 479
- View details
safe-renameSkillDev tools
Lets your agent rename functions, types, or variables across a codebase and verify nothing breaks.
Ready to connect★ 479
- 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★ 479
- 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★ 479
- View details
swarmSkillDev tools
Lets your agent run a swarm-style workflow with parallel investigation and extra review rigor in Codex threads.
Ready to connect★ 479
- 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★ 479
- View details
swarm-resumeSkillDev tools
Lets your agent safely continue an already-approved plan from where it left off.
Ready to connect★ 479
- 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★ 479
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.
55,004 of the 55,435 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.