agentleFS

Find the best CLAUDE.md, AGENTS.md and Claude skills

One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.

Best matches · from page 12Worked for most · soon
swigSkill

swig-test

swig/swig/.agents/skills/swig-test/SKILL.md

Run the SWIG test suite for specific languages or one test case across every configured language. Use when testing SWIG changes, adding or changing a test case, verifying language support, debugging test failures or running regression tests.

6.3k9d agoReviewMountCreate a free account to mount
ElasticSkill

scout-ui-testing

elastic/kibana/.agents/skills/scout-ui-testing/SKILL.md

Use when creating, updating, debugging, or reviewing Scout UI tests in Kibana (Playwright + Scout fixtures), including page objects, browser authentication, parallel UI tests (spaceTest/scoutSpace), a11y checks, and flake control.

Steady2 mentions in 2 weeks

No other project uses it yet

21k5mo agoReviewMountCreate a free account to mount
DevolutionsSkill

test-pruner

Devolutions/IronRDP/.agents/skills/test-pruner/SKILL.md

Prune, strengthen, and consolidate tests in a pass of at most one hour, using oracle classification and domain mutants, with cargo-mutants or Stryker.NET where their estimated run fits that hour. Use when asked to remove redundant tests, consolidate tests into cases or properties, audit test value, clean up AI-written tests, finalize a change's tests before its pull request opens, or get a mutation-backed review of a pull request's tests. For a quick oracle-only check, use `test-oracle-reviewer` instead.

Steady17 mentions in 2 weeks

No other project uses it yet

3.3k16d agoReviewMountCreate a free account to mount
callstackSkill

react-native-testing

callstack/react-native-testing-library/skills/react-native-testing/SKILL.md

Write tests using React Native Testing Library (RNTL) v13 and v14 (`@testing-library/react-native`). Use when writing, reviewing, or fixing React Native component tests. Covers: render, screen, queries (getBy/getAllBy/queryBy/findBy), Jest matchers, userEvent, fireEvent, waitFor, and async patterns. Supports v13 (React 18, sync render) and v14 (React 19+, async render). Triggers on: test files for React Native components, RNTL imports, mentions of "testing library", "write tests", "component tests", or "RNTL".

Steady8 mentions in 2 weeks

1 project uses a version of this

3.4k10mo agoReviewMountCreate a free account to mount
openstackSkill

neutron-testing-patches

openstack/neutron/.agents/skills/neutron-testing-patches/SKILL.md

Create temporary DNM patches that stress-test Zuul CI jobs or individual tests by running them multiple times. Covers strategies for duplicating Zuul jobs, duplicating test classes/methods, modifying tox regexes, and repeating tests with stestr. Use when the user asks to create a testing patch, stress-test a CI job, run a test multiple times, or debug flaky tests.

1.5k2mo agoReviewMountCreate a free account to mount
samugit83Skill

redamon-testing

samugit83/redamon/skills/redamon-testing/SKILL.md

How RedAmon tests actually run and how to author them: the per-file Docker gate, the unit/integration/live tiers, and the failure modes that make a green run a lie. Trigger: editing any test_*.py, *.test.ts(x) or tests/*.sh; a test that is red, skipped or xfailed; a request to "run the tests", "make it green" or check coverage; editing redamon.sh cmd_test, tooling/scripts/pytest_isolated.py, any conftest.py or any pytest.ini.

3.3k8mo agoReviewMountCreate a free account to mount
Agenta-AISkill

test-design

Agenta-AI/agenta/.agents/skills/test-design/SKILL.md

Decide what to test and how to write the tests for a frontend change. Use before you write or review unit tests for web/mobile or the @agenta/* packages, when you fix a bug and add a regression test, and before you say a change is tested. Gives the risk list, the rules for each test, and the mutation check.

Steady16 mentions in 2 weeks

18 projects use a version of this

4.9k4mo agoReviewMountCreate a free account to mount
ethereumSkill

run-tests

ethereum/consensus-specs/.claude/skills/run-tests/SKILL.md

Run tests and generate reference tests. All testing goes through `make test`, never `pytest` directly. Always load this skill before running tests.

4k3mo agoReviewMountCreate a free account to mount
medplumSkill

test-compactor

medplum/medplum/.agents/skills/test-compactor/SKILL.md

Cut the tests a diff adds down to the ones that each catch a bug no other test catches, and tighten the survivors. Use after tests pass and before comment-compactor, `git push`, or `gh pr create`. Also use when asked to "trim the tests", "dedupe the tests", "compact the tests", or when a review says a PR has too many, redundant, or overly long tests.

Steady9 mentions in 2 weeks

No other project uses it yet

2.8k34d agoReviewMountCreate a free account to mount
podman-desktopSkill

playwright-testing

podman-desktop/podman-desktop/.agents/skills/playwright-testing/SKILL.md

Guide for writing, updating, and maintaining Playwright end-to-end tests for Podman Desktop using the project's Electron runner, custom fixtures, and Page Object Model hierarchy. Use when creating new E2E spec files, building or modifying page objects, updating the test framework or utilities, debugging test failures, adding smoke tests, or when the user asks about Playwright tests, test automation, spec files, page models, or the E2E test structure.

8.1k12d agoReviewMountCreate a free account to mount
projenSkill

projen-testing-review

projen/projen/skills/projen-review/projen-testing-review/SKILL.md

projen testing reviewer. Use on any projen pull request that changes behavior in `src/**`, `projenrc/**` or `scripts/integ-*.sh`, or adds or changes tests in `test/**`: a feature or fix whose main effect no test would catch breaking, tests that run the code but assert nothing that would catch it, hand-rolled test setup where `synthSnapshot` / `Testing.synth` / `TestProject` / `withProjectDir` / `mkdtemp` already exist, packaged-artifact behavior tested in Jest instead of `scripts/integ-*.sh`, and snapshot tests whose name or file does not match what they snapshot.

Steady2 mentions in 2 weeks

No other project uses it yet

3k11d agoReviewMountCreate a free account to mount
Significant-GravitasSkill

write-frontend-tests

Significant-Gravitas/AutoGPT/.claude/skills/write-frontend-tests/SKILL.md

Analyze the current branch diff against dev, plan integration tests for changed frontend pages/components, and write them. TRIGGER when user asks to write frontend tests, add test coverage, or 'write tests for my changes'.

Steady5 mentions in 2 weeks

3 projects use a version of this

188k11d agoReviewMountCreate a free account to mount
kubernetes-sigsSkill

test-pyramid

kubernetes-sigs/agent-sandbox/.agents/skills/test-pyramid/SKILL.md

Analyze the repo's unit and E2E tests and propose rebalancing toward a test pyramid — which E2E tests (or assertions inside them) can be covered by unit tests, which unit-level gaps genuinely need E2E coverage, and where coverage is duplicated. Use when the user asks about test pyramid, test rebalancing, "should this be an e2e or unit test", E2E-to-unit migration, or slow/flaky E2E suites that might shrink.

1 project uses a version of this

4.5k18d agoReviewMountCreate a free account to mount
cockroachdbSkill

skip-test-with-issue

cockroachdb/cockroach/.claude/skills/skip-test-with-issue/SKILL.md

Skip a flaky or broken test with proper issue tracking. Use when asked to skip a test, disable a test, or mark a test as flaky.

33k8mo agoReviewMountCreate a free account to mount
JetBrainsSkill

writing-tests

JetBrains/intellij-community/.agents/skills/writing-tests/SKILL.md

Write IntelliJ JUnit 5 tests with fixtures, lifecycle, and EDT.

21k8d agoReviewMountCreate a free account to mount
JetBrainsSkill

writing-tests

JetBrains/intellij-community/.claude/skills/writing-tests/SKILL.md

Write IntelliJ JUnit 5 tests with fixtures, lifecycle, and EDT.

21k8d agoReviewMountCreate a free account to mount
dotnetSkill

run-tests

dotnet/sdk/.github/skills/run-tests/SKILL.md

Select and run .NET SDK tests through the repository's diagnostic-preserving test entry point. REQUIRED whenever an agent will select, run, or rerun local dotnet/sdk tests, including a project, class, method, targeted test, focused test, smallest relevant test, or completed-change validation. NEVER invoke when the user says not to run tests yet.

3.2k5mo agoReviewMountCreate a free account to mount
coollabsioSkill

testing-best-practices

coollabsio/coolify/.agents/skills/testing-best-practices/SKILL.md

Laravel test design and review. Use when selecting coverage, naming or structuring tests, choosing assertions or test data, isolating dependencies, testing HTTP or security boundaries, improving suite performance, or reviewing test value. Use framework guidance or search-docs for Pest and PHPUnit syntax.

Cooling2 mentions in 2 weeks

16 projects use a version of this

Often used withinfer-conventionsconfiguring-horizonai-sdk-development

66k45d agoReviewMountCreate a free account to mount
lobehubSkill

agent-testing-bot

lobehub/lobe-chat/.agents/skills/agent-testing-bot/SKILL.md

Use for real bot-channel acceptance in Discord, Slack, Telegram, WeChat/Weixin, Lark/Feishu, QQ or iMessage on macOS. Extends acceptance with native chat apps.

1 project uses a version of this

84k10d agoReviewMountCreate a free account to mount
apacheSkill

connector-testing

apache/iggy/.claude/skills/connector-testing/SKILL.md

Write tests for Apache Iggy connectors - sinks, sources, transforms, SDK, runtime. Covers BDD unit-test naming, the canonical source state round-trip tests, and the real-infra integration test layout under `core/integration/tests/connectors/` with `testcontainers-modules` + `#[iggy_harness]`. Load when writing or reviewing tests in `core/connectors/` or `core/integration/tests/connectors/`. Use for connector test authoring. NOT for runtime internals or non-connector test patterns.

No other project uses it yet

5.3k22d agoReviewMountCreate a free account to mount
CLAUDE.md vs AGENTS.md

Agent instruction files

What are agent instruction files?

Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.

CLAUDE.md or AGENTS.md?

CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.

What is a skill?

A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.

Can I search my own team's files too?

Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.