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 7Worked for most · soon
lobehubSkill

local-testing

lobehub/lobe-ui/.agents/skills/local-testing/SKILL.md

Local browser verification for the lobe-ui component library and documentation site. Uses agent-browser against the React Router and Vite development server, including component pages, manifest-backed standalone demos, theme states, and responsive layouts. Trigger on local test, UI test, verify component, test in browser, visual check, or screenshot demo.

2 projects use a version of this

2.3k25d agoReviewMountCreate a free account to mount
rosuHSkill

testing-setup

rosuH/EasyWatermark/.agents/skills/testing-setup/SKILL.md

Analyze and create a testing strategy for Android apps - install testing

1.9k29d agoReviewMountCreate a free account to mount
TeamHypersomniaReads credentialsSkill

local-testing

TeamHypersomnia/Hypersomnia/.claude/skills/local-testing/SKILL.md

Test Hypersomnia end to end without the user, mainly networking - local masterserver, dedicated servers and CLI clients (UDP and WebRTC), server keys, certs and the identity broker, the web build in Firefox under Xvfb, game UI via screenshots and XTest clicks, the hypersomnia.io site in a scratch copy, isolated builds (native, Steam, web, Ubuntu containers for the remote hosts) and test servers on arena and arenaus. Use whenever the user asks to test something "lokalnie", "headless", "z CLI", "bez mojej ingerencji", "postaw dedyka i połącz się", to check a UI change on screen, or to verify networking, ranked/auth, WebRTC or web build changes before a release. Also for gameplay logic (dropping, picking up, inventory, buying, bots, physics) - "przetestuj", "stestuj sobie", "sprawdź czy działa w grze".

2 projects use a version of this

1.7k18d agoReviewMountCreate a free account to mount
dotnetSkill

review-testing

dotnet/orleans/.github/skills/review-testing/SKILL.md

Testing lens for Orleans — spec-derived oracles, example tests, Accordant model-based tests, CsCheck property-based tests, deterministic simulation with controlled time, fault injection, and Verify snapshots. Use during code review, and when planning or writing tests.

6 projects use a version of this

11k13d agoReviewMountCreate a free account to mount
OrchardCMSSkill

orchardcore-unit-test

OrchardCMS/OrchardCore/.agents/skills/orchardcore-unit-test/SKILL.md

Writes and runs OrchardCore tests — xUnit unit tests, SiteContext-based integration tests, Moq mocking, and Playwright functional tests. Use when the user needs to add a test, set up a test harness/tenant for tests, mock OrchardCore services, or run the test suite.

No other project uses it yet

8.2k29d agoReviewMountCreate a free account to mount
bklitSkill

unit-tests

bklit/bklit-ui/.agents/skills/unit-tests/SKILL.md

Guardrails for adding unit tests in bklit-ui without over-testing. Use when the user mentions unit test, unit tests, tests, test coverage, add tests, write tests, vitest, jest, or asks whether something should be tested.

Often used withauto-perf-optimizechat-customizations-editorcomponent-fixtures

1.9k15d agoReviewMountCreate a free account to mount
SentrySkill

test-guidelines

getsentry/sentry-react-native/.agents/skills/test-guidelines/SKILL.md

Enforce Sentry React Native SDK test conventions for naming, structure, mocking, and fixtures with Jest. Use when writing tests, adding tests, modifying tests, reviewing test code, fixing failing tests, adding coverage, TDD, test-first / red-green, reproducing bugs with tests, regression tests, or test refactoring in `packages/core`.

1.8k2mo agoReviewMountCreate a free account to mount
dotnetReads credentialsSkill

standalone-test-repro

dotnet/runtime/.github/skills/standalone-test-repro/SKILL.md

Generate a standalone console application under artifacts/tmp from a managed test under src/tests so it can be run directly with corerun. USE FOR: "create a standalone repro for this runtime test", converting a CoreCLR test wrapper path such as JIT/.../TestName.cmd into a console app, or extracting a fully qualified xUnit test method from a merged test assembly, including when a CI scenario such as jitstress1 is specified. DO NOT USE FOR: adding a regression test to src/tests, library tests under src/libraries, NativeAOT-only tests, or tests whose behavior fundamentally requires a native, browser, mobile, multi-process, or external-service harness.

18k2y agoReviewMountCreate a free account to mount
clawdbotSkill

openclaw-testing

clawdbot/clawdbot/.agents/skills/openclaw-testing/SKILL.md

Choose proportional OpenClaw tests/checks, diagnose failures, route environment-sensitive or release proof to its owner.

Often used withdiscord-e2eauto-qaproof-video

394k14d agoReviewMountCreate a free account to mount
esphomeSkill

component-tests

esphome/esphome/.agents/skills/component-tests/SKILL.md

Write and run tests for ESPHome components - YAML build tests (test.*.yaml, validate.*.yaml, common.yaml) under tests/components, shared bus packages and CI test grouping, C++ gtest unit tests, and host integration tests including the uart_mock fixture. Use when adding or changing files under tests/, or when a code change needs test coverage.

12k7d agoReviewMountCreate a free account to mount
dotnetSkill

verify-tests-fail-without-fix

dotnet/maui/.github/skills/verify-tests-fail-without-fix/SKILL.md

Verifies tests catch the bug. Auto-detects test type (UI tests, device tests, unit tests) and dispatches to the appropriate runner. Supports two modes - verify failure only (test creation) or full verification (test + fix validation).

23k16d agoReviewMountCreate a free account to mount
SimonHalvdanssonSkill

testing-setup

SimonHalvdansson/Harmonic-HN/.agents/skills/testing-setup/SKILL.md

Analyze and create a testing strategy for Android apps - install testing

3 projects use a version of this

1k17d agoReviewMountCreate a free account to mount
dotnetSkill

tests

dotnet/android/.github/skills/tests/SKILL.md

Runs, discovers, or recommends dotnet/android tests. Handles standalone tests (plain dotnet test), full-build tests (local SDK required), and on-device MTP/NUnit tests. Maps source files to relevant test suites. Trigger on test execution requests, questions about available tests, or "which tests should I run for this change?"

2.1k11d agoReviewMountCreate a free account to mount
apacheSkill

review-testing

apache/pinot/.claude/skills/review-testing/SKILL.md

Review Apache Pinot regression coverage and test quality when behavior or tests change.

6 projects use a version of this

6.2k2mo agoReviewMountCreate a free account to mount
udecodeSkill

test-audit

udecode/plate/.agents/skills/test-audit/SKILL.md

Audit existing tests for low-value, duplicated or implementation-coupled cases and the test-only code they keep alive, then remove or rewrite them on evidence. /test-audit full covers the whole suite and also lists public contracts no test guards. Use for test-audit, /test-audit <scope>, /test-audit full, a test sweep, or pruning tests. Not for writing a new test; the project's Tests rule gates that.

Cooling6 mentions in 2 weeks

80 projects use a version of this

17k9d agoReviewMountCreate a free account to mount
Galaxy-DawnSkill

webapp-testing

Galaxy-Dawn/claude-scholar/skills/webapp-testing/SKILL.md

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Often used withacademy-guideskill-shareintelligent-routing

5.9k7mo 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.