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 18Worked for most · soon
zed-industriesSkill

lint-creator

zed-industries/zed/.agents/skills/lint-creator/SKILL.md

Add, modify, or test a custom dylint lint in `tooling/lints`. Covers the module/registration layout, UI test conventions (including negative tests and the gpui test fixture), how to run tests with the crate's pinned nightly and update `.stderr` files, and how to validate a lint against the real codebase with `single-lint`. Use whenever the user asks to write a new lint or debug an existing one.

1 project uses a version of this

95k49d agoReviewMountCreate a free account to mount
TriliumNextSkill

writing-unit-tests

TriliumNext/Trilium/.claude/skills/writing-unit-tests/SKILL.md

Use when writing, extending, or debugging Vitest unit tests anywhere in the Trilium monorepo — Preact components, jQuery widgets, client services, or the server/trilium-core backend. Covers how to render components (zero new deps), the easy-froca/becca fixtures, supertest API patterns, the honest coverage config, running a single test, and the known gotchas.

Steady11 mentions in 2 weeks

5 projects use a version of this

39k26d agoReviewMountCreate a free account to mount
reflex-devDeletes or force-pushesSkill

prerelease-test

reflex-dev/reflex/.claude/skills/prerelease-test/SKILL.md

Run the independent pre-release QA campaign for a Reflex release train. Discovers what shipped by reading every CHANGELOG.md on the pre-release branch, checks each package actually published to PyPI, then exercises the new features end-to-end in real apps driven by a real browser using ONLY published packages, upgrade-tests reflex-examples apps from the previous stable, regression-tests reflex-enterprise demos, audits wheel/sdist packaging, and produces a triaged FINDINGS.md plus a fix-before-release plan. Use this whenever a Reflex release is being prepared or checked — the user mentions a pre-release, an alpha/beta/rc, an `r/pre-*` branch, "about to release", release QA, validating a release candidate, or re-verifying that release-blocking fixes landed in a newer alpha. Also use it for the narrower slices on their own: smoke-testing published packages, upgrade/regression testing example apps against a new version, or auditing that packages ship their `.pyi` stubs in both wheel and sdist.

Steady2 mentions in 2 weeks

No other project uses it yet

29k5mo agoReviewMountCreate a free account to mount
usestrixSkill

application-security-testing

usestrix/strix/skills/application-security-testing/SKILL.md

Application security testing (AppSec) across a whole product with Strix — decide which asset needs which test (source code, running web app, API, CI pipeline), run it, and turn the results into a ranked remediation plan. Autonomous agents exploit and prove each issue instead of emitting static-analysis alerts, so the plan is ordered by what is actually reachable. Use when the user asks for an application security review or audit, an appsec assessment, vulnerability scanning across their stack, a security review before a launch or a customer security questionnaire, or does not yet know which kind of security test they need.

Steady4 mentions in 2 weeks

3 projects use a version of this

76k9mo agoReviewMountCreate a free account to mount
mesherySkill

gen-test

meshery/meshery/.agents/skills/gen-test/SKILL.md

Generate idiomatic tests for Go packages and handlers in the Meshery project.

12k3mo agoReviewMountCreate a free account to mount
molt-botSkill

openclaw-test-heap-leaks

molt-bot/clawdbot/.agents/skills/openclaw-test-heap-leaks/SKILL.md

Investigate OpenClaw pnpm test memory growth, Vitest OOMs, RSS spikes, and heap snapshot deltas.

Steady5 mentions in 2 weeks

14 projects use a version of this

395ktodayReviewMountCreate a free account to mount
gravitationalSkill

flaky-test

gravitational/teleport/.claude/skills/flaky-test/SKILL.md

Run when the user asks to investigate, troubleshoot, or fix a flaky Go test.

21k4mo agoReviewMountCreate a free account to mount
JetBrainsReads credentialsSkill

conda-env-tests

JetBrains/intellij-community/.agents/skills/conda-env-tests/SKILL.md

Bump the pinned Miniconda version for the Python conda env tests.

21k3d agoReviewMountCreate a free account to mount
JetBrainsReads credentialsSkill

conda-env-tests

JetBrains/intellij-community/.claude/skills/conda-env-tests/SKILL.md

Bump the pinned Miniconda version for the Python conda env tests.

21k3d agoReviewMountCreate a free account to mount
LMCacheSkill

lmcache-p2p-test

LMCache/LMCache/.claude/skills/lmcache-p2p-test/SKILL.md

Test a running LMCache P2P deployment: cross-node correctness (basic_test), stress ladder (concurrency, long documents, sustained mixed load), the standard lmcache bench long-doc-qa across nodes, and live Prometheus monitoring with a results summary. Use when asked to verify, stress, benchmark or monitor P2P KV sharing or to produce a P2P test report.

Steady3 mentions in 2 weeks

No other project uses it yet

12k4d agoReviewMountCreate a free account to mount
appsmithorgSkill

fix-pw-spec

appsmithorg/appsmith/.agents/skills/fix-pw-spec/SKILL.md

Fix a failing Playwright spec by analyzing error output, identifying the root cause in the test code, and applying corrections. Use when a Playwright test fails due to wrong selectors, bad waits, incorrect assertions, or code errors. Trigger phrases: "fix this playwright test", "this spec is failing", "playwright test broken", "fix the flaky test".

Steady6 mentions in 2 weeks

No other project uses it yet

41k21d agoReviewMountCreate a free account to mount
prowler-cloudReads credentialsSkill

prowler-test-ui

prowler-cloud/prowler/skills/prowler-test-ui/SKILL.md

E2E testing patterns for Prowler UI (Playwright). Trigger: When writing Playwright E2E tests under ui/tests in the Prowler UI (Prowler-specific base page/helpers, tags, flows).

Steady14 mentions in 2 weeks

No other project uses it yet

15k7mo agoReviewMountCreate a free account to mount
dotnetDeletes or force-pushesSkill

run-device-tests

dotnet/maui/.github/skills/run-device-tests/SKILL.md

Build and run .NET MAUI device tests locally with category filtering. Supports iOS, MacCatalyst, Android on macOS; Android, Windows on Windows. Use TestFilter to run specific test categories.

23k5d agoReviewMountCreate a free account to mount
JetBrainsSkill

minimize-repro-for-diagnostic-test

JetBrains/kotlin/.claude/skills/minimize-repro-for-diagnostic-test/SKILL.md

Makes a minimal reproduction of a Frontend-related bug as a diagnostic test

54k11d agoReviewMountCreate a free account to mount
PostHogSkill

extending-personhog-test-harness

PostHog/posthog/.agents/skills/extending-personhog-test-harness/SKILL.md

When and how to add scenarios, chaos events, and invariants to the personhog e2e test harness (rust/personhog-test-harness). Use after fixing a bug or regression in the personhog leader path (leader, router, writer, replica, coordination protocol) so the fix gets a permanent regression scenario; when adding a new failure mode to test (crashes, drains, zombies, lag, failover); or when a new correctness property needs asserting during runs. Trigger terms: personhog gate, chaos scenario, test harness, leader path regression, handoff bug, eviction, writer lag, acked write.

41k3d agoReviewMountCreate a free account to mount
remotion-devSkill

web-renderer-test

remotion-dev/remotion/.agents/skills/web-renderer-test/SKILL.md

Add explicitly requested web renderer tests or update existing ones for implementation changes.

Steady7 mentions in 2 weeks

No other project uses it yet

73k2d agoReviewMountCreate a free account to mount
Wox-launcherSkill

wox-test-ensurance

Wox-launcher/Wox/.agents/skills/wox-test-ensurance/SKILL.md

Use when the user invokes Wox test assurance or asks to run Wox tests; direct invocation is explicit permission to execute the current core, Go UI unit, and native smoke suites and fix failures until they pass.

No other project uses it yet

28k5d agoReviewMountCreate a free account to mount
comet-mlSkill

explore-feature

comet-ml/opik/.agents/skills/explore-feature/SKILL.md

Use when a developer wants an e2e test covering a change they just made — e.g. "explore this feature", "add a test for my PR", "cover the feature in PR #7303", "test my branch". Reads a ticket + changed code to work out the one flow worth covering, then delegates authoring to writing-e2e-tests, which writes a normal tiered spec under tests/<area>/.

Steady6 mentions in 2 weeks

No other project uses it yet

23k4mo agoReviewMountCreate a free account to mount
MicrosoftSkill

flaky-smoke-tests

microsoft/vscode/.github/skills/flaky-smoke-tests/SKILL.md

Diagnose intermittent VS Code Electron smoke-test failures from the Azure DevOps Flaky Smoke Tests pipeline (definition 700). Covers finding failed iterations, downloading task logs and platform artifacts with Azure CLI, correlating cumulative runner logs, tracing the introducing commit, and queueing focused validation runs.

Steady+17 stars this week

1 project uses a version of this

195k4d agoReviewMountCreate a free account to mount
open-gsdSkill

gsd-add-tests

open-gsd/get-shit-done-redux/skills/gsd-add-tests/SKILL.md

Generate tests for a completed phase based on UAT criteria and implementation

Steady9 mentions in 2 weeks

4 projects use a version of this

12k3mo 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.