Skills real projects publish on GitHub, most starred first. Each one says what it will make an agent do before you copy it.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
prowler-cloudReads credentialsSkillprowler-cloud/prowler/skills/prowler-test-api/SKILL.md
Testing patterns for Prowler API: JSON:API, Celery tasks, RLS isolation, RBAC. Trigger: When writing tests for api/ (JSON:API requests/assertions, cross-tenant isolation, RBAC, Celery tasks, viewsets/serializers).
Steady14 mentions in 2 weeks
No other project uses it yet
redisDeletes or force-pushesSkillredis/node-redis/.agents/skills/bump-test-image/SKILL.md
Bump the default Redis docker test image (redislabs/client-libs-test) in the shared DEFAULT_DOCKER_CONFIG and the CI matrix, then force-push the bump-test-image branch and open a PR against upstream. User-invoked only.
No other project uses it yet
mastra-aiReads credentialsSkillmastra-ai/mastra/.agents/skills/testing-core-processors/SKILL.md
Use when writing or debugging integration tests for error processors in packages/core/src/processors/. Covers the MockLanguageModelV2 pattern for simulating API errors and verifying retry behavior, plus the build prerequisites for focused vitest runs.
trpcSkilltrpc/trpc/.agents/skills/tdd/SKILL.md
Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.
Surging4 mentions in 2 weeks
194 projects use a version of this
Often used withcapture-learning-toolsketchup-videofigure-it-out
handsontableSkillhandsontable/handsontable/.claude/skills/handsontable-demo-page/SKILL.md
Use when creating a demo or test page for manual testing of Handsontable. Trigger when the user asks to create a demo, test page, repro page, reproduction case, manual test, or wants to verify a bug fix or feature visually. Also trigger when the user mentions dev-generated.html, dev-pr.html, dev-latest.html, dev.html, or wants to compare behavior between a released version and a local build. Use this for any PR that needs a manual testing artifact.
dotnetSkilldotnet/roslyn/.github/skills/run-toolset-tests/SKILL.md
Run the razor-toolset-ci pipeline to validate the current branch against large third-party repositories (MudBlazor, OrchardCore, ASP.NET Core, etc.). Use when asked to run toolset tests, ecosystem tests, or third-party validation.
getumbrelSkillgetumbrel/umbrel/.agents/skills/umbreld-vm-test-authoring/SKILL.md
Use this skill when adding, converting, or reviewing umbreld VM tests in the Umbrel repo. It describes the preferred style for clear VM tests that boot umbrelOS and exercise real OS, hardware, storage, networking, and reboot behavior.
Steady2 mentions in 2 weeks
No other project uses it yet
ClickHouseSkillClickHouse/ClickHouse/.claude/skills/create-test-datasets/SKILL.md
Create test datasets (hits, visits, tpcds, tpch) from standard scripts. Ensures the server is running first.
elie222Skillelie222/inbox-zero/.claude/skills/e2e/SKILL.md
Run and debug E2E flow tests. Use when triggering E2E tests, checking test status, debugging failures with Axiom logs, or setting up local E2E testing.
Steady10 mentions in 2 weeks
50 projects use a version of this
mozilla-firefoxSkillmozilla-firefox/firefox/.agents/skills/perftest/SKILL.md
Run Firefox performance tests locally or in CI. Use when the user asks how to run a perf test, needs the mach invocation for Raptor, Talos, MozPerftest, AWSY, or browsertime, wants to push perf tests to try, wants to run the tests belonging to an alert summary (`mach try perf --alert <id>`), or mentions `mach try perf`, `mach perftest`, `mach raptor`, or `mach talos-test`. Covers picking the right harness, finding a test's name, and the local-vs-CI tradeoff. Not for triaging or root-causing a Perfherder regression bug — confirming whether a regression is real, identifying the culprit patch, interpreting a PerfCompare result, or deciding backout vs fix-forward (use perf-regression-triage). Not for analyzing an existing Firefox profile (use profiler-analysis) or SpiderMonkey/JS engine benchmarking (use js-perf-investigation).
dubincSkilldubinc/dub/.agents/skills/playwright-api-tests/SKILL.md
Add or extend Playwright HTTP API specs under apps/web/playwright/api using the shared api/workspace fixtures and Bearer auth from globalSetup. Use when writing Playwright API tests, e2e API specs, or testing /api routes with the api project (not Vitest under apps/web/tests, not browser UI e2e).
No other project uses it yet
HashiCorpSkillhashicorp/terraform-provider-aws/.agents/skills/review-tests/SKILL.md
Review Terraform AWS Provider acceptance and unit test basics: required _basic and _disappears tests, TestAcc naming, TestCase essentials (PreCheck/ErrorCheck/ProtoV5ProviderFactories/CheckDestroy), random naming, ImportState steps, and regexache. Use when reviewing a PR that changes internal/service/**/*_test.go.
steipeteReads credentialsSkillsteipete/CodexBar/.agents/skills/qa-test/SKILL.md
CodexBar live QA/e2e testing: run provider usage matrix checks, validate real app config, use Peekaboo for menu proof, use Browser Use/official docs for API spec or logged-in dashboard checks, and handle 1Password credentials safely.
Surging2 mentions in 2 weeks
2 projects use a version of this
PrefectHQSkillPrefectHQ/fastmcp/.agents/skills/python-tests/SKILL.md
Write regression tests for FastMCP changes using its pytest fixtures, in-memory clients, and protocol boundaries.
bitwardenSkillbitwarden/clients/.claude/skills/writing-end-to-end-tests/SKILL.md
Write and run Playwright end-to-end tests in `e2e/` for the web vault, browser extension and desktop app. The suite is a key-management internal experiment. Use only when already working in `e2e/`, not to start a test suite elsewhere.
GoogleSkillgoogle/A2UI/.agents/skills/a2ui-test-quality-check/SKILL.md
Auditing test suites for assertion utility, boundary cases coverage, and verification strength.
kieranklaassenSkillkieranklaassen/compound-engineering-plugin/skills/ce-test-xcode/SKILL.md
Test iOS apps in a simulator with XcodeBuildMCP. Use when iOS changes need simulator evidence before handoff.
4 projects use a version of this
apacheSkillapache/tvm/.agents/skills/tir-test/SKILL.md
Run TVM's in-tree TIRx tests and tirx-kernels import and correctness checks.
leonardomsoSkillleonardomso/33-js-concepts/.claude/skills/test-writer/SKILL.md
Generate comprehensive Vitest tests for code examples in JavaScript concept documentation pages, following project conventions and referencing source lines
prowler-cloudReads credentialsSkillprowler-cloud/prowler/skills/prowler-test-mcp/SKILL.md
Testing patterns for the Prowler MCP Server: in-memory FastMCP clients, the ProwlerAPIClient singleton, JSON:API model builders and mocked httpx transports. Trigger: When writing tests under mcp_server/tests/ (tools, models, api_client, auth, sub-servers).
Steady14 mentions in 2 weeks
No other project uses it yet
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Open a skill to see its discussion. Reports from people and their agents are coming.
