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.
AnthropicSkillanthropics/knowledge-work-plugins/finance/skills/sox-testing/SKILL.md
Generate SOX sample selections, testing workpapers, and control assessments. Use when planning quarterly or annual SOX 404 testing, pulling a sample for a control (revenue, P2P, ITGC, close), building a testing workpaper template, or evaluating and classifying a control deficiency.
alfredobs97Skillalfredobs97/flutter_agentic_template/.agents/skills/testing/SKILL.md
Covers the testing pattern for every layer — domain (package:test with a hand-written Fake data provider, no mocktail), data (an ephemeral real instance or a mocked client), ui Cubit/BLoC (blocTest + mocktail against the domain repository), ui widgets (the pumpApp helper), and router tests (a fresh buildAppRouter() per test); triggers whenever a test is being written for a new entity, provider, repository, Cubit/BLoC, widget, or route.
alumpeSkillalumpe/skills/testing/SKILL.md
Guides risk-based selection and clear construction of useful automated tests. Use when deciding whether code needs tests or when creating, modifying, debugging, or reviewing automated tests.
anipy1Skillanipy1/claude-flutter-kit/.claude/skills/testing/SKILL.md
Unit, bloc, widget, and integration testing conventions — bloc_test, mocktail, http_mock_adapter, test naming, and what to test. Use when writing or fixing any test, mocking a dependency, or deciding what tests a change requires.
anurag-azureSkillanurag-azure/skills/testing/SKILL.md
Application test strategy: unit, slice, and integration testing; coverage targets; test data; mocking discipline. Framework resolved from the TSA.
bmarshall511Skillbmarshall511/Trellis/.claude/skills/testing/SKILL.md
Use when writing tests, deciding what to test, reviewing test coverage, or verifying that a spec's acceptance criteria are actually covered. Also when a test is failing and the fix is unclear.
davidmarcombesSkilldavidmarcombes/skills/skills/python/testing/skill.md
skill_name: pytest_testing_guide version: 1.0.0 tags: [testing, pytest, quality, tdd] --- # Pytest Testing Guide ## Core Principles 1. **Use pytest exclusively** - not unittest or nose 2. **Organize tests by concern
dewitt4Skilldewitt4/claude-code-template/.claude/skills/testing/SKILL.md
Generate comprehensive test cases, improve test coverage, and create testing strategies for unit, integration, and e2e tests
Geoffe-GaSkillGeoffe-Ga/well-worn-tools/.claude/skills/testing/SKILL.md
Write comprehensive, maintainable tests following TDD and AAA pattern. Use when writing unit tests, integration tests, setting up fixtures, mocking dependencies, or improving test coverage. Covers Python (pytest), TypeScript (Jest), Go (testing), and Rust (built-in + proptest). Do NOT use for mutation testing specifics (use mutation-testing skill).
hallucinautSkillhallucinaut/skills/testing/SKILL.md
Write unit tests, integration tests, and end-to-end tests. Use when implementing test suites, improving coverage, or ensuring code quality through testing.
irwebtoolsSkillirwebtools/Product-Skills/skills/optional/testing/SKILL.md
Plan and record checks and acceptance journey evidence for React FSD work.
LeostrukaSkillLeostruka/devin-bundle/skills/testing/SKILL.md
Use when implementing any feature or bugfix and a test-driven approach is appropriate (red-green-refactor, seams-first), or when the user asks to find testing gaps, mutation test, or identify surviving mutants.
Lion-1209SkillLion-1209/dsh-plugin-lion-skills/skills/testing/SKILL.md
需为代码写测试或改进脆弱测试时。
muxammadmamajonovSkillmuxammadmamajonov/dot-claude/.claude/skills/testing/SKILL.md
Use when defining a test strategy, choosing layers, raising meaningful coverage, or fixing flaky suites — write tests with the feature, failing test first for bugs, QA audit before launch.
ReaperOAKSkillReaperOAK/ForgeOS/.claude/skills/testing/SKILL.md
Testing best practices including unit testing, integration testing, E2E testing with Playwright, and test writing guidelines for TypeScript.
swapnil-saalSkillswapnil-saal/agentic-react-starter/.claude/skills/testing/SKILL.md
How to test in this repo — the verification loop, the four unit-test archetypes, MSW mock handlers, and Playwright e2e. Use when writing or fixing any test, adding a mock endpoint, or deciding whether a change is adequately covered.
swift-instituteSkillswift-institute/Skills/testing/SKILL.md
Design, structure, and place Swift Institute tests and benchmarks — suite shape, nested test packages, snapshot tests, Swift Testing framework traps, and executable benchmark mechanics. Apply whenever writing, restructuring, or reviewing tests or performance measurement.
syntropic137Skillsyntropic137/harness-app-template/.claude/skills/testing/SKILL.md
Use when reviewing testing concerns: pyramid coverage (unit, integration, E2E), test code quality, TDD discipline, regression discipline, FIRST principles, feedback-loop speed
syntropic137Skillsyntropic137/software-leverage-points/skills/testing/SKILL.md
Use when reviewing testing concerns: pyramid coverage (unit, integration, E2E), test code quality, TDD discipline, regression discipline, FIRST principles, feedback-loop speed
Talktodre-opsSkillTalktodre-ops/claude-skills/testing/SKILL.md
How to test a full-stack app to a shipping bar, distilled from a real recruiter-led SaaS. Covers the test layers (unit, integration, contract, end-to-end, smoke, regression, security, performance, accessibility), what to run per change versus per release, the cross-viewport visual discipline (mobile, tablet, desktop, wide), the "verify for real" principle that a passing type-check is not a passing feature, hermetic stubbed e2e, tenant-isolation as a standing regression gate, and the file-upload and authorization security checks that keep a multi-tenant app safe. Load when writing tests, setting up a test harness, deciding what to verify before a commit, or reviewing whether a change is actually safe to ship. Fetch current framework docs with Context7 rather than from memory.
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 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.
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.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
