Testing strategy, patterns, and evaluation for software and LLM/AI systems. Use when: writing tests, choosing test boundaries, designing test data, structuring test suites, evaluating LLM outputs, building evaluation pipelines, setting coverage thresholds, auditing test coverage gaps in existing projects, or improving test quality and structure.
Write, repair, debug, audit or delete automated tests. Use when adding coverage for new behavior, writing a regression test for a defect, fixing a failing or flaky test, choosing the right test level, or auditing a suite's quality. Not for explaining what an existing test does, and not for running a suite as a routine verification step.
Use when writing or reviewing Java tests (JUnit, Mockito, @SpringBootTest, Testcontainers), choosing H2 or a real database for repository tests, testing code that reads the time or waits, splitting fast and slow tests (surefire, failsafe), fixing flaky or order-dependent tests, or seeing "A Java agent has been loaded dynamically". Key rule: JUnit 6 (junit-jupiter.version 6.1.3 over Spring Boot 4.1.1's 6.0.3) and Testcontainers 2 (testcontainers-postgresql, org.testcontainers.postgresql.PostgreSQLContainer); repository tests on the production engine and version (postgres:17), never H2 or a mocked repository; static @Container @ServiceConnection in Spring Boot tests; inject java.time.Clock and use Clock.fixed, never Thread.sleep; each test owns its data, no @TestMethodOrder dependence; *Test in surefire without Docker, *IT in failsafe; Mockito as -javaagent via maven-dependency-plugin properties and argLine @{argLine} -javaagent:${org.mockito:mockito-core:jar}.
Where a repo's test recipes live — TESTING.md at root, per-directory deltas in monorepos, nearest scope wins — and how implementing and shipping skills scope their test runs to a change. Consult before running tests as a spawned agent, filling a workflow's test-notes slot, or setting up a repo's TESTING.md.
Pragmatic testing guidance focused on confidence, behavior over implementation details, and integration-first coverage. Use when designing a test strategy, writing or reviewing tests, reducing brittle mocks, or deciding what is worth testing in an application or library.
Software testing documentation dispatcher. Use when creating, reviewing, or improving test specifications and test documentation. Trigger on: "write test cases", "create a test plan", "test specification", "STS", "TDS", "TCS", "TPS", "test procedure", "define exit criteria", "requirements traceability matrix", "RTM", "risk-based testing", "test environment", "non-functional testing", "accessibility testing", "security testing", "performance testing", "CI/CD test integration", "document how to test this feature", "IEEE 829", or any task producing or reviewing software test documentation.
Design test strategy using Beck's Test Desiderata — which properties matter, which tradeoffs to make. Use when the user asks "how should I test this", "what tests do I need", "review my test strategy", "is this well-tested", or when planning tests for a new feature or refactor.
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.
Steady49 mentions in 2 weeks
No other project uses it yet
34k9mo agoReviewMountCreate a free account to mount
Testing Gloomberb at every level: CLI commands for fast data/integration checks, OpenTUI's built-in test harness for component tests, and tmux for full end-to-end terminal TUI testing. Use this skill when you need to verify terminal TUI features, write OpenTUI regression tests, or smoke-test the terminal app. Do not use it for Electrobun/desktop-web-only visual or window chrome work unless tmux/OpenTUI coverage is explicitly needed.
2.6k29d agoReviewMountCreate a free account to mount
Use when writing or updating Krayin CRM tests (unit or feature), debugging test failures, using datasets, mocks or custom expectations, writing architecture tests, or when the user mentions test, spec, TDD, expects, assertion, or coverage. Uses the Pest PHP framework (v3) with Laravel 12.
Test a change across the surfaces it touches, not only the path just written. Use when starting non-trivial implementation (claims, case grid, seams), when that work is built (attack the grid, keep few durable tests), when fixing a reported defect, and when judging an existing suite. Skip for one-line fixes with an obvious cause, copy or colour changes, and renames.
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.
Guides which automated tests are worth writing and how to write them well. Use when deciding whether code needs tests or when creating, modifying, or reviewing automated tests.
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.
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.
Coverage-driven, discovery-first product testing that operates a real app across risk-driven sessions and multi-session campaigns, maintains complementary product-surface and risk-dimension coverage, uncovers unreported bugs, and independently verifies fixes without changing production code. Use for Quick Exploration, Delta Discovery, systematic Full Discovery Campaigns, Final Broad Testing, Fix Verification / Regression after Builder implementation, Maestro-assisted flows, hardware/device coverage planning, or proactive testing beyond existing unit/UI suites.
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.