Universal testing framework (frontend + backend) — a meticulous run of any testing task with evidence discipline. Use when you need to test a feature/form/build/API/service, draft a test plan, run checks, perform exploratory or regression testing, or find defects.
Write, review, and debug tests using Vitest. Use for: unit tests, API route tests, executor/serializer/tool tests, jsdom vs node environment selection, shared __test-utils__ patterns, and mandatory code-to-test sync with executed test runs.
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program," or "experiment playbook." Use this whenever someone is comparing two approaches and wants to measure which performs better, or when they want to build a systematic experimentation practice. For tracking implementation, see analytics. For page-level conversion optimization, see cro.
Test user-facing UI with TDD, component tests, a11y checks, and critical-path coverage. Use when writing or fixing UI tests, verifying loading/error/empty states, or when the user mentions test/TDD/coverage/regresi — including natural language, not only /test-ui.
How DAG nodes prove code changes through public interfaces - red before green for new behavior and bug fixes, preservation checks for refactors, and mocks at system boundaries - loaded through load_skills.
Validate and choose proportionate test proof for tests, CI, coverage, evals, and closeout evidence: map changed files to repo-native commands, place checks at commit, push, and pull-request gates, classify pass/fail/blocked ownership, and preserve trace/regression artifacts. Use when users ask what tests or gates to run, how to design coverage, why validation failed, or what proof supports a claim.
Write tests for code. Use when: (1) user asks to write, add, or improve tests; (2) after implementing non-trivial features—propose which tests would add value before writing; (3) user asks to verify a bugfix with a regression test; (4) user wants to understand what tests a change needs.
Design or review testing strategy, test portfolios, and test quality. Use for unit/integration/contract/E2E choices, flaky or brittle tests, mocks and test doubles, BDD review, legacy-code testing, production QA, and testing LLM or AI-generated systems. Also covers TCRDD / TCR (test && commit || revert, red-green-refactor, baby steps, commit on green, revert on failure, approval-gated TDD) and HTTP API smoke tests (smoke test, critical path test, CI gate, Hurl, .hurl files, curl smoke test).
Write tests for E2BGateway. Use when writing unit tests, integration tests, or E2E tests — covers conventions, layer selection, mocks, and race detection.
Write, change, or review Fast Link tests, choose between specs, browser tests, and real app fixtures, or audit and clean up test suites. Use when assessing test value, duplication, reliability, or coverage in this repository.
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.