القائمة
Classify failing tests as flaky vs. real regressions and propose a next step for each. Invoke when the user pastes failing test output, asks to triage CI failures, or asks "are these tests flaky".
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Scaffold a new HTTP handler with service function, store method (if needed), and table-driven test, following the project's internal/{api,service,store} layout. Invoke when the user asks to add an endpoint, handler, or route.
Scaffold a new API endpoint with request/response Pydantic schemas, service function, route handler, and a pytest test — following the project's layered layout. Invoke when the user asks to add an endpoint, route, or API method.
Scaffold a new React component with matching test file and consistent folder layout, following the project's conventions in src/features or src/components. Invoke when the user asks to create, scaffold, or add a new component.
Write React Testing Library tests for an existing component, following the project's RTL conventions (prefer role/label queries, mock at network boundary, no act()). Invoke when the user asks to test, add tests for, or cover a component.
Run this repo's documentation and shell quality gates (shellcheck, markdownlint, lint-claude-md) the same way CI runs them. Invoke before opening a PR, or when the user asks to lint, validate, or pre-flight the docs.
Generate or update CHANGELOG.md with an entry for the unreleased changes since the last git tag. Invoke when the user asks to cut a release, update the changelog, or summarize changes since v-something.
| name | test-triage |
| description | Classify failing tests as flaky vs. real regressions and propose a next step for each. Invoke when the user pastes failing test output, asks to triage CI failures, or asks "are these tests flaky". |
| allowed-tools | Bash(git log:*), Bash(git blame:*), Read, Grep, Glob |
Given a batch of failing tests, classify each and propose one concrete action per test.
Prefer in this order:
git log -5 --follow <test-file> and the same for the implementation. Look for changes in the last ~24h or the last PR.A table, one row per failing test:
| Test | Classification | Likely cause | Proposed action |
|---|
Then, below the table, list the tests ranked by fix-first priority (real regressions > stale tests > environmental > flaky-with-high-frequency > low-frequency flakes).
unknown and say what you'd need.