← ClaudeAtlas

run-testplanlisted

Run every test case in a TESTPLAN. Use when the user asks to run a testplan, execute tests, verify a story, or work with a testplan file under the project's testplans folder. Runs each TC's Command verbatim, marks PASS/FAIL, and auto-files BUG-YYYYMMDD-NN files for every failure before reporting in chat.
DATA-AI-XYZ/Tandem · ★ 0 · AI & Automation · score 70
Install: claude install-skill DATA-AI-XYZ/Tandem
# Tandem: run-testplan (QA hat) Operate as **QA hat**. A story has flipped to `in-review` and its paired testplan needs verification. ## Pre-flight — refuse loudly if the kit isn't wired Before running any TC, run the cheap wiring gate: `node _00-Project-Management/93-Scripts/doctor.js --gate` (npm: `npm run pm:doctor -- --gate`). It is **silent on success**; on an unwired project it exits non-zero and prints one line — **kit not wired — run `npm run pm:install`**. If it fails, **refuse and surface that message verbatim** rather than proceeding — a mis-wired kit must fail loudly, not silently no-op. (STORY-12.2.03) ## Inputs needed - Testplan file path — resolve the `testplans` folder via the path map (`node _00-Project-Management/93-Scripts/lib/pm-paths.js resolve testplans`; the config is `90-Standards/pm-paths.json`), then glob for `EPIC-NN/FEAT-NN.M/TESTPLAN-NN.M.PP-*.md` under it. (E.g., it resolves to `05-Test` in a flattened layout.) - If the user didn't supply it, infer from a recently-completed story or ask. ## Load into context Folder locations are resolved through the path map (`pm-paths.js` / `pm-paths.json`) rather than hardcoded, ensuring consistent references across all skills. Use the resolver script to determine physical folders for logical roles such as stories, testplans, bugs, and templates. If NONE of the candidates exist for a given role, note it in the output (don't fabricate scaffolding) and degrade gracefully. - **Testplan file** — at the reso