skills.rest
DATA-AI-XYZ
DATA-AI-XYZOFFICIAL
Explore all skills by this author →
GitHub

run-testplan

Executes every test case in a TESTPLAN file and files bug reports for failures.

Updated May 25, 2026
Search Tags:#markdown#qa#claude code#verification#test execution#bug filing#testplan
One-click install
npx skills add https://github.com/DATA-AI-XYZ/Tandem --skill run-testplan-data-ai-xyz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: run-testplan
Source: https://github.com/DATA-AI-XYZ/Tandem/tree/main/skills/run-testplan
Command: npx skills add https://github.com/DATA-AI-XYZ/Tandem --skill run-testplan-data-ai-xyz

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Verifying a story against its testplan manually is error-prone: commands get improvised, failures get reported in chat but never tracked, and sign-off happens without evidence. This Skill runs every test case verbatim, records PASS/FAIL results in the testplan file, and automatically files a BUG markdown file for each failure so nothing slips through. ## Core Features & Use Cases - Verbatim test execution: Runs each TC's Command exactly as written, compares output to the Expected line, and updates the Result line with a dated PASS or a linked bug reference. - Automatic bug filing: On any failure, immediately creates a BUG-YYYYMMDD-NN markdown file from the BUG template with repro steps, environment snapshot, and fix direction before reporting in chat. - Status lifecycle management: Flips the testplan from not-started to in-progress to done, updates the Sign-off section, and recommends closing the story when all tests pass. - Use Case: A story has moved to in-review and its paired TESTPLAN-NN.M.PP file needs verification. Invoke the Skill to run all test cases serially, file bugs for the two failures found, and hand the bug list to the dev for fixes. ## Quick Start Run the testplan for the story currently in review and file bugs for any failing test cases.

Frequently Asked Questions about run-testplan

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a testplan against a story in review?▼

Invoke the run-testplan Skill with the testplan file path, or let it infer the testplan from a recently completed story. It resolves the testplans folder via the path map, runs each test case command verbatim, and updates each Result line with PASS or a linked bug.

What happens when a test case fails during a testplan run?▼

The Skill immediately files a BUG-YYYYMMDD-NN markdown file using the BUG template, including repro steps, environment snapshot, and a suggested fix direction. The failed test case's Result line links to that bug, and the testplan stays in-progress until fixes are verified.

Can I batch multiple test cases into one test runner invocation?▼

Yes, batching is allowed when test cases share a runner, such as one jest --testPathPattern call, as long as per-file PASS/FAIL output keeps each Result line attributable. Batching across different runners like jest plus Playwright is not permitted.

Why does the testplan run refuse to start on my project?▼

The Skill runs a pre-flight wiring gate via doctor.js --gate before any test case. If the project kit is not wired, it exits non-zero and the Skill refuses to proceed, surfacing the message to run npm run pm:install first.

What if a test failure is caused by a wrong expected value rather than a code bug?▼

When the failure indicates the acceptance criteria or Expected line is wrong, the Skill files an ADR documenting the spec correction instead of a BUG. The ADR linked from the test case Result line serves as the resolution, and both are never filed for the same root cause.

Related Skills

Explore More Software Engineering Skills→
AiFirstDevelopmentAiFirstDevelopment

history

Lists every change planned through the quorum pipeline from docs/work/ and git history.

Community
Intermediate
SynkraAISynkraAI
3.1k

aiox-apply-qa-fixes

Applies QA gate findings to a story and hands back for re-review.

Official
Intermediate
HelloWorldSunginHelloWorldSungin

wiki-lint

Run lint checks on Obsidian-like vaults and output a structured health report.

Community
Intermediate
coreymaypraycoreymaypray
1

workflow-optimizer

Analyze CI/CD pipelines and test suites to identify bottlenecks and propose optimizations.

Community
Advanced