skills.rest
claretagrapelike32
claretagrapelike32COMMUNITY
Explore all skills by this author →
GitHub

test-evidence-review

Reviews test files and manual evidence documents for assertion coverage, sign-offs, and completeness.

Updated Aug 2, 2026
Search Tags:#game development#qa#evidence#sign-off#test review#quality audit#assertion coverage
One-click install
npx skills add https://github.com/claretagrapelike32/codex-ai-game-studio --skill test-evidence-review-claretagrapelike32
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: test-evidence-review
Source: https://github.com/claretagrapelike32/codex-ai-game-studio/tree/main/plugins/ai-game-studio/skills/test-evidence-review
Command: npx skills add https://github.com/claretagrapelike32/codex-ai-game-studio --skill test-evidence-review-claretagrapelike32

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? A test file that exists and passes may still leave critical behavior uncovered, and an evidence document may lack required sign-offs. This Skill audits the quality of test files and manual evidence documents per story, producing an ADEQUATE/INCOMPLETE/MISSING verdict before QA sign-off. ## Core Features & Use Cases - Automated Test Quality Review: Evaluates assertion coverage, edge case handling, naming conventions, and formula traceability for Logic and Integration story tests. - Manual Evidence Review: Checks criterion linkage, developer/designer/QA sign-offs, screenshot artefacts, and evidence freshness for Visual/Feel and UI stories. - Structured Verdict Report: Produces a story-by-story report with BLOCKING and ADVISORY issues, plus an overall sprint or system verdict. - Use Case: Before closing a sprint, run the review across all stories to find tests with zero assertions, evidence docs missing QA lead sign-off, or stories with no test file at all. ## Quick Start Ask the AI to run a test evidence review on the current sprint and report which stories have blocking quality gaps.

Frequently Asked Questions about test-evidence-review

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

FAQPage Schema
How do I review test quality before QA sign-off?▼

Run the review on a single story, the current sprint, or a system. It reads each story's test files and evidence documents, evaluates assertion coverage and sign-offs, and returns an ADEQUATE, INCOMPLETE, or MISSING verdict per story.

What makes a test file fail a quality review?▼

A test with zero assertions is flagged as BLOCKING because it passes vacuously. Tests with only 1-2 assertions per function are noted as thin, and generic names like test_1 or testBasic are flagged as naming issues.

What sign-offs are required in a manual evidence document?▼

Evidence documents need developer sign-off, designer or art-lead sign-off for Visual/Feel stories, and QA lead sign-off. Missing or blank sign-offs mark the story INCOMPLETE and prevent closure.

Does this skill modify test files or evidence documents?▼

No. It only reads and evaluates tests and evidence, then reports quality issues. Fixing thin assertions or collecting missing sign-offs is left to the user or other skills.

When should I run a test evidence review?▼

Run it before QA hand-off sign-off, on any story where test quality is in question, or during milestone reviews of Logic and Integration story quality. It complements existence checks that only verify tests pass.

Related Skills

Explore More Software Engineering Skills→
solace-illsolace-ill

test-evidence-review

Evaluate test evidence against acceptance criteria and produce per-story verdicts.

Community
Advanced
Euraika-LabsEuraika-Labs
14

test-evidence-review

Review test files and manual evidence documents for quality and completeness.

Official
Intermediate
imclabimclab
1

test-helpers

Generate engine-specific test helper libraries with assertions, factories, and mocking.

Official
Intermediate
JunnnnyWonJunnnnyWon

test-evidence-review

Review test files and evidence documents to produce ADEQUATE, INCOMPLETE, or MISSING verdicts.

Community
Advanced