test-evidence-review

Review test files and evidence to determine QA sign-off readiness.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/dawn840705/claude-code-game-studios --skill test-evidence-review-dawn840705
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: test-evidence-review
Source: https://github.com/dawn840705/claude-code-game-studios/tree/main/skills/test-evidence-review
Command: npx skills add https://github.com/dawn840705/claude-code-game-studios --skill test-evidence-review-dawn840705

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

QA teams often rely on scattered test and evidence documents; this skill provides a structured, automated review of test files and manual evidence to ensure coverage, completeness, and readiness for sign-off.

Core Features & Use Cases

  • Parse a single story and extract Type, Test Evidence, acceptance criteria, and evidence paths
  • Review automated tests for assertion coverage, edge-case handling, and naming quality
  • Review manual evidence for criterion linkage, sign-offs, and freshness
  • Produce a per-story verdict (ADEQUATE, INCOMPLETE, MISSING) and an overall sprint/system verdict

Quick Start

Run the /test-evidence-review sprint command to start a sprint-wide evidence quality check.

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 evidence and determine QA sign-off readiness for a sprint?

Review test evidence by parsing stories to locate test files, evaluating assertion coverage, edge cases, and sign-offs, then generating per-story and overall sprint verdicts of ADEQUATE, INCOMPLETE, or MISSING for release readiness.

What is test evidence review and how does it evaluate story quality?

Test evidence review is a structured process that evaluates automated tests for assertion coverage, edge-case handling, and naming quality, while checking manual evidence for criterion linkage and freshness to produce a readiness verdict.

Can I audit assertion coverage and edge cases across an entire epic or system scope?

Yes, the review applies to single-story reviews, sprint-wide audits, and epic or system scopes, parsing evidence paths and acceptance criteria to report an overall sprint or system verdict.

How do I identify incomplete or missing test evidence before a release?

Identify incomplete or missing test evidence by running an automated audit that checks manual evidence for criterion linkage and freshness, assigning an INCOMPLETE or MISSING verdict to stories lacking sufficient assertion coverage.

Do I need specific test frameworks to run a QA evidence and story quality check?

No specific test frameworks are required as dependencies; the review parses existing test files and manual evidence documents directly to evaluate assertion coverage, edge cases, and sign-offs.

What's the best way to evaluate manual evidence linkage and freshness for QA sign-off?

The best way is to use an automated evidence review that parses manual evidence documents, checks them for acceptance criterion linkage, verifies freshness, and reports gaps to determine sign-off readiness.