test-evidence-review

Audit test evidence and QA documents for coverage, readiness, and traceability.

Updated Apr 22, 2026
One-click install
npx skills add https://github.com/brand6/Claude-Code-Game-Studios-zh-auto --skill test-evidence-review-brand6
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: test-evidence-review
Source: https://github.com/brand6/Claude-Code-Game-Studios-zh-auto/tree/main/.claude/skills/test-evidence-review
Command: npx skills add https://github.com/brand6/Claude-Code-Game-Studios-zh-auto --skill test-evidence-review-brand6

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill performs a structured quality review of test files and manual evidence documents associated with user stories. It goes beyond mere existence checks by assessing assertion coverage, boundary condition handling, naming quality, and evidence completeness to determine ADEQUATE, INCOMPLETE, or MISSING outcomes for each story, typically before QA sign-off or on-demand.

Core Features & Use Cases

  • Load scopes from single stories, current sprints, or system epics and extract test evidence references.
  • Evaluate automated and manual evidence across logical, integration, visual/UX, and UI stories, including coverage for acceptance criteria and traceability to GDD formulas.
  • Produce a structured assessment report and optional evidence-review artifact that highlights gaps and suggested remediation.

Quick Start

Run a sprint audit with the command to review all stories in the active sprint and generate an evidence-review report.

Frequently Asked Questions about test-evidence-review

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

FAQPage Schema
How do I verify test evidence and assertion coverage for user stories before QA sign-off?

Test evidence review audits QA documents and test files to verify assertion coverage, boundary handling, and traceability against acceptance criteria, generating a structured report with ADEQUATE, INCOMPLETE, or MISSING outcomes before sign-off.

What is the best way to audit test readiness across an entire sprint?

Sprint-level test evidence audits load all active stories, parse evidence files, cross-reference acceptance criteria, and flag coverage gaps to produce a comprehensive readiness assessment for the entire sprint.

How does QA evidence review handle traceability to acceptance criteria?

QA evidence review cross-references acceptance criteria with parsed evidence files, evaluating logical, integration, visual, and UI story coverage to ensure traceability and flag any missing or incomplete assertions.

Can I assess test evidence quality for system-level epics, not just single stories?

Yes, evidence review supports scoping at the single story, current sprint, or system-level epic tier, applying the same assertion coverage and naming quality assessments regardless of scope size.

What does a structured evidence-review report include when test coverage gaps are found?

The evidence-review report highlights coverage gaps, flags incomplete or missing evidence, and provides suggested remediation steps alongside the ADEQUATE, INCOMPLETE, or MISSING status for each evaluated story.