test-evidence-review

Evaluate automated tests and manual evidence documents for game story completeness.

Updated May 13, 2026
One-click install
npx skills add https://github.com/FrancisVarga/the-dream-machine --skill test-evidence-review-francisvarga
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: test-evidence-review
Source: https://github.com/FrancisVarga/the-dream-machine/tree/main/.claude/skills/test-evidence-review
Command: npx skills add https://github.com/FrancisVarga/the-dream-machine --skill test-evidence-review-francisvarga

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents stories from moving forward when tests exist only in name or evidence documents are missing required sign-offs, reducing late-stage QA surprises.

Core Features & Use Cases

  • Automated test quality review: Evaluates assertion coverage, edge-case coverage, naming quality, and formula traceability (for Logic stories).
  • Manual evidence quality review: Verifies acceptance-criterion linkage, required sign-offs, artefact completeness (screenshots/walkthroughs), and evidence freshness.
  • Scope-based reporting: Review a single story, an entire sprint, or all stories in an epic/system and produce an ADEQUATE/INCOMPLETE/MISSING verdict.

Quick Start

Run test-evidence-review for a story to generate a quality verdict covering both automated tests and manual evidence documents.

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 and evidence coverage before QA sign-off?

Test quality and evidence coverage reviews evaluate automated assertion coverage, edge-case handling, and manual document linkage against acceptance criteria to generate an ADEQUATE, INCOMPLETE, or MISSING verdict before QA sign-off.

What is assertion coverage evaluation for game story logic?

Assertion coverage evaluation for game story logic verifies that automated tests contain sufficient assertions, trace formulas correctly, and handle edge cases to ensure logic story requirements are fully validated before QA.

How do I check if manual testing evidence meets acceptance criteria?

Checking manual testing evidence involves verifying required sign-offs, confirming acceptance-criterion linkage, and validating artefact completeness such as screenshots or walkthroughs to ensure evidence documents are fresh and valid.

Can I evaluate test evidence across an entire sprint or epic scope?

You can evaluate test evidence across single story, sprint, or system and epic scopes by locating expected evidence through repository scanning and generating a comprehensive quality verdict for the entire batch.

What are the limitations of automated test evidence reviews for UI and config stories?

Automated test evidence reviews for UI and config stories focus primarily on assertion coverage and artefact completeness, meaning complex visual or feel validations may still require manual evidence checks to achieve a fully adequate verdict.