test-evidence-review

Evaluate test files and evidence documents for assertion coverage and completeness.

Updated Mar 26, 2026

Search Tags:#documentation #qa #verification #sign-off #evidence-review #test-review #assertion-coverage

Ready to run

npx skills add https://github.com/LordKuper/agentic-game-studio --skill test-evidence-review-lordkuper

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: test-evidence-review
Source: https://github.com/LordKuper/agentic-game-studio/tree/main/.claude/skills/test-evidence-review
Command: npx skills add https://github.com/LordKuper/agentic-game-studio --skill test-evidence-review-lordkuper

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Quality review of test files and manual evidence documents. Goes beyond existence checks — evaluates assertion coverage, edge case handling, naming conventions, and evidence completeness. Produces ADEQUATE/INCOMPLETE/MISSING verdict per story. Run before QA sign-off or on demand.

Core Features & Use Cases

Evaluate assertion coverage across test files and evidence documents.
Detect edge cases, naming quality, and completeness gaps in evidence.
Produce per-story verdicts (ADEQUATE / INCOMPLETE / MISSING) for QA workflows.

Quick Start

Invoke test-evidence-review on a story or sprint to generate a verdict and a structured 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 automate QA sign-off by reviewing test assertion coverage and evidence?▼

Automating QA sign-off involves evaluating assertion coverage, edge cases, naming conventions, and evidence completeness to produce per-story ADEQUATE, INCOMPLETE, or MISSING verdicts. This structured review workflow runs before final approval or on demand across single stories, sprints, or system-wide scopes.

What is an ADEQUATE, INCOMPLETE, or MISSING verdict in test evidence review?▼

A test evidence review verdict classifies per-story quality as ADEQUATE, INCOMPLETE, or MISSING based on evaluated assertion coverage and evidence completeness. It extracts these structured verdicts to generate a reproducible QA workflow report for sprint or system-wide sign-off.

How do I evaluate edge case handling and naming conventions in test files?▼

Evaluating edge case handling and naming conventions requires reviewing test files for completeness gaps and assertion quality. This process detects missing edge cases and naming inconsistencies, generating a structured report that highlights areas needing correction before QA sign-off.

Can I perform a sprint-level test evidence review for multiple stories?▼

Yes, test evidence review applies to single-story, sprint, or system-wide QA scopes. It evaluates assertion coverage and evidence completeness across multiple stories, extracting individual ADEQUATE, INCOMPLETE, or MISSING verdicts to generate a comprehensive structured report.

Does test evidence review work with manual evidence documents as well as automated test files?▼

Test evidence review works with both automated test files and manual evidence documents. It goes beyond existence checks by evaluating assertion coverage, edge case handling, and evidence completeness to produce structured per-story verdicts for QA workflows.

Why does my QA evidence review report show INCOMPLETE verdicts for stories with existing test files?▼

QA evidence review shows INCOMPLETE verdicts when test files exist but lack sufficient assertion coverage, miss edge cases, violate naming conventions, or have evidence completeness gaps. It evaluates quality beyond mere file existence to ensure rigorous sign-off standards.