test-evidence-review

Review test evidence and produce ADEQUATE, INCOMPLETE, or MISSING verdicts per story.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/CarlosQ96/robot-crawler --skill test-evidence-review
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: test-evidence-review
Source: https://github.com/CarlosQ96/robot-crawler/tree/main/.agents/skills/test-evidence-review
Command: npx skills add https://github.com/CarlosQ96/robot-crawler --skill test-evidence-review

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill helps teams evaluate test quality and evidence completeness beyond mere existence checks, ensuring assertion coverage, edge-case handling, naming quality, and sign-offs to yield a reliable verdict per story.

Core Features & Use Cases

  • Reviews assertion coverage across unit/integration tests and manual evidence
  • Judges edge-case handling, naming quality, and sign-off completeness
  • Produces verdict per story: ADEQUATE / INCOMPLETE / MISSING; supports QA handoffs

Quick Start

Run the /test-evidence-review command on a story or sprint to generate a verdict and actionable improvements.

Frequently Asked Questions about test-evidence-review

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

FAQPage Schema
How do I evaluate test evidence quality for sprint stories?

Evaluating test evidence quality requires reviewing assertion coverage, edge-case handling, naming quality, and sign-offs to yield a reliable verdict of ADEQUATE, INCOMPLETE, or MISSING per story.

What is test evidence review in QA?

Test evidence review is assessing assertion coverage across unit, integration, and manual tests to verify logic, integration, visual feel, UI, and config/data stories within a sprint.

How do I check assertion coverage and edge-case handling for user stories?

Check assertion coverage and edge-case handling by applying a QA-grade review to the test evidence of each story, verifying that all critical paths and boundaries are explicitly asserted.

Can I generate QA sign-offs and verdicts for incomplete test evidence?

Yes, evaluating test evidence produces a verdict per story—ADEQUATE, INCOMPLETE, or MISSING—by judging sign-off completeness and edge-case handling to support reliable QA handoffs.

What's the best way to review test evidence across logic and integration stories?

The best way to review test evidence is to apply a consistent evaluation across logic, integration, visual feel, UI, and config/data stories, summarizing quality and producing actionable improvements.