test-evidence-review

Evaluate test evidence and manual artefacts with per-story verdicts.

3|Updated Jun 3, 2026
One-click install
npx skills add https://github.com/Negentropy-Laby/Constitution-Driven-Development --skill test-evidence-review-negentropy-laby
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: test-evidence-review
Source: https://github.com/Negentropy-Laby/Constitution-Driven-Development/tree/main/.agents/skills/test-evidence-review
Command: npx skills add https://github.com/Negentropy-Laby/Constitution-Driven-Development --skill test-evidence-review-negentropy-laby

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 test files for assertion coverage, edge-case handling, and naming quality.
  • Assess manual evidence docs for criterion linkage, sign-offs, and artefact completeness.
  • Generate per-story verdicts (ADEQUATE / INCOMPLETE / MISSING) and actionable next steps.

Quick Start

Run /test-evidence-review sprint to assess all stories in the current sprint and generate an evidence review.

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 QA sign-off?

Test evidence review checks assertion coverage, edge case handling, naming conventions, and evidence completeness to generate a per-story verdict of ADEQUATE, INCOMPLETE, or MISSING before QA sign-off.

What is assertion coverage and how does it affect test evidence reviews?

Assertion coverage measures the validation depth within test files. Evaluating it during a test evidence review identifies untested edge cases and triggers an INCOMPLETE or MISSING verdict if quality gaps exist.

Can I review manual evidence documents and test files for an entire sprint?

Yes, you can assess test evidence across a single story, a full sprint, or a system epic. The review evaluates both test files and manual evidence documents, returning structured verdicts and gap highlights for the entire scope.

How do I know if my manual test artefacts are ready for sign-off?

Manual test artefacts are ready for sign-off when they demonstrate proper criterion linkage, complete sign-offs, and artefact completeness. The review returns an ADEQUATE verdict if these evidence quality standards are met.

What is the best way to identify gaps in test documents and edge cases?

The best way to identify gaps in test documents is to run a structured QA evidence review. It evaluates assertion coverage and edge case handling, returning a MISSING or INCOMPLETE verdict with guidance on next steps.