test-evidence-review

Assess test coverage and evidence quality for software stories.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/HechaoYannet/3kingdom-unity --skill test-evidence-review-hechaoyannet
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: test-evidence-review
Source: https://github.com/HechaoYannet/3kingdom-unity/tree/main/.claude/skills/test-evidence-review
Command: npx skills add https://github.com/HechaoYannet/3kingdom-unity --skill test-evidence-review-hechaoyannet

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

  • Comprehensive assessment of unit and integration test coverage, including assertion counts, edge-case handling, and naming quality.
  • Evaluation of manual evidence documents for sign-off completeness and linkage to acceptance criteria.
  • Generates a structured verdict and actionable recommendations to improve test and evidence quality.

Quick Start

Run the review on a single story path, sprint, or system to generate a verdict and recommendations.

Frequently Asked Questions about test-evidence-review

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

FAQPage Schema
How do I check software test coverage and validate evidence quality before QA sign-off?

Test coverage and evidence quality are checked by parsing story files, validating assertion counts, evaluating edge cases, and scoring verdicts as ADEQUATE, INCOMPLETE, or MISSING before QA sign-off.

What is story-level test evidence review and how does it work?

Story-level test evidence review assesses unit, integration, visual, and UI tests by evaluating assertion coverage and naming conventions, producing a structured verdict with actionable recommendations for each story.

Can I run a sprint-wide test review across multiple software stories?

Sprint-wide test reviews are supported by applying the assessment logic across multiple story paths, locating test files and evidence artifacts to generate ADEQUATE, INCOMPLETE, or MISSING verdicts for the entire sprint.

What's the best way to evaluate manual evidence documents for acceptance criteria linkage?

Manual evidence documents are evaluated by checking sign-off completeness and verifying linkage to acceptance criteria, ensuring the evidence supports the story requirements before generating a final verdict.

Does the test review process check for edge case handling and naming conventions?

Edge case handling and naming conventions are explicitly checked during the test review, going beyond simple existence checks to ensure comprehensive assertion coverage and test quality.