test-evidence-review

Review test files and manual evidence to produce story closure verdict reports.

1|Updated May 3, 2026
One-click install
npx skills add https://github.com/imclab/xrA1-swarm --skill test-evidence-review-imclab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: test-evidence-review
Source: https://github.com/imclab/xrA1-swarm/tree/main/.claude/skills/test-evidence-review
Command: npx skills add https://github.com/imclab/xrA1-swarm --skill test-evidence-review-imclab

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents stories from being marked complete when required tests and evidence are missing or present but insufficient, reducing the risk of uncovered behavior and incomplete sign-offs.

Core Features & Use Cases

  • Scope-based evidence review: Review a single story, an entire sprint, or all stories in a system/epic.
  • Automated test quality checks (Logic/Integration): Evaluate assertion coverage, edge-case coverage signals, naming quality, and formula traceability.
  • Manual evidence quality checks (Visual/Feel/UI): Verify acceptance-criterion linkage, required sign-offs, artefact completeness (screenshots/walkthrough evidence), and freshness.

Quick Start

Run the test-evidence-review for a specific story by saying: "/test-evidence-review path/to/production/stories/your-story.md" and review the ADEQUATE/INCOMPLETE/MISSING results.

Frequently Asked Questions about test-evidence-review

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

FAQPage Schema
How do I validate test evidence and assertion coverage before closing a story?

You can review test quality for a single story, an entire sprint, or all stories in a system scope. The review locates evidence via repository globs and greps, evaluating coverage and sign-off quality to produce a comprehensive verdict report.

How do I check manual evidence quality for UI and Visual story types?

For Logic and Integration story types, automated test quality checks evaluate assertion coverage, edge-case coverage signals, naming quality, and formula traceability to determine if the story is adequately validated.

Can I use evidence review for sprint-level or system-level scope?

To run a review for a specific story, provide the path to the story file. The system analyzes the associated test files and manual evidence documents, outputting an ADEQUATE, INCOMPLETE, or MISSING verdict based on validation criteria.

What is the best way to prevent stories from being marked complete with missing test evidence?

The best way to prevent incomplete story closures is to perform an evidence review that verifies required tests and evidence are present and sufficient, scoring assertion coverage and sign-off quality to reduce the risk of uncovered behavior.