test-evidence-review

Assess test evidence quality and return per-story verdicts with a sprint summary.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/naxoruto/TE-limonchero-3d --skill test-evidence-review-naxoruto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: test-evidence-review
Source: https://github.com/naxoruto/TE-limonchero-3d/tree/main/.claude/skills/test-evidence-review
Command: npx skills add https://github.com/naxoruto/TE-limonchero-3d --skill test-evidence-review-naxoruto

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a structured quality review of test files and manual evidence documents, going beyond mere existence checks to assess coverage, edge cases, naming conventions, and evidence completeness.

Core Features & Use Cases

  • Evaluate assertion coverage across tests and identify gaps in edge-case handling.
  • Verify alignment between acceptance criteria and evidence, tests, and sign-offs.
  • Generate per-story verdicts (ADEQUATE / INCOMPLETE / MISSING) and a sprint-level summary for QA and sign-off.

Quick Start

Run a full evidence review for the current sprint or a chosen scope and return a detailed 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 review test evidence and assess assertion coverage for a sprint?

Test evidence review evaluates automated tests, edge-case coverage, naming quality, and sign-off completeness to return a structured verdict per story and a final sprint-level summary.

What is the best way to verify alignment between acceptance criteria and manual test documentation?

Acceptance criteria alignment is verified by assessing manual evidence documents against automated tests and sign-offs, scoring adequacy to determine if story coverage is ADEQUATE, INCOMPLETE, or MISSING.

How do I identify gaps in edge-case handling across automated test files?

Edge-case gaps are identified by applying defined scoring criteria to evaluate assertion coverage across test files, pinpointing missing edge-case handling and incomplete manual documentation.

Can I generate a sprint-level QA summary that flags incomplete sign-offs?

Sprint-level QA summaries compile per-story verdicts based on sign-off completeness, flagging stories with missing or inadequate evidence to finalize the sprint quality assessment.

Does test evidence review only check for the existence of test files?

Test evidence review goes beyond mere existence checks by thoroughly assessing coverage, edge-case handling, naming conventions, and evidence completeness to determine overall story adequacy.