How does Spec Reviewer differ from regular QA tools?

While standard QA tools focus on bug detection, Spec Reviewer specifically focuses on 'spec compliance'—ensuring that every single requirement in the original planning document is actually represented in the testing suite.

What is the difference between Phase 1-A and Phase 1-B reviews?

Phase 1-A checks if the written scenarios cover the initial spec, while Phase 1-B checks if the final JSON test cases accurately reflect those confirmed scenarios.

What file formats does it support for review?

The skill primarily reviews Markdown (.md) files for scenarios and JSON files for test cases, comparing them against the provided project specifications.

Can it integrate with Confluence documents?

Yes, it is designed to use Confluence-based planning and policy documents as the primary source of truth for cross-referencing scenarios and test cases.

Does it provide automated fixes for missing test cases?

It provides detailed feedback, missing item IDs, and improvement suggestions in a structured JSON report, which the developer or QA engineer can use to update the documentation.

Spec Reviewer

Name: Spec Reviewer
Author: MediSolveAIDev

byMediSolveAIDev

0•

Security & Testing

Validates test scenarios and test cases against project specifications to ensure full requirement coverage and logical consistency.

Spec Reviewer is a specialized QA agent designed to cross-reference test documentation with original planning and policy documents. It ensures that every functional requirement, business logic rule, and edge case defined in specifications (such as Confluence pages) is accurately captured in test scenarios and JSON test cases. By identifying gaps in coverage and inconsistencies in logic early in the development lifecycle, it helps teams maintain high-quality standards and prevents missing features during the testing phase. It works in tandem with general QA reviewers to provide a comprehensive audit of the software's readiness against its original intent.

Key Features

01Requirement Coverage Analysis: Maps planning documents to test scenarios to identify missing features or skipped requirements.

02Scenario-to-TC Mapping: Ensures finalized markdown scenarios are correctly and fully translated into executable JSON test cases.

03Structured JSON Reporting: Generates detailed audit logs with pass/fail verdicts, coverage rates, and severity-ranked findings.

04Automated Rule Integration: Dynamically loads active business logic and spec-gap rules from local directories for customized auditing.

05Historical Review Tracking: Maintains a versioned history of review rounds to monitor progress and compliance over time.

060 GitHub stars

Use Cases

01Verifying that a new product version's test plan covers all updated features defined in the Confluence specification.

02Detecting logical inconsistencies between internal business policies and the 'Expected Result' fields in a test suite.

03Auditing the transition from high-level markdown test scenarios to structured JSON test data to prevent translation errors.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add medisolveaidev/qa-medi-plugin review-spec

For use in Claude.ai and ChatGPT

Key Features

01Requirement Coverage Analysis: Maps planning documents to test scenarios to identify missing features or skipped requirements.

02Scenario-to-TC Mapping: Ensures finalized markdown scenarios are correctly and fully translated into executable JSON test cases.

03Structured JSON Reporting: Generates detailed audit logs with pass/fail verdicts, coverage rates, and severity-ranked findings.

04Automated Rule Integration: Dynamically loads active business logic and spec-gap rules from local directories for customized auditing.

05Historical Review Tracking: Maintains a versioned history of review rounds to monitor progress and compliance over time.

060 GitHub stars

Use Cases

01Verifying that a new product version's test plan covers all updated features defined in the Confluence specification.

02Detecting logical inconsistencies between internal business policies and the 'Expected Result' fields in a test suite.

03Auditing the transition from high-level markdown test scenarios to structured JSON test data to prevent translation errors.