semantic-review

Community

Validate code quality with evidence-backed checks

Authorgleeb
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Semantic review verifies that local-model outputs and the implemented code truly match the planned scope and acceptance criteria, reducing drift, confabulation, and unreliable “claimed verification” after changes are integrated.

Core Features & Use Cases

  • 3-check validation workflow that defaults checks to NEEDS WORK until proven PASS.
  • Agent report integrity to detect contradictions within and across reviewer/QA reports and ensure all agents operated on the same scope.
  • Senior-developer code quality review that drills into every changed file, traces logic paths, and re-runs evidence verification commands from the reports.
  • Terminology and contract alignment to catch naming drift between contracts/architecture/stories and the actual implementation.
  • Structured guidance packages that produce actionable correction steps and knowledge-gap fetch instructions for re-dispatch when issues are found.

Quick Start

Use the semantic-review skill when the sdlc-engineering-semantic-reviewer needs to validate local model outputs and review the implemented code quality for a completed story before acceptance validation.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: semantic-review
Download link: https://github.com/gleeb/ai-registry/archive/main.zip#semantic-review

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.