Back to skills
SkillHub ClubAnalyze Data & AIFull StackData / AI

increment-quality-judge-v2

This skill provides AI-powered quality assessment using the LLM-as-Judge pattern, evaluating specifications and plans across 7 dimensions including risk scoring to deliver PASS/CONCERNS/FAIL decisions with actionable recommendations.

Packaged view

This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.

Stars
95
Hot score
94
Updated
March 20, 2026
Overall rating
C5.1
Composite score
5.1
Best-practice grade
C67.9

Install command

npx @skill-hub/cli install anton-abyzov-specweave-increment-quality-judge-v2

Repository

anton-abyzov/specweave

Skill path: plugins/specweave/skills/increment-quality-judge-v2

This skill provides AI-powered quality assessment using the LLM-as-Judge pattern, evaluating specifications and plans across 7 dimensions including risk scoring to deliver PASS/CONCERNS/FAIL decisions with actionable recommendations.

Open repository

Best for

Primary workflow: Analyze Data & AI.

Technical facets: Full Stack, Data / AI.

Target audience: Development teams looking for install-ready agent workflows..

License: Unknown.

Original source

Catalog source: SkillHub Club.

Repository owner: anton-abyzov.

This is still a mirrored public skill entry. Review the repository before installing into production workflows.

What it helps with

  • Install increment-quality-judge-v2 into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
  • Review https://github.com/anton-abyzov/specweave before adding increment-quality-judge-v2 to shared team environments
  • Use increment-quality-judge-v2 for development workflows

Works across

Claude CodeCodex CLIGemini CLIOpenCode

Favorites: 0.

Sub-skills: 0.

Aggregator: No.

increment-quality-judge-v2 | SkillHub