pipeline-judge-dual
CommunityDual-LLM judge for end-to-end plan evaluation.
Authordanielgap
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Dual-LLM evaluation of business plans to produce a unified judge report and actionable feedback for re-runs.
Core Features & Use Cases
- Parallel dual-LLM evaluation of plan artifacts (analytical and strategic perspectives) and synthesis into JUDGE-A.json, JUDGE-B.json, JUDGE-REPORT.json, and FEEDBACK-FOR-RERUN.json.
- Validates plan completeness, consistency, and investor-readiness with a structured checklist.
- Provides guidance for re-runs and improvement phases.
Quick Start
Place the inputs in the project directory and run the dual-LLM judge to generate JUDGE-A.json, JUDGE-REPORT.json, JUDGE-B.json, and FEEDBACK-FOR-RERUN.json.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 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: pipeline-judge-dual Download link: https://github.com/danielgap/openclaw-planitor/archive/main.zip#pipeline-judge-dual Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.