eval-debate
CommunityRate your use-self debate quality.
Education & Research#quality assurance#decision analysis#local-first#persona evaluation#debate scoring#prompt benchmarking
AuthorYIKUAIBANZI
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It solves the problem of objectively evaluating whether your use-self “persona debate” output is actually high-quality, internally consistent, and aligned with the target persona’s language style.
Core Features & Use Cases
- Three-phase debate evaluation (Phase 1/2/3): Runs independent variant stances, then performs challenge/assumption scrutiny, and finally produces a synthesis report.
- Five-dimension scoring rubric: Immediately scores results per scenario across variant distinctness,质询 depth, parameter consistency,综合覆盖度, and用户语言风格.
- Persona- and test-case-driven benchmarking: Loads persona ground truth (L0/L2/L3/L4) and executes over multiple decision scenarios from evals/test_cases.
- Local-only execution: Designed to complete evaluation entirely within the current conversation without external API calls.
Quick Start
Ask the assistant to run “/eval-debate” to generate a scored evaluation report for the specified persona and its decision scenarios.
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: eval-debate Download link: https://github.com/YIKUAIBANZI/forge-skill/archive/main.zip#eval-debate 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.