wjs-evaling-voicedrop-prompts

Community

Evaluate VoiceDrop's prompt system for effectiveness.

Authorjianshuo
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill assesses the effectiveness of changes to VoiceDrop's mining system prompt, ensuring improvements are actually beneficial compared to the live version.

Core Features & Use Cases

  • Prompt Evaluation: Compares new and existing prompts, providing a win-rate verdict based on evaluations.
  • Local Evaluation Harness: Utilizes a local Claude Code instance for running evaluations.
  • Subagent Dispatching: Sends pairwise judgments to subagents for blind evaluations.
  • Report Generation: Aggregates results into a report for further analysis.
  • Manual Approval: Allows manual approval to promote candidates into the main prompt system.

Quick Start

Run the 'wjs-evaling-voicedrop-prompts' skill to evaluate a new prompt against the current version.

Dependency Matrix

Required Modules

VoiceDrop APIClaude Code

Components

scriptsreferences

💻 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: wjs-evaling-voicedrop-prompts
Download link: https://github.com/jianshuo/claude-skills/archive/main.zip#wjs-evaling-voicedrop-prompts

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 620,000+ vetted skills library on demand.