skills.rest
jianshuo
jianshuoCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

wjs-evaling-voicedrop-prompts

Evaluate VoiceDrop mining prompt changes with local evaluations and pairwise judgments.

114|17|Updated May 11, 2026
Search Tags:#prompt evaluation#prompt system#VoiceDrop#mining system#local evaluation
One-click install
npx skills add https://github.com/jianshuo/claude-skills --skill wjs-evaling-voicedrop-prompts
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wjs-evaling-voicedrop-prompts
Source: https://github.com/jianshuo/claude-skills/tree/main/wjs-evaling-voicedrop-prompts
Command: npx skills add https://github.com/jianshuo/claude-skills --skill wjs-evaling-voicedrop-prompts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires VoiceDrop API, Claude Code, and includes scripts (resource) and references (resource) components.

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.

Frequently Asked Questions about wjs-evaling-voicedrop-prompts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I evaluate prompt changes for a mining system?▼

To evaluate prompt changes for a mining system, you can run local evaluations that compare a new prompt against the current live version to generate a win-rate verdict and approval report.

How does local prompt evaluation work with Claude Code?▼

Local prompt evaluation with Claude Code works by utilizing a local instance to run evaluation harnesses, dispatching pairwise judgments to subagents for blind comparisons against live prompts.

Do I need a VoiceDrop API to test prompt effectiveness?▼

Yes, you need VoiceDrop API access to test prompt effectiveness, as the evaluation process requires retrieving live system data and dispatching pairwise judgments for comparison.

What is the best way to compare new prompts against existing ones?▼

The best way to compare new prompts against existing ones is through pairwise blind evaluations dispatched to subagents, which aggregate results into a report for manual approval.

How do I generate a prompt evaluation report for manual approval?▼

You generate a prompt evaluation report for manual approval by running local evaluations that aggregate pairwise judgment results, providing a comprehensive analysis to promote successful candidates.

Related Skills

Explore More Software Engineering Skills→
matthewdeavesmatthewdeaves

setup-machine

Register a new Classic Mac in the MCP server and verify FTP connectivity.

Community
Intermediate
aresbitaresbit
46

openai-image-gen

Generate images from sampled prompts via the OpenAI Images API and save them with a local HTML gallery.

Community
Intermediate
ollieb89ollieb89

llm-evaluation

Evaluate LLM outputs with automated metrics and LLM-as-Judge workflows.

Community
Advanced
emilneuraz-aiemilneuraz-ai

llm-evaluation

Evaluate LLM outputs with automated metrics, human feedback, and benchmarking.

Community
Advanced