skill-evolver

Analyze JSON trace files and feedback to diagnose and fix skill issues.

1.1k|99|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/MooseGoose0701/skill-compose --skill skill-evolver
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-evolver
Source: https://github.com/MooseGoose0701/skill-compose/tree/main/skills/skill-evolver
Command: npx skills add https://github.com/MooseGoose0701/skill-compose --skill skill-evolver

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automatically analyzes skill execution traces and user feedback to identify issues and suggest or apply improvements to existing skills, enhancing their performance and reliability.

Core Features & Use Cases

  • Trace Analysis: Identifies common issues like failures, high turn counts, and token usage from execution logs.
  • Feedback Integration: Incorporates user suggestions to guide improvements.
  • Automated Fixes: Suggests or applies changes to skill scripts, SKILL.md, or reference files.
  • Use Case: After a skill experiences a low success rate, you can feed its execution traces to this Skill to pinpoint the exact errors, understand the root causes, and have it propose specific code or instruction changes to fix the problem.

Quick Start

Use the skill-evolver to analyze the provided trace file 'traces.json' and suggest improvements.

Frequently Asked Questions about skill-evolver

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

FAQPage Schema
How do I debug skill execution failures using trace analysis?▼

Skill trace analysis debugs execution failures by processing JSON trace files to detect high turn counts, excessive token usage, and tool errors, identifying root causes to apply targeted fixes to skill scripts and reference files.

Can I use user feedback to guide automated skill improvements?▼

Yes, user feedback integration guides automated improvements by processing optional feedback alongside execution traces to diagnose issues and suggest specific code or instruction changes to skill scripts and SKILL.md files.

What is the best way to reduce high token usage in skill execution?▼

Reducing high token usage involves analyzing JSON execution trace files to detect excessive consumption patterns, diagnosing the root causes, and applying targeted fixes to skill scripts and reference files based on severity levels.

How do I automatically fix tool errors found in skill execution logs?▼

Automatically fixing tool errors requires processing JSON execution logs to identify the failures, diagnosing root causes from the traces, and applying predefined pattern fixes to skill scripts, SKILL.md, and reference files.

Does skill evolution require specific input formats for trace files?▼

Skill evolution requires JSON trace files containing execution data to detect issues like failures and high turn counts, alongside optional user feedback, to automatically suggest and apply improvements to skill components.

Why does my skill have a low success rate after multiple execution turns?▼

A low success rate after multiple turns indicates execution failures or high token usage, which trace analysis pinpoints by processing JSON logs to understand root causes and propose specific code or instruction changes.