team-skill-evolve

Analyze feedback and execution logs to propose skill library improvements.

8|1|Updated May 10, 2026
One-click install
npx skills add https://github.com/coolbeevip/team-ai-skills --skill team-skill-evolve
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: team-skill-evolve
Source: https://github.com/coolbeevip/team-ai-skills/tree/main/skills/harness/team-skill-evolve
Command: npx skills add https://github.com/coolbeevip/team-ai-skills --skill team-skill-evolve

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the challenge of continuously improving the team's AI skill library by analyzing real-world feedback, identifying issues, and proposing actionable improvements.

Core Features & Use Cases

  • Feedback Analysis: Reviews user feedback, failures, and execution logs to identify areas for improvement.
  • Skill Evolution: Proposes auditable suggestions for enhancing the skill library based on feedback.
  • Use Case: When a user reports that a skill is over-engineered or not reusing existing code, this skill can analyze the situation and suggest minimal changes to improve the skill.

Quick Start

Run the 'team-skill-evolve' skill to analyze and suggest improvements for the 'team-skill-evolve' skill itself.

Frequently Asked Questions about team-skill-evolve

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

FAQPage Schema
How do I improve my team's AI skills using real-world feedback?

To improve your team's AI skills using real-world feedback, you need a tool that analyzes execution logs and user feedback to identify issues and propose actionable, auditable enhancements to the skill library.

What is continuous improvement for an AI skill library?

Continuous improvement for an AI skill library is the process of analyzing real-world execution logs and user feedback to identify failures and propose minimal, auditable changes that enhance skill performance.

How do I analyze AI skill execution logs to propose skill evolution?

You can analyze AI skill execution logs by reviewing failures and user feedback to detect over-engineering or code reuse issues, then generating minimal, actionable suggestions to evolve the skill library.

What data do I need to provide for AI skill feedback analysis?

For AI skill feedback analysis, you need to provide access to skill metadata, execution logs, and user feedback to successfully identify issues and propose actionable improvements.

Does this approach work for resolving over-engineered AI skills?

Yes, this approach works for resolving over-engineered AI skills by analyzing user feedback and execution logs to suggest minimal changes that improve reusability and simplify the skill design.