skill-improver

Apply improvements from review plans to update skills.

2|Updated Jul 9, 2026
One-click install
npx skills add https://github.com/koki3141/codex-global-skills --skill skill-improver-koki3141
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-improver
Source: https://github.com/koki3141/codex-global-skills/tree/main/skill-improver
Command: npx skills add https://github.com/koki3141/codex-global-skills --skill skill-improver-koki3141

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the process of improving and evolving skills based on review history and conversation, saving time and reducing manual effort.

Core Features & Use Cases

  • Automated Skill Improvement: Apply improvements from review plans or conversation history.
  • Skill Evolution: Evolve skills based on repeated corrections and durable preferences.
  • Use Case: After a quality review, use this Skill to automatically update and fix issues in your skills, or evolve them based on feedback from a conversation.

Quick Start

Run the skill-improver with the command 'apply-improvements' followed by the name of the skill and the improvement plan file.

Frequently Asked Questions about skill-improver

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

FAQPage Schema
How do I automate skill updates from review history and conversation feedback?

Automating skill updates from review history involves applying patches from conversation logs or review plans to fix issues and evolve behaviors. This process supports backup, patching, verification, and reporting to ensure accurate improvements.

Can I apply patches to evolving skills based on repeated corrections without manual editing?

Applying patches to evolving skills based on repeated corrections is supported through automated updates. The system reads durable preferences and correction patterns from history to generate and apply patches directly to the skill files.

Do I need Python to run automated skill improvement and verification scripts?

Python is required to run automated skill improvement scripts. The environment uses Python scripts specifically for executing backup operations and verifying that applied skill updates function correctly before finalizing.

What is the best way to back up skills before applying automated improvements?

The best way to back up skills before applying automated improvements is using the integrated backup script. This creates a restorable snapshot before patching, ensuring you can revert if the evolution or update causes unexpected behavior.

How do I execute an improvement plan to patch and verify a skill?

To execute an improvement plan, run the 'apply-improvements' command followed by the target skill name and the improvement plan file. The system then patches the skill, verifies the update using Python scripts, and generates a report.