skill-improver

Analyzes agent conversations and generates pull requests with suggested skill improvements.

Updated Feb 5, 2026
One-click install
npx skills add https://github.com/ilamanov/skills --skill skill-improver-ilamanov
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-improver
Source: https://github.com/ilamanov/skills/tree/main/skills/skill-improver
Command: npx skills add https://github.com/ilamanov/skills --skill skill-improver-ilamanov

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the analysis of agent conversations to identify areas for skill improvement, streamlining the process of continuous learning and enhancement.

Core Features & Use Cases

  • Conversation Analysis: Identifies moments where an agent's responses could be improved based on actual interactions.
  • Proposed Edits: Generates pull requests with suggested edits to improve specific skills.
  • Self-Improvement: Analyzes its own runs to iteratively improve its own functionality.
  • Use Case: Ideal for teams aiming to enhance the performance of their AI agents, especially in environments where recursive skill improvement and post-mortem analysis of conversations are critical.

Quick Start

Run the skill-improver to analyze recent conversations and generate improvement proposals.

Frequently Asked Questions about skill-improver

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

FAQPage Schema
How do I automate AI agent conversation analysis for skill improvement?

You can automate AI agent conversation analysis by running this skill against recent interaction logs. It identifies suboptimal agent responses and generates targeted proposals for skill improvement.

What is recursive learning for AI enhancement?

Recursive learning for AI enhancement is a continuous improvement process where an agent analyzes its own past runs. This skill uses this technique to iteratively evaluate its performance and propose edits to its own functionality.

Do I need GitHub CLI and git to generate pull requests for AI skill edits?

Yes, generating pull requests for AI skill edits requires git and GitHub CLI. These dependencies are necessary to automatically propose targeted code changes and manage the version control workflow.

How do I run a post-mortem analysis on agent conversations?

To run a post-mortem analysis on agent conversations, execute this skill to scan interaction data sources. It automatically detects moments where agent responses could be improved and formulates actionable feedback.

Can this skill analyze its own runs for continuous self-improvement?

Yes, this skill can analyze its own runs for continuous self-improvement. It is specifically designed to evaluate its own past performance and iteratively generate suggestions to enhance its own functionality.

What are the limitations of automating skill improvement through conversation analysis?

A limitation of automating skill improvement is the strict dependency on external tools like git and GitHub CLI. Additionally, the analysis quality is constrained by the availability and structure of the relevant conversation data sources.