self-improve

Coordinate research, planning, Git-based execution, and tournament-style evaluation for iterative codebase improvement.

1|Updated Apr 6, 2026

Search Tags:#automation #planning #self-improvement #agents #orchestration #benchmark

Ready to run

npx skills add https://github.com/Hyeonjun0527/yeon --skill self-improve-hyeonjun0527

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: self-improve
Source: https://github.com/Hyeonjun0527/yeon/tree/main/.codex/skills/self-improve
Command: npx skills add https://github.com/Hyeonjun0527/yeon --skill self-improve-hyeonjun0527

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Autonomous orchestration of a self-improvement loop for a codebase: it coordinates research, planning, execution, and evaluation to iteratively enhance the repository.

Core Features & Use Cases

Autonomous loop control: manages setup, research, planning, execution, and stop conditions without user prompts.
Tournament-style evaluation: runs parallel experiments, benchmarks winners, and archives results for visualization.
Git-centric improvement: creates isolated worktrees, merges winners into an improvement branch, and pushes changes when configured.
Stateful traceability: maintains detailed histories, reports, and plots for progress monitoring.

Quick Start

Provide the path to your target repository and start the self-improvement loop to begin autonomous optimization.

Frequently Asked Questions about self-improve

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

FAQPage Schema

How do I automate codebase improvement with a self-improvement loop?▼

Autonomous codebase improvement uses an orchestration loop coordinating research, planning, execution, and evaluation to iteratively enhance repositories. It manages setup and stop conditions without user prompts, applying tournament-style evaluation to benchmark parallel experiments and merge winners into an improvement branch.

What is tournament-style evaluation for iterative code enhancement?▼

Tournament-style evaluation runs parallel experiments, benchmarks winners, and archives results for visualization. It maintains detailed histories and plots for progress monitoring, supporting iterative hypothesis evaluation to measure and compare codebase improvements against defined benchmarks.

How do I set up autonomous evolutionary code improvement for my repository?▼

Provide the path to your target repository and start the self-improvement loop. The tool requires a software project with measurable goals and a defined benchmark, using isolated git worktrees for experiments and merging winners into an improvement branch.

Does autonomous code orchestration work with git worktrees and benchmarking?▼

Yes, the orchestration creates isolated git worktrees for parallel experiments, merges winners into an improvement branch, and pushes changes when configured. It requires a defined benchmark to evaluate measurable goals and iteratively test hypotheses for repository enhancement.

Can I use matplotlib for visualizing autonomous code improvement progress?▼

Yes, matplotlib is a required dependency for plotting progress. The orchestration maintains detailed histories, reports, and plots for stateful traceability, enabling visualization of benchmark results and iterative improvement progress across the codebase.

What are the limitations of autonomous self-improvement for codebases?▼

Autonomous self-improvement requires a software project with measurable goals and a defined benchmark. It is limited to repositories where iterative hypothesis evaluation can be applied, needing git-centric workflows with isolated worktrees and clear stop conditions for effective orchestration.