ck:autoresearch

Run iterative code changes and measure a numeric metric per iteration.

Updated Apr 9, 2026

Search Tags:#automation #git #optimization #metrics #iteration #experimentation #autonomous

Ready to run

npx skills add https://github.com/DatTran26/KienTruThiHanh --skill ck-autoresearch-dattran26

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ck:autoresearch
Source: https://github.com/DatTran26/KienTruThiHanh/tree/main/.agents/skills/ck-autoresearch
Command: npx skills add https://github.com/DatTran26/KienTruThiHanh --skill ck-autoresearch-dattran26

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Autonomous iterative optimization loop designed to improve a mechanical metric by running multiple iterations, learning from git history, and auto-keeping or discarding changes to drive measurable improvements while maintaining traceable experiments.

Core Features & Use Cases

Autonomous iteration: executes N iterations with minimal human intervention to optimize a defined metric.
Git-backed experimentation: records each change, bases decisions on commit history, and enables rollback.
Guarded verification: pairs a verify command with an optional guard step to ensure genuine progress and regression prevention.
Use Cases: ideal for improving metrics such as test coverage, bundle size, lint errors, or performance in software projects.

Quick Start

Configure your Goal, Scope, and Verify commands, then start the loop to run N iterations automatically.

Frequently Asked Questions about ck:autoresearch

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

FAQPage Schema

How do I automate iterative code optimization for measurable metrics?▼

Automated iterative code optimization executes a sequence of atomic code changes and measures a defined metric per iteration. It uses a git-tracked history to enable rollback and auto-keeps or discards changes to drive measurable improvements.

How does git-backed experimentation prevent regressions during autonomous optimization?▼

Git-backed experimentation prevents regressions by recording each atomic change as a commit and using an optional Guard step. This pairs with a verify command to ensure genuine progress and enable rollback if a metric degrades.

What metrics can I improve using an autonomous optimization loop?▼

You can improve mechanical metrics like test coverage, bundle size, lint errors, or performance. The loop requires a measurable Verify command that outputs a single numeric metric to evaluate each iteration.

Do I need a clean git repository to run automated iterative optimization?▼

Yes, you need a clean git repository to run automated iterative optimization. A clean state allows the loop to track atomic changes, base decisions on commit history, and safely roll back discarded iterations.

How do I configure iteration limits and noise control for autonomous optimization?▼

You configure iteration limits and noise control using optional Iterations, Noise, and Min-Delta configurations. These settings control the loop length and prevent marginal metric fluctuations from being kept as false progress.

What is the best way to set up a guarded verification step for code changes?▼

The best way to set up guarded verification is to pair a Verify command that outputs a numeric metric with an optional Guard step. This ensures regression prevention by validating genuine progress across build pipelines.