olelehmann1337olelehmann1337Communityยท2 Agent Skills Included

autoresearch-skill

Automatically test and improve any AI skill prompt

Runs any AI skill repeatedly, scores outputs against binary pass/fail checks, and mutates the prompt to fix failures. Eliminates guesswork and manual prompt tweaking by keeping only changes that measurably improve results. Delivers an improved skill file, a full experiment changelog, and a live browser dashboard tracking every score.
npx skills add olelehmann1337/autoresearch-skill --all -g -y

All Skills in This Repository (2)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install autoresearch-skill?โ–ผ

Run `npx skills add olelehmann1337/autoresearch-skill --all -g -y` in your terminal to install it globally.

How to automatically improve an AI skill prompt?โ–ผ

Point autoresearch at your skill, define 3-6 yes/no quality checks, and it runs an autonomous loop that tests, mutates, and keeps only improvements.

What makes a good eval for skill testing?โ–ผ

Every eval must be a binary yes/no question that is specific and checkable, like 'Does the code run without errors?' instead of vague scales or subjective ratings.

Does autoresearch work with Claude Code?โ–ผ

Yes. It is built as a standard SKILL.md file and runs directly inside Claude Code and other compatible AI agents.

Can I watch the optimization progress live?โ–ผ

Yes. The skill generates a self-updating HTML dashboard showing score charts, experiment history, and per-eval breakdowns in your browser.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’