autoresearch

Name: autoresearch
Availability: InStock
Author: olelehmann1337

Run autonomous experiments to iteratively optimize a SKILL.md against binary evaluation criteria.

979|119|Updated Mar 18, 2026

Search Tags:#logs #dashboard #experimentation #skill-improvement #autoresearch #binary-evals #prompt-mutation

Ready to run

npx skills add https://github.com/olelehmann1337/autoresearch-skill --skill autoresearch-olelehmann1337

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: autoresearch
Source: https://github.com/olelehmann1337/autoresearch-skill/tree/main
Command: npx skills add https://github.com/olelehmann1337/autoresearch-skill --skill autoresearch-olelehmann1337

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Autoresearch for Skills provides an automated, repeatable approach to improve any Skill by running autonomous experiments, scoring outputs against binary criteria, mutating prompts, and preserving successful mutations to build better skills over time.

Core Features & Use Cases

Autonomous experimentation loops that repeatedly generate, evaluate, and iterate on a Skill to close performance gaps.
Binary eval scoring that translates success criteria into yes/no signals to guide mutations.
Targeted prompt mutations applied one change at a time, with baseline tracking, a changelog, and a live dashboard to monitor progress.
Outputs produced: an updated SKILL.md, a results log (results.tsv), a changelog (changelog.md), and a real-time dashboard (dashboard.html).

Quick Start

Provide the path to the target SKILL.md, a set of test prompts, and a defined binary eval suite to start the autonomous optimization loop.

Frequently Asked Questions about autoresearch

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

FAQPage Schema

How do I automate prompt optimization for Claude Code skills?▼

Automate prompt optimization by running autonomous experimentation loops that test a SKILL.md against binary evaluation criteria, applying targeted prompt mutations one change at a time to iteratively improve outputs. You provide test prompts and a binary eval suite to guide the process.

What is binary eval scoring and how does it guide skill mutation?▼

Binary eval scoring translates success criteria into yes/no signals to guide prompt mutations. The autonomous loop evaluates mutated SKILL.md outputs against this fixed suite, preserving successful mutations and discarding failures to build better skills over time.

How do I start autonomous experimentation to improve a skill?▼

Start the autonomous optimization loop by providing the file path to your target SKILL.md, a set of varied test prompts for different use-case scenarios, and a defined binary eval suite to score the outputs.

Does the skill mutation process track changes and generate logs?▼

The skill mutation process tracks changes by generating a results.tsv log, a changelog.md, and a live dashboard (results.json + dashboard.html) that refreshes after each experiment to monitor progress and preserve baseline tracking.

Can I use this autonomous optimization approach for any Claude Code skill?▼

Yes, the approach applies to any Claude Code skill by running autonomous experiments against your defined binary evaluation criteria. It tests varied test prompts and use-case scenarios to close performance gaps in the target SKILL.md.

What are the limitations of using binary criteria for prompt mutation?▼

Binary eval criteria restrict scoring to yes/no signals, meaning nuanced performance gradients are lost. Prompt mutations are applied one change at a time, which ensures baseline tracking but may slow down optimization for complex skills requiring multi-variable adjustments.