autoresearch

Name: autoresearch
Availability: InStock
Author: marcoapereirav-arch

Run iterative evaluations and mutations on a skill until performance thresholds are met.

Updated Aug 23, 2026

Search Tags:#git #validation #baseline #skill-optimization #prompt-evaluation #automated-loop #autoresearch

Ready to run

npx skills add https://github.com/marcoapereirav-arch/nvision-saas-factory --skill autoresearch-marcoapereirav-arch

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: autoresearch
Source: https://github.com/marcoapereirav-arch/nvision-saas-factory/tree/main/saas-factory/.claude/skills/autoresearch
Command: npx skills add https://github.com/marcoapereirav-arch/nvision-saas-factory --skill autoresearch-marcoapereirav-arch

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the autonomous improvement of a skill by running iterative evaluations and targeted mutations to discover better prompts and configurations over time.

Core Features & Use Cases

Baseline evaluation of a target skill from its SKILL.md to establish a performance starting point.
Iterative mutation and experimentation with isolated changes to prompts, instructions, and constraints.
Automated commit-and-run loop that records results, compares scores, and preserves the best baseline for deployment.

Quick Start

Identify the target skill from its SKILL.md, create a branch autoresearch/autoresearch, and let the autonomous loop run until the target score is reached or the maximum iterations are completed.

Frequently Asked Questions about autoresearch

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

FAQPage Schema

How do I automate iterative prompt evaluation and mutation for my skills?▼

Automated prompt evaluation runs iterative loops that baseline a skill, mutate its prompts, and commit improvements until performance thresholds are met. It requires a SKILL.md with a clear description and binary evaluation criteria to drive the loop safely.

What do I need to set up before running an autonomous prompt improvement loop?▼

Before running an autonomous prompt improvement loop, you need a Git repository for versioning and a target skill defined in a SKILL.md file. The SKILL.md must contain a clear name and description to establish the baseline evaluation starting point.

How does automated skill optimization handle version control during mutations?▼

Automated skill optimization handles version control by creating an isolated branch, applying targeted mutations to prompts, and running an automated commit-and-run loop. This records results, compares scores against the baseline, and preserves the best configuration for deployment.

Can I use automated self-improvement loops to refine tool configurations and workflows?▼

Yes, you can use automated self-improvement loops to refine tool configurations and workflows. The loop applies targeted mutations and isolated changes to instructions and constraints, evaluating them against binary criteria to discover better configurations over time.

When should I not use an autonomous mutation loop for prompt refinement?▼

You should not use an autonomous mutation loop if your target skill lacks a SKILL.md with a clear name and description, or if you cannot define binary evaluation criteria. Without these safe guards and a Git repository, the loop cannot establish a baseline or measure improvements.

What is the best way to establish a performance baseline for a target skill?▼

The best way to establish a performance baseline is to evaluate the target skill directly from its SKILL.md file. This baseline evaluation provides the starting point for the iterative mutation loop to compare subsequent scores and preserve the best configuration.