skills.rest
uditgoenkauditgoenkaCommunity·2 Agent Skills Included

autoresearch

Autonomous AI loops that debug, fix, secure, and ship code

Runs autonomous improvement loops that modify code, verify results against a metric, and keep or roll back each change automatically. Hunts bugs, fixes failing tests and type errors, audits security with STRIDE and OWASP checks, and ships releases through a guided pipeline. Eliminates manual trial-and-error by logging every experiment in git, so your AI agent keeps improving until the goal is met.
5,975|446
↗
npx skills add uditgoenka/autoresearch --all -g -y
Available:

Tells any AI agent how to run the autoresearch command set, including the iteration loop rules, configuration fields, safety constraints, and how to route plain-language goals to the right subcommand.

All Skills in This Repository (2)

Pure Emerald Level Indicators
📦 In Repo
uditgoenkauditgoenka

autoresearch

Coordinate autonomous modify-verify loops for AI coding agents.

Community
Advanced
📦 In Repo
uditgoenkauditgoenka

autoresearch

Runs autonomous iteration loops that modify code, verify against metrics, and keep or discard changes.

Community
Advanced

Frequently Asked Questions

FAQPage Schema
How to install Autoresearch?▼

Run `npx skills add uditgoenka/autoresearch --all -g -y` in your terminal to install the full skill suite globally for your AI agent.

What does Autoresearch actually do?▼

It turns your AI agent into an autonomous improvement loop: set a goal and a measurable metric, and the agent modifies code, verifies results, keeps wins, and reverts failures until the goal is met.

Can Autoresearch fix failing tests automatically?▼

Yes. The fix command detects broken tests, type errors, lint issues, and build failures, then repairs them one at a time until the error count reaches zero.

Does Autoresearch work with Claude Code and Codex?▼

Yes. It ships ready-made plugins for Claude Code, OpenAI Codex, and OpenCode, and the AGENTS.md file lets any other agent adopt the same command surface.

Is Autoresearch safe to run on my codebase?▼

Yes. Every change is committed atomically in git, failed experiments roll back automatically, dangerous commands are blocked, and deploys always require your explicit approval.

Related Repositories in Software Engineering

View All in Software Engineering→
openclawopenclaw
388.4k

openclaw

Run a personal AI assistant across your devices and chat apps

Official📦 120 Skills
obraobra
280.0k

superpowers

Gives coding agents a disciplined workflow from idea to merged code

Community📦 15 Skills
facebookfacebook
248.4k

react

AI agent skills for building, testing, and porting React core

Official📦 14 Skills