Autoresearch

Autoresearch is an AI Engineering skill for Claude Code, published by FlorianBruniaux in claude-code-ultimate-guide.

5.7K stars751 forkson FlorianBruniaux/claude-code-ultimate-guideAdded 2026/08/15Repository updated 2026/08/14

agentic-codingai-assistantai-codingai-pair-programmingai-securityanthropicbest-practicesclaudeclaude-codeclaude-code-guideclaude-code-tutorialcli-toolcoding-assistantcursor-alternativedeveloper-toolsllmmcp-serversprompt-engineeringtutorialvibe-coding

Install in seconds

Install Autoresearch

Copy Autoresearch into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples/skills/autoresearch ~/.claude/skills/autoresearch

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/FlorianBruniaux/claude-code-ultimate-guide.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: examples/skills/autoresearch/SKILL.md in FlorianBruniaux/claude-code-ultimate-guide
Installs to: ~/.claude/skills/autoresearch
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Autoresearch does

Autoresearch scans codebase quality metrics and runs autonomous agent iterations that keep changes only when a metric improves. Use it to run self-correcting improvement loops over a codebase until stopped.

Autoresearch is cataloged under AI Engineering on DirSkills. Autoresearch comes from a repository tagged agentic-coding, ai-assistant, ai-coding, ai-pair-programming and ai-security.

Documentation

README

Excerpt

Autoresearch: Autonomous Improvement Loop

Scan codebase quality metrics, propose improvement loops, and run autonomous agent iterations. Inspired by karpathy/autoresearch, adapted from ML research to code quality.

Concept: The agent proposes a code change, runs the measurement, keeps the change if the metric improved, reverts via git reset if not, and repeats until manually stopped.

Time: Scan ~30s | Per iteration: depends on scope | Loop: runs indefinitely until you stop it

Mode 1: Scan (default)

Measure current state, detect existing loops, propose next actions.

Instructions

Run the following metrics and display a prioritized proposal table.

Step 1: Measure codebase metrics

This is the opening of the README. Read the full README on GitHub.

Commands Autoresearch provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

/autoresearch
/worktree

Frequently asked about Autoresearch

What else does FlorianBruniaux publish alongside Autoresearch?
Autoresearch is one of 25 skills that DirSkills catalogs from FlorianBruniaux/claude-code-ultimate-guide, the repository it ships in. Its siblings there include Audit Agents Skills, Audit Prose and Audit Whitepapers. Each one is a separate skill with its own page in this directory, installs the same way Autoresearch does, and is maintained by FlorianBruniaux in that same repository. The rest of the collection is listed on the FlorianBruniaux/claude-code-ultimate-guide page.
How does Autoresearch compare to other AI Engineering skills?
Autoresearch ranks #460 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Autoresearch against them. Open each page to compare what they document and how they install.