Autoresearch

Autoresearch is an AI Engineering skill for Claude Code, published by oliver-kriska in claude-elixir-phoenix.

533 stars38 forkson oliver-kriska/claude-elixir-phoenixAdded 2026/08/26+1% in starsRepository updated 2026/08/19

ai-agentsai-coding-assistantautomationclaudeclaude-codeclaude-code-pluginclaude-code-skillsclaude-skillscode-reviewdeveloper-toolsectoelixirelixir-langelixir-phoenixliveviewobanphoenixphoenix-frameworktidewavevibe-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/oliver-kriska/claude-elixir-phoenix/tree/main/lab/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/oliver-kriska/claude-elixir-phoenix.git

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

In this catalog

Source file: lab/autoresearch/SKILL.md in oliver-kriska/claude-elixir-phoenix
Installs to: ~/.claude/skills/autoresearch
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Autoresearch does

Autoresearch runs a loop that mutates one plugin skill at a time, evaluates it with deterministic checks, and keeps or reverts the change. Use it for targeted or overnight improvement runs.

Autoresearch is cataloged under AI Engineering on DirSkills. Autoresearch comes from a repository tagged ai-agents, ai-coding-assistant, automation, claude and claude-code.

Documentation

README

Excerpt

Autoresearch — Plugin Skill Self-Improvement

Iteratively improve plugin skills via the autoresearch pattern: propose one mutation -> eval -> keep/revert -> repeat.

Usage

/lab:autoresearch                           # Targeted: attack weakest skill+dimension
/lab:autoresearch --skill review            # Focus on one skill
/lab:autoresearch --strategy sweep          # Process all skills alphabetically
/lab:autoresearch --dry-run                 # Show what would change, don't commit

For overnight runs:

/loop 5m /lab:autoresearch --strategy sweep --max-iterations 200

Iron Laws

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.

/loop

Frequently asked about Autoresearch

What else does oliver-kriska publish alongside Autoresearch?
Autoresearch is one of 25 skills that DirSkills catalogs from oliver-kriska/claude-elixir-phoenix, the repository it ships in. Its siblings there include Ash Framework, Brainstorm and Catchup. Each one is a separate skill with its own page in this directory, installs the same way Autoresearch does, and is maintained by oliver-kriska in that same repository. The rest of the collection is listed on the oliver-kriska/claude-elixir-phoenix page.
How does Autoresearch compare to other AI Engineering skills?
Autoresearch ranks #2074 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.