Dueling Autoresearch

Dueling Autoresearch is an AI Engineering skill for Claude Code, published by gaasher in Agent-Loop-Skills.

166 stars19 forkson gaasher/Agent-Loop-SkillsAdded 2026/09/08+2% in starsRepository updated 2026/06/30

agent-skillsagentic-loopsagentic-workflowsai-agentsanthropicautoresearchclaudeclaude-codedata-analysisliterature-reviewllm-agentsmachine-learningml-autoresearchopen-sourceprompt-engineeringred-teamingscientific-writingskillssubagents

Install in seconds

Install Dueling Autoresearch

Copy Dueling 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/gaasher/Agent-Loop-Skills/tree/main/loops/dueling-autoresearch ~/.claude/skills/dueling-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/gaasher/Agent-Loop-Skills.git

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

In this catalog

Source file: loops/dueling-autoresearch/SKILL.md in gaasher/Agent-Loop-Skills
Installs to: ~/.claude/skills/dueling-autoresearch
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What Dueling Autoresearch does

Dueling Autoresearch runs two different approaches against the same metric in parallel and keeps a shared scoreboard. Use it when you want an analysis-first head-to-head between lanes such as classical versus learned methods.

Dueling Autoresearch is cataloged under AI Engineering on DirSkills. Dueling Autoresearch comes from a repository tagged agent-skills, agentic-loops, agentic-workflows, ai-agents and anthropic.

Documentation

README

Excerpt

Dueling Autoresearch Loop

Two lanes work the same objective in parallel and race the same metric — by default a classical/algorithmic lane against an ML/learned lane (the lanes are user-named). Each lane runs its own analysis-first iteration via roles/TrackAgent.md, confined to its lane. Every round both lanes post to a shared duel_log.md scoreboard and may borrow ideas across the lane boundary — but each stays in its lane. The feedback signal is the shared <metric> on a shared eval: if the classical lane wins, that is a real result. Lanes support mixed code locations — a codebase lane edits existing repo files, a sandbox lane authors its own code — and an eval-parity gate keeps the scores comparable.

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

Frequently asked about Dueling Autoresearch

What else does gaasher publish alongside Dueling Autoresearch?
Dueling Autoresearch is one of 25 skills that DirSkills catalogs from gaasher/Agent-Loop-Skills, the repository it ships in. Its siblings there include Alpha Evolve, Anomaly Investigation and Blue Team. Each one is a separate skill with its own page in this directory, installs the same way Dueling Autoresearch does, and is maintained by gaasher in that same repository. The rest of the collection is listed on the gaasher/Agent-Loop-Skills page.
How does Dueling Autoresearch compare to other AI Engineering skills?
Dueling Autoresearch ranks #3327 by stars among the 3670 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 Dueling Autoresearch against them. Open each page to compare what they document and how they install.