Arbor

Arbor is an AI Engineering skill for Claude Code, published by K-Dense-AI in scientific-agent-skills.

33.5K stars3.3K forkson K-Dense-AI/scientific-agent-skillsAdded 2026/08/14Repository updated 2026/08/13

agent-skillsai-scientistbioinformaticschemoinformaticsclaudeclaude-skillsclaudecodeclinical-researchcomputational-biologydata-analysisdrug-discoverygenomicsmaterials-sciencemetabolomicsproteomicsscientific-computingscientific-visualization

Install in seconds

Install Arbor

Copy Arbor 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/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor ~/.claude/skills/arbor

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/K-Dense-AI/scientific-agent-skills.git

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

In this catalog

Source file: skills/arbor/SKILL.md in K-Dense-AI/scientific-agent-skills
Installs to: ~/.claude/skills/arbor
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Arbor does

Arbor autonomously improves a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator using Hypothesis Tree Refinement (HTR). Use it for iterative optimization over many experiments without overfitting.

Arbor is cataloged under AI Engineering on DirSkills. Arbor comes from a repository tagged agent-skills, ai-scientist, bioinformatics, chemoinformatics and claude.

Documentation

README

Excerpt

Overview

This skill runs an Autonomous Optimization (AO) loop: starting from an existing artifact and a measurable objective, improve it through many rounds of experiment and evaluation — without step-by-step human supervision and without overfitting to the feedback signal. It's the right tool when the bottleneck isn't writing one good change, but organizing dozens of trials so that lessons accumulate instead of evaporating.

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

Frequently asked about Arbor

What else does K-Dense-AI publish alongside Arbor?
Arbor is one of 25 skills that DirSkills catalogs from K-Dense-AI/scientific-agent-skills, the repository it ships in. Its siblings there include Adaptyv Bio Foundry API, Aeon and Analytical Method Validation. Each one is a separate skill with its own page in this directory, installs the same way Arbor does, and is maintained by K-Dense-AI in that same repository. The rest of the collection is listed on the K-Dense-AI/scientific-agent-skills page.
How does Arbor compare to other AI Engineering skills?
Arbor ranks #171 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 Arbor against them. Open each page to compare what they document and how they install.