skill

arbor

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.

Description as published by the maintainer. Source

• active

active — Most recent push to the repository was 2026-08-03.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Will this work with your setup?

No harness stated by the author and no install path convention detected. Compatibility is untested.

We have not run this skill against a task with and without it enabled, so we cannot tell you whether it improves anything, what it costs in tokens, or whether it duplicates behaviour your harness already has. When we have run that test, the result will appear on this page with the task, the versions and the budget it used.

The skill definition lives at skills/arbor/SKILL.md in https://github.com/K-Dense-AI/scientific-agent-skills.

Where to get it

• Repository — https://github.com/K-Dense-AI/scientific-agent-skills

Also from k-dense-ai

• k-dense-ai-scientific-agent-skills-adaptyv — last commit 2026-08-03
  How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval.…
• k-dense-ai-scientific-agent-skills-aeon — last commit 2026-08-03
  This skill should be used for time series machine learning tasks including classification, regression, clustering, fore…
• k-dense-ai-scientific-agent-skills-analytical-method-validation — last commit 2026-08-03
  Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framewo…
• k-dense-ai-scientific-agent-skills-anndata — last commit 2026-08-03
  Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with th…
• k-dense-ai-scientific-agent-skills-arboreto — last commit 2026-08-03
  Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when…
• k-dense-ai-scientific-agent-skills-astropy — last commit 2026-08-03
  Core Python library for astronomy and astrophysics workflows that need Astropy APIs, including units/quantities, coordi…
• k-dense-ai-scientific-agent-skills-autoskill — last commit 2026-08-03
  Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-ag…
• k-dense-ai-scientific-agent-skills-benchling-integration — last commit 2026-08-03
  Benchling Python SDK and REST API integration for registry entities, inventory, ELN entries, workflows, Benchling Apps,…
• k-dense-ai-scientific-agent-skills-bgpt-paper-search — last commit 2026-08-03
  Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP se…
• k-dense-ai-scientific-agent-skills-biopython — last commit 2026-08-03
  Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics…