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.
- Version
- 1.2
- License
- MIT license
Pinned to revision 70a605012eee, so it is the text this page describes rather than whatever the author pushed since.
Pre-approved tools experimental
Experimental field. Support varies between clients, so this list is what the author declared, not what your client will enforce.
- Read
- Write
- Edit
- Bash
- Agent
Files
- skills/arbor/SKILL.md
- skills/arbor/references/arbor-upstream.md
- skills/arbor/references/executor-brief.md
- skills/arbor/references/htr-methodology.md
- skills/arbor/references/report-template.md
- skills/arbor/scripts/tree.py
Every link opens the file at its source, pinned to the revision this page describes.