OpenAgentSkill Registry Manifest
Skill: arbor
Slug: k-dense-ai-arbor
Category: research
Description: 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.

Agent fit:
- Decision: 100/100 Production-ready
- Primary fit: Research agents
- Role: Primary pick

Supply profile:
- Track: Research and knowledge work
- Scenario: Research agents
- Applicable agents: Claude Code, CLI, Codex, Cursor
- Maintenance: 2d since push
- Risk: Safe to try

Trust:
- Trust score: 84/100 Strong shortlist
- Audit: 89/100 Safe to try

Attribution:
- Status: Registry indexed
- Source: recursive skill source sync
- Creator: K-Dense-AI
- Claim URL: https://www.openagentskill.com/skills/k-dense-ai-arbor#claim-this-skill

Install:
npx skills add K-Dense-AI/scientific-agent-skills --skill arbor

URLs:
- Web: https://www.openagentskill.com/skills/k-dense-ai-arbor
- API: https://www.openagentskill.com/api/agent/skills/k-dense-ai-arbor
- Install API: https://www.openagentskill.com/api/skills/k-dense-ai-arbor/install
- Repository: https://github.com/K-Dense-AI/scientific-agent-skills/tree/main/skills/arbor