arbor

SKILLWorkflowcommunity
v0.0.0K-Dense-AIMITUpdated 1d agoSource →

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 overf

Community-submitted skill. Not yet reviewed by the Forge team. Full prompt content may not be available.Request review →
34kRepo stars
1Clients
1Formats
1d agoLast update
Skill
AuthorK-Dense-AI
Version0.0.0
LicenseMIT
CategoryWorkflow
Formatsskill.md
PromptOpen (see Prompt tab)
Compatibility
Claude✓ Supported
Cursor
Copilot
ChatGPT
Gemini
About

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", "b

Keywords
skillclaude