Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses persistent hypotheses, isolated experiments, evidence propagation and held-out candidate comparison for multi-experiment research runs.
Install
npx skills add K-Dense-AI/scientific-agent-skills --skill arbornpx skills add K-Dense-AI/scientific-agent-skills --skill arbor -a claude-code -gnpx skills add K-Dense-AI/scientific-agent-skills --skill arbor -a codex -ggemini skills install https://github.com/K-Dense-AI/scientific-agent-skills.git --path skills/arborgh skill install K-Dense-AI/scientific-agent-skills arborgit clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-skills /tmp/K-Dense-AI__scientific-agent-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/K-Dense-AI__scientific-agent-skills/skills/arbor ~/.claude/skills/arbor # Claude Code
cp -R /tmp/K-Dense-AI__scientific-agent-skills/skills/arbor ~/.agents/skills/arbor # Codex, Cursor, Gemini CLI, Copilot, OpenCode