PandaAIDD/dsh-aidd

README 摘要

dsh-aidd A Claude Science–style research workbench for DeepSeek Harness, tailored for AI-driven drug discovery — cheminformatics / computational biology / molecular design projects. One-liner: dsh-aidd — a Claude Science-style AIDD workbench for DSH: a ReAct research-loop engine (research tools), versioned artifacts with provenance (artifact tools), and 17 skills covering virtual screening / molecular generation / property & ADMET prediction / protein targets / DTI modeling / model reproduction. - ReAct research-loop engine — research init / research state / research hypothesis / research experiment / research findings / research phase / research review / research report , with state persisted in research-manifest.json (question → hypothesis → experiment → observation → analysis → conclusion → next question). AIDD semantics: target hypotheses → screening/generation/modeling experiments → evaluated conclusions → iterate. - Versioned artifacts with provenance — artifact save / artifact list / artifact show / artifact diff / artifact verify / artifact deprecate / artifact reproduce : hit lists, score tables, data-split files , model checkpoints and metric tables are stored as artifact…

分类