BigHugger
sk Skill · HKUST-KnowComp

deeprefine

Agent-native DeepRefine refinement loop — same control flow as DeepRefine.refine(), graphify search instead of FAISS, session LLM, dry-run review before approved graph writes.

installs 8w
0
30-day movement
starts with the next reading
Related entries
2
Connections
0
jsonbashPython
Host repository
HKUST-KnowComp/DeepRefine-Skill
Invocable by
model
Host stars
93
Host language
Python