HKUST-KnowComp

7 mods across 2 repositories, 106 stars between them.

deeprefine

02

HKUST-KnowComp/DeepRefine-Skill

Skill Claude CodeCodex

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.

93 9d ago A 42 tokens original MIT

deeprefine

03

HKUST-KnowComp/DeepRefine-Skill

Skill Claude CodeCodex

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.

93 9d ago A 42 tokens original MIT

deeprefine

04

HKUST-KnowComp/DeepRefine-Skill

Skill Claude CodeCodex

Claude Code adapter for the DeepRefine agent-native refinement loop. Use when the user invokes /deeprefine, or asks to refine, diagnose, review, or apply changes to a Graphify / LLM-Wiki knowledge graph. Must follow the canonical DeepRefine skill rules and stop for review before graph writes.

93 9d ago A 68 tokens original MIT

deeprefine

05

HKUST-KnowComp/DeepRefine-Skill

Skill Claude CodeCodex

Codex adapter for the DeepRefine agent-native refinement loop. Use when the user invokes $deeprefine or /deeprefine, or asks to refine, diagnose, review, or apply changes to a Graphify / LLM-Wiki knowledge graph. Must follow the canonical DeepRefine skill rules and stop for review before graph writes.

93 9d ago A 73 tokens copy · 92% MIT

deeprefine

06

HKUST-KnowComp/DeepRefine-Skill

Skill Claude CodeCodex

DeepSeek Harness (dsh) adapter for the DeepRefine agent-native refinement loop. Use when the user invokes /deeprefine, or asks to refine, diagnose, review, or apply changes to a Graphify / LLM-Wiki knowledge graph. Must follow the canonical DeepRefine skill rules and stop for review before graph writes.

93 9d ago A 73 tokens copy · 89% MIT

deeprefine

07

HKUST-KnowComp/DeepRefine-Skill

Skill Claude CodeCodex

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.

93 9d ago A 42 tokens copy · 100% MIT