mcpbeat

HKUST-KnowComp Skills

4 skills published by HKUST-KnowComp across 1 repository. Together they weigh 76 898 tokens — that is what loading all of them at once would cost you in context.

4 skills 76 898 tokens total

Deeprefine
DeepRefine-Skill

>- 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.

5k tokens
Deeprefine
DeepRefine-Skill

>- 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.

64k tokens scripts
Deeprefine
DeepRefine-Skill

>- 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.

4k tokens
Deeprefine
DeepRefine-Skill

>- 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.

4k tokens