An agent skill to evolve the quality of LLM-Wiki (Graphify) at test time.
This repository also configures its own agents. See what DeepRefine-Skill tells them →
HKUST-KnowComp/DeepRefine-Skill
Skill Claude Code
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.
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.
HKUST-KnowComp/DeepRefine-Skill
Skill Claude Code
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.
HKUST-KnowComp/DeepRefine-Skill
Skill Codex
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.
HKUST-KnowComp/DeepRefine-Skill
Skill Claude Code
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.
HKUST-KnowComp/DeepRefine-Skill
Skill Claude Code
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.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: