菜单
Normalize extracted paper entities into canonical forms with lightweight audit logs.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Build, query, and visualize literature relationship clusters using Kuzu and Cypher.
Fetch paper metadata from lightweight academic sources like arXiv and save normalized paper JSON records.
Write lightweight graph edges from normalized paper entities into a local graph store.
Build a lightweight local vector-style index record from normalized paper data.
Generate a lightweight structured reflection JSON for a single paper record.
Orchestrate the lightweight academic pipeline by chaining paper-fetch, paper-reflect, and paper-normalize.
| name | paper-normalize |
| description | Normalize extracted paper entities into canonical forms with lightweight audit logs. |
| metadata | {"openclaw":{"emoji":"🧩","requires":{"bins":["python3"]}}} |
Use this skill after paper-reflect when the user wants canonical entities and alias cleanup.
Workflow
python3 /root/openclaw-dev/workspace/scripts/normalize_entities.py <reflection_json_path>/root/openclaw-dev/workspace/data/normalized/audit_log for alias mappings and dedupe actionsNotes