document-object-split
97 / 100 · Low risk
Fine to try.
根据数字员工当前挂载的 Ontology 对象类型(Bug、需求管理、产品、订单等), 对文档内容进行结构化拆分:OpenClaw 从当前数字员工上下文取得 Ontology 对象编码(objectCode), 再经 get_object_detail.py 调用 byaiService /ontology/object/detail 获取各类型的 schema(object_name、properties), 据此对文档分类并抽取独立实例——每个可拆分实例在对应 page_prefix 下形成 一个独立 gbrain page(N 实例 = N page);page 字段结构由接口返回的 properties 定义, 字段取值结合文档内容适当抽取填写。完成后输出 page 清单并询问是否导出。 再次拆分时按 external_id 匹配已有 page 更新。
What this skill can do
Runs commands on your computer
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'document-object-split' ] || [ -L ~/.agents/skills/'document-object-split' ]; then echo 'A skill folder named document-object-split already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/beyonai/ByClaw' "$d" && git -C "$d" checkout --quiet '97eef801b981038485ccf5774c9a6c4c946e796c' -- 'middleware/builtin/skills/gbrain/references/document-object-split' && mkdir -p ~/.agents/skills && cp -R "$d"/'middleware/builtin/skills/gbrain/references/document-object-split' ~/.agents/skills/'document-object-split' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'document-object-split' ~/.claude/skills/'document-object-split' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/beyonai/ByClaw/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-11 | 97eef80 | 97 |