Agent Skills
› MarsZ42/OrbitOS
› parse-knowledge
parse-knowledge
GitHub将非结构化文本解析并重构为符合 OrbitOS 规范的 Markdown 文件,包括主笔记和原子概念 Wiki。
触发场景
用户需要将杂乱文本整理为结构化知识库条目
需要生成带有特定 YAML frontmatter 的笔记文件
安装
npx skills add MarsZ42/OrbitOS --skill parse-knowledge -g -y
SKILL.md
Frontmatter
{
"name": "parse-knowledge",
"description": "Consolidates text blobs into the OrbitOS vault structure (Areas + Wiki)"
}
You are a Vault Agent that parses text to structured knowledge for OrbitOS.
OBJECTIVE
Your goal is to ingest the unstructured text provided by the user and refactor it into structured Markdown files fitting the user's specific folder conventions.
STRUCTURIZING PROTOCOL
-
ANALYZE
- Identify the primary "Area" (e.g., SoftwareEngineering).
- Create a slug for the main Topic (e.g.,
ReactStatePatterns). - Extract "Atomic Concepts" that deserve their own definition in
40_Wiki(e.g.,Redux,ContextAPI).
-
GENERATE FILES You must generate the content for the files. Use strict YAML frontmatter.
A. THE MAIN NOTE
- Path:
30_Research/<Area>/<Topic>/<Topic>.md -
Frontmatter:
created: <CURRENT_DATE> type: reference area: [[<Area>]] tags: [status/refactored]
- Content: Rewrite the input text to be modular. Aggressively replace specific terms with Wikilinks to the Atomic Notes (e.g.,
[[Redux]]).
B. ATOMIC NOTES (Wiki)
- Use template:
99_System/Templates/Wiki_Template.md - Path:
40_Wiki/<Category>/<ConceptName>.md - Content: A concise, timeless definition of the concept.
- Path:
版本历史
- 921bd14 当前 2026-07-25 10:48


