← 返回 Skills 市场
qomg

Knowledge Base SOP

作者 hormaz · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
46
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install knowledge-base-sop
功能描述
Knowledge base management SOP for ingesting, archiving, linting, and maintaining a personal wiki knowledge base. Use when processing raw documents, bookmarks...
使用说明 (SKILL.md)

Knowledge Base SOP

Directory Structure

  • raw/ — Original, unprocessed materials (web scrapes, bookmark exports, PDFs). Never modify directly.
  • wiki/ — Cleaned, structured core knowledge base (Markdown).
  • outputs/ — Temporary reports, drafts, or exported files.

1. Ingest & Compile

Trigger: New files appear in raw/.

  • Extract core points, entities (names/projects/tech stacks), and logical relationships.
  • Split long text into reasonable paragraphs of structured Markdown (H2/H3 headings, bold key terms).
  • Noise rule: Discard content under 300 words or with no substantive technical/knowledge value. Log the discard.
  • Hallucination guard: Strictly summarize from source. Never fabricate data or conclusions not in the original.

2. Archive

  • File naming: YYYY-MM-DD-core-topic-source.md
  • Obsidian wikilinks: Use [[Concept Name]] for cross-references in wiki pages.
  • Dedup: Before writing, search wiki/ for titles with >90% similarity. If found, append new content as a "supplemental update" at the bottom with a timestamp.
  • See references/archive-rules.md for detailed dedup logic.

3. Bookmark Pipeline

Trigger: raw/bookmarks.html updated.

  1. Parse HTML, extract all \x3Ca> tags (URL, title, meta description).
  2. Headlessly visit each URL to fetch body content (strip ads, nav bars).
  3. Summarize fetched content (≤300 chars), extract 5 keywords.
  4. Generate Markdown cards in wiki/Bookmarks/.
  5. Mark processed entries in the original HTML to prevent re-crawl.

4. Lint & Cleanup

  • Trust levels: All newly ingested wiki pages carry a [[待验证]] tag. Remove only after user confirmation.
  • Dead link detection: Weekly scan of all URLs in wiki/. On HTTP 404 or timeout, add {{dead_link}} marker at page top.
  • Orphan cleanup: Monthly check for pages not linked by any other page. Move to outputs/orphans/.

5. Interaction Constraints

  • Maintain a professional, precise communication style.
  • Before destructive operations (e.g., bulk deletion), present a plan and wait for confirmation.
  • Prioritize local tools. Minimize unnecessary follow-up questions.
安全使用建议
This skill appears safe to install if you want an agent to help maintain a local personal wiki. Use it on a dedicated KB folder, keep backups or version control, review imported pages before trusting them, and clarify whether raw/bookmarks.html may be modified or should be tracked with a separate processed-state file.
功能分析
Type: OpenClaw Skill Name: knowledge-base-sop Version: 1.0.0 The skill bundle defines a standard workflow for personal knowledge management, including document ingestion, bookmark processing, and wiki maintenance. The instructions in SKILL.md and references/archive-rules.md are transparent, align with the stated purpose, and include safety-oriented constraints such as requiring user confirmation for destructive operations and implementing 'hallucination guards' during summarization.
能力评估
Purpose & Capability
The requested behavior matches a personal knowledge-base workflow: ingest raw material, summarize it into Markdown, deduplicate pages, check links, and maintain wiki folders. Users should still expect local file edits and web requests.
Instruction Scope
The scope is mostly bounded to raw/, wiki/, and outputs/, with confirmation required before destructive operations. One instruction conflicts with the raw/ immutability rule by marking processed entries in the original bookmarks HTML.
Install Mechanism
No install spec, code files, required binaries, environment variables, or credentials are present; this is an instruction-only skill.
Credentials
Network fetching of bookmark URLs and weekly link checks are proportionate to the stated bookmark/wiki maintenance purpose, but users should only run it on intended KB folders and URLs.
Persistence & Privilege
The skill creates and updates persistent Markdown pages and markers inside the local wiki workflow, but it does not request credentials, elevated privileges, background services, or hidden persistence.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install knowledge-base-sop
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /knowledge-base-sop 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release: Ingest & compile, archive with dedup, bookmark pipeline, lint & cleanup, trust levels and orphan detection.
元数据
Slug knowledge-base-sop
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Knowledge Base SOP 是什么?

Knowledge base management SOP for ingesting, archiving, linting, and maintaining a personal wiki knowledge base. Use when processing raw documents, bookmarks... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 46 次。

如何安装 Knowledge Base SOP?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install knowledge-base-sop」即可一键安装,无需额外配置。

Knowledge Base SOP 是免费的吗?

是的,Knowledge Base SOP 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Knowledge Base SOP 支持哪些平台?

Knowledge Base SOP 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Knowledge Base SOP?

由 hormaz(@qomg)开发并维护,当前版本 v1.0.0。

💬 留言讨论