agentleFS
fzs356113-ossfzs356113-oss/dsh-knowledge-forge/skills/knowledge-forge/SKILL.md

knowledge-forge

Skill0 starsChanged 3 months agoMITView on GitHub

把 Obsidian 风格知识库当作"会生长的有机体"来维护。当用户要求"编译""归档""整理知识库""知识库体检""代谢""回顾""织网""问答"或提到 raw、wiki、回顾队列、孤儿笔记、死链时触发。本技能编排 5 个 DSH 工作流(compile/link-weaver/metabolism/qa-archive/health-check)对 vault 做递进编译、织网、代谢回顾、问答归档与体检。

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. chipoto69/claude-skills★ 2same name
    2. ANGJustinl/knowledge-forge-skill★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

Files
SKILL.md

Knowledge Forge 技能

定位

Knowledge Forge 把知识库(vault)当作会生长的有机体: raw/ 是食物,compile 是消化,link-weaver 是血管,metabolism 是呼吸,qa-archive 是免疫,health-check 是体检。你(DSH 智能体)是它的园丁: 用 5 个工作流喂养它,它就持续生长。

前置条件

  • 需要用户提供 vaultRoot(知识库根目录的绝对正斜杠路径,如 E:/vault);若用户只说了仓库名,先用 glob 定位。
  • 工作流以 DSH workflow 工具运行: meta 参数粘贴对应 <name>.meta.json 内容,script 参数粘贴 <name>.workflow.js 内容,args 传 JSON。

5 个工作流的调用时机

场景工作流args
用户丢了一批新素材到 raw/,要求"编译/归档/整理知识库/生成 wiki"compile{"vaultRoot": "..."}
体检发现孤儿笔记,或用户说"织网/补链接"link-weaver{"vaultRoot": "...", "maxNotes": 10}
用户说"做一次代谢/回顾/复习",或 06-回顾/回顾队列.md 有到期项metabolism{"vaultRoot": "...", "maxItems": 5}
用户对知识库提问("问知识库/检索"),或希望答案沉淀回 wikiqa-archive{"vaultRoot": "...", "question": "..."}
用户说"体检/健康检查/审计/找死链",或大规模改动后health-check{"vaultRoot": "..."}

执行纪律(传给每个子代理的要求)

  1. 路径一律绝对正斜杠(如 E:/vault/wiki/concepts/foo.md),绝不使用相对路径;
  2. 禁止编造: 摘要、统计数字、[[wikilink]] 目标必须来自子代理实际读到的文件;
  3. 检索不足就明说: 找不到相关笔记、素材不足、无法回答时如实说明,不许硬编;
  4. 编排脚本不读写文件: 所有文件读写由子代理完成。

典型会话流程

  1. 用户: "我的知识库该整理了"
  2. 先跑 health-check 拿到现状 → 把报告要点讲给用户
  3. 跑 compile(如果有新素材)消化 raw/
  4. 跑 link-weaver 织网(按体检发现的孤儿)
  5. 跑 metabolism 消化到期回顾
  6. 汇总: 本轮代谢了多少素材、补了多少链接、清了多少死链、回顾了几条笔记

注意

  • 工作流返回的是 JSON 汇总,要向用户转述成可读结论;
  • 子代理失败会返回 null(已由脚本 filter 处理),向用户如实报告哪部分失败、建议重跑;
  • 技能只负责调度与解释,不代替用户决定"删哪条笔记"——把建议交给用户。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.