wiki-init
Skill0 starsChanged 3 months agoMITView on GitHub
初始化 LLM Wiki 知识库目录结构。创建 raw/、wiki/ 及子目录(概念/实体/摘要/综合), 生成 index.md 和 log.md,确认并配置 rawPath。首次使用知识库前必须执行。
10 other projects use a version of this.
Adopted by
Most recently taken up by
- barakgut/llm-wikitheir own version, first seen Nov 1, 2026
- ProduktEntdecker/enterprise-memory-startertheir own version, first seen Nov 1, 2026
- rumi-chan/llm-wikitheir own version, first seen Oct 25, 2026
- juanitourquiza/shipframetheir own version, first seen Oct 23, 2026
- foryouself83/harness-tiertheir own version, first seen Oct 13, 2026
- chris-santiago/ml-wikitheir own version, first seen Jul 16, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- kfchou/wiki-skills★ 189same name
- bozhouDev/bozhou-skills★ 78same name
- foryouself83/harness-tier★ 10same name
- crabin/llm-wiki★ 8same name
- juanitourquiza/shipframe★ 4same name
- ProduktEntdecker/enterprise-memory-starter★ 2same name
- barakgut/llm-wiki★ 1same name
- rumi-chan/llm-wiki★ 1same name
- chris-santiago/ml-wiki★ 0same name
- graypirate/Alexandria★ 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.
In this repository4 other files it gives its agents.
- wiki-classifySkill
- wiki-ingestSkill
- wiki-lintSkill
- wiki-querySkill
The file
Files
/wiki-init — 初始化 LLM Wiki 知识库
初始化一个新的 LLM Wiki 知识库项目。
流程
- 创建目录结构:
raw/— 原始资料(不可变)wiki/— LLM 维护的笔记wiki/概念/— 方法论、架构模式、第一性原理wiki/实体/— 人名、公司、工具软件、项目wiki/摘要/— 针对 raw 文件的一对一核心观点提炼wiki/综合/— 深度研究报告
- 创建系统文件:
wiki/index.md— 内容目录wiki/log.md— 操作日志
- 询问用户确认 raw 笔记保存目录的绝对路径
- 将
rawPath写入配置文件:- 全局模式:
~/.config/opencode/wiki-config.json - 项目模式:项目根目录
wiki-config.json
- 全局模式:
配置
初始化完成后,wiki-config.json 示例:
{
"scope": "project",
"rawPath": "D:/WorkDev/KnowleageBase/raw",
"kbPath": "D:/WorkDev/KnowleageBase"
}rawPath:raw 原始资料存放目录的绝对路径kbPath:知识库项目根目录的绝对路径(wiki/和AGENTS.md所在位置)
工具使用规则
更新 index.md、log.md 等累积性文件时:
- 必须先用
Read读取当前内容 - 必须用
Edit工具做增量修改(追加、替换) - 禁止用
Write工具覆盖整个文件
Write 工具仅用于:
- 创建全新文件
- 用户明确要求覆盖整个文件
脚本执行优先级
需要执行脚本操作时,按以下顺序选择实现方式:
- Python — 检测到 Python 环境则优先使用
- Linux — Shell 脚本(bash/sh)
- Windows + Git Bash — 用 Git Bash 执行
- Windows(无 Git Bash) — PowerShell
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

