LLM Wiki
个人知识库构建系统（基于 Karpathy llm-wiki 方法论）。让 AI 持续构建和维护你的知识库， 支持多种素材源（网页、推特、公众号、小红书、知乎、YouTube、PDF、本地文件）， 自动整理为结构化的 wiki。 触发条件：用户明确提到"知识库"、"wiki"、"llm-wiki"，或要求对已初始化的知识库执行 消化、查询、健康检查等操作。不要在用户只是要求"总结这篇文章"时触发——必须是明确的 知识库相关意图。
Install
npx skills add sdyckjq-lab/llm-wiki-skill --skill llm-wikigit clone --depth 1 https://github.com/sdyckjq-lab/llm-wiki-skill.git /tmp/llm-wiki-skill
mkdir -p ~/.claude/skills
cp -r /tmp/llm-wiki-skill/. ~/.claude/skills/llm-wikiPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# llm-wiki — 个人知识库构建系统
> 把碎片化的信息变成持续积累、互相链接的知识库。你只需要提供素材，AI 做所有的整理工作。
## 这个 skill 做什么
llm-wiki 帮你构建一个**持续增长的个人知识库**。它不是传统的笔记软件，而是一个让 AI 帮你维护的 wiki 系统：
- 你给素材（链接、文件、文本），AI 提取核心知识并整理成互相链接的 wiki 页面
- 知识库随着每次使用变得越来越丰富，而不是每次重新开始
- 所有内容都是本地 markdown 文件，用 Obsidian 或任何编辑器都能查看
## 核心理念
传统方式（RAG/聊天记录）的问题：每次问问题，AI 都要从头阅读原始文件，没有积累。知识库的价值在于**知识被编译一次，然后持续维护**，而不是每次重新推导。
## 快速开始
告诉用户这两步就够了：
1. **初始化**：说"帮我初始化一个知识库"
2. **添加素材**：给一个链接或文件，说"帮我消化这篇"
---
## Script Directory
Scripts located in `scripts/` subdirectory.
**Path Resolution**:
1. `SKILL_DIR` = this SKILL.md's directory
2. Script path = `${SKILL_DIR}/scripts/<script-name>`
---
## 依赖检查
核心主线（本地文件、纯文本、已有知识库操作）默认不需要这些提取依赖。
只有当用户给的是 URL 类来源，并且明确要自动提取网页 / X / 微信公众号 / YouTube / 知乎内容时，才检查以下可选依赖。
如果缺失，提示用户运行：
```bash
bash ${SKILL_DIR}/install.sh --platform <当前平台> --with-optional-adapters
```
可选依赖 skill / 工具：
- `baoyu-url-to-markdown` — 普通网页、X/Twitter、部分知乎提取
- `wechat-article-to-markdown` — 微信公众号提取
- `youtube-transcript` — YouTube 字幕提取
即使这些依赖缺失，skill 仍可工作（用户可以直接提供本地文件、粘贴文本，或改走手动入口）。
## 外挂状态模型
外挂失败统一分成 `not_installed / env_unavailable / runtime_failed / unsupported / empty_result` 五类。
所有需要枚举来源、读取 `source_label`、`raw_dir`、`adapter_name`、`fallback_hint` 的地方，都先读来源总表：
```bash
bash ${SKILL_DIR}/scripts/source-registry.sh list
```
需要拿单个来源的定义时，用：
```bash
bash ${SKILL_DIR}/scripts/source-registry.sh get <source_id>
```
对 URL 类来源，先运行：
```bash
bash ${SKILL_DIR}/scripts/adapter-state.sh check <source_id>
```Details
- Skill name
llm-wiki- Repository
- sdyckjq-lab/llm-wiki-skill
- Repo updated
- 27 July 2026
FAQ
What does the LLM Wiki skill do?
个人知识库构建系统（基于 Karpathy llm-wiki 方法论）。让 AI 持续构建和维护你的知识库， 支持多种素材源（网页、推特、公众号、小红书、知乎、YouTube、PDF、本地文件）， 自动整理为结构化的 wiki。 触发条件：用户明确提到"知识库"、"wiki"、"llm-wiki"，或要求对已初始化的知识库执行 消化、查询、健康检查等操作。不要在用户只是要求"总结这篇文章"时触发——必须是明确的 知识库相关意图。
How do I install the LLM Wiki skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add sdyckjq-lab/llm-wiki-skill --skill llm-wiki. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is LLM Wiki popular?
It lives in sdyckjq-lab/llm-wiki-skill, which has 2,573 GitHub stars and 301 forks.
Related skills
Agent Skills Platform
2.4kFrancyJGLisboa/agent-skills-platform
Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill, audit this skill, is this skill safe, vet a skill before installing, what does this skill access. Supports single skills, multi-agent suites, transcript
Create Ex
2.6kperkfly/ex-skill
Distill an ex-girlfriend into an AI Skill. Import WeChat/iMessage/SMS/photos, generate Memories + Persona, with continuous evolution. | 把前任蒸馏成 AI Skill，导入微信/iMessage/短信/照片，生成共同记忆 + Persona，支持持续进化。
Agents Best Practices
2.4kDenisSergeevitch/agents-best-practices
Use this skill when designing, generating an MVP blueprint for, auditing, troubleshooting, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, record provenance, interactive presentation, user-memory lifecycles, environment-adaptive tools, speculative tool execution, late-bound capabilities, permissions, system prompts, planning, goals, always-on agents and durable runtime, adaptive agent teams, context compaction, memory, skills, MCP/external connectors, public-boa
Subagent Driven Development
1.8kNeoLabHQ/context-engineering-kit
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
Openclaw Master Skills
2.2kLeoYeAI/openclaw-master-skills
A curated collection of 2703+ best OpenClaw skills — AI tools, productivity, marketing, frontend, mobile, backend, DevOps and more. Daily updated by MyClaw.ai — Powered by MyClaw.ai
Prompt Engineering
1.8kNeoLabHQ/context-engineering-kit
Learn and apply prompt engineering techniques and patterns. Master the art of crafting effective prompts for LLMs.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.