Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\
This skill should be used when the user asks to "audit a wiki vault", "check dead links or orphan pages", "inspect knowledge base structure", "审计 wiki", "检查知识库结构", "看看有没有死链或孤立页", or "检查导航、frontmatter 和噪音回流". It audits a markdown/wiki knowledge base by reading a vault profile first and then checking structure, navigation, metadata, boundary drift, noise regression, and stray markdown files at the vault root.
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。 --- # 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 首次使用时，检查以下依赖是否已安装。如果缺失，提示用户运行安装： ```bash bash ${SKILL_DIR}/setup.sh ``` 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 即使部分依赖缺失，skill 仍可工作（用户可以手动粘贴文本内容）。 --- ## 工作流路由 根据用户的意图，路由到对应的工作流： | 用户意图关键词 | 工作流 | |---|---| | "初始化知识库"、"新建 wiki"、"创建知识库" | → **init** | | URL / 文件路径 / "添加素材"、"消化"、"整理" / 直接给链接 | → **ingest** | | "批量消化"、"把这些都整理" / 给了文件夹路径 | → **batch-ingest** | | "关于 XX"、"查询"、"XX 是什么"、"总结一下" | → **query** | | "给我讲讲 XX"、"深度分析 XX"、"综述 XX"、"digest XX" | → **digest** | | "检查知识库"、"健康检查"、"lint" | → **lint** | | "知识库状态"、"现在有什么"、"有多少素材" | → **status** | | "画个知识图谱"、"看看关联图"、"graph"、"知识库地图" | → **graph** | **重要**：如果用户直接给了一个 URL 或文件，但没有明确说要做什么，默认走 **ingest** 工作流。如果知识库还不存在，先自动走 **init** 再走 **ingest**。 --- ## 通用前置检查 除 `init` 外，其他工作流默认先执行这段检查： 1. 先检查**当前工作目录**是否包含 `.wiki-schema.md` - 如果包含 → 用当前目录作为知识库根路径 - 如果不包含 → 回退到读取 `~/.llm-wiki-path` 2. 如果两者都没有： - `ingest` / `batch-ingest` → 先运行 `init` - `query` / `lint` / `status` / `digest` / `graph` → 提示用户先初始化知识库 3. 读取知识库根目录下的 `.wiki-schema.md` 4. 从 `.wiki-schema.md` 的"语言"字段判断 `WIKI_LANG` - `语言：中文` → `WIKI
Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\
One-time integration: set up the llm-wiki daemon, configure backend profiles, register the MCP server with an agent framework, and handle conflicts with pre-MCP wiki skills. Triggers: 'set up llm wiki', 'integrate llm-wiki', 'configure wiki MCP', 'register wiki server'.
Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\
Autonomous Obsidian vault management using the PARA + LLM Wiki pattern. Three operations: ingest (inbox to wiki + PARA routing), query (cross-vault synthesis), lint (health check). Scheduled via CronCreate 4x/day. Filesystem-only -- no Obsidian app dependency. Activate when the user mentions 'ingest', 'vault', 'wiki page', 'obsidian brain', 'vault lint', 'inbox', 'wiki index', 'knowledge base query', or wants to process, organize, query, or audit their Obsidian vault.
Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\
Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: \"Index this repo\", \"Reanalyze the codebase\", \"Generate a wiki\
LLM-compiled knowledge base manager. Activates when user works with wiki directories, mentions knowledge base management, asks knowledge questions in a project with a wiki, wants to ingest/compile/query/lint knowledge, or uses /wiki commands. Also activates when user says "wiki", "knowledge base", "ingest", "compile wiki", "add to wiki", "search wiki", or asks a factual question in a directory containing .wiki/ or when ~/wiki/ exists.
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
