Agent skill

LLM Wiki

by staruhub in staruhub/ClaudeSkills

Build and maintain a structured LLM-generated wiki for any codebase.

MITAuto-check passedKnowledge Management

Install LLM Wiki

skills CLI
$ npx skills add staruhub/ClaudeSkills --skill llm-wiki -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install staruhub/ClaudeSkills llm-wiki --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/staruhub/ClaudeSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/llm-wiki .claude/skills/llm-wiki && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
llm-wiki
GitHub stars
728
Token cost
~1.6k tokens
SKILL.md length
697 words
Files
3 (incl. references)
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

Build and maintain a structured LLM-generated wiki for any codebase.

  • Works in 5 steps: Reconnaissance → Skeleton → Core Articles → …
  • The user asks to analyze/understand/document a codebase
  • SKILL.md covers Mode Detection, Full Build Workflow, Update Workflow and Writing Guidelines, plus 3 more sections
  • Calls git

What it does

LLM Wiki is an agent skill from staruhub/ClaudeSkills. Build and maintain a structured LLM-generated wiki for any codebase. Use when the user asks to analyze/understand/document a codebase, build a code wiki, create project documentation from source, or update an existing .llm-wiki. Triggers on phrases like "build wiki", "analyze this codebase", "document this project", "update wiki", "llm-wiki", or when entering an unfamiliar project that has no .llm-wiki yet.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/article-templates.md` and `references/wiki-schema.md`).

It sits in Knowledge Management, covering LLM wikis. The repository describes itself as: 13 curated Agent Skills for research, product decisions, decks, publishing, audits, and more — portable across skills-compatible agents. The licence is MIT.

When your agent uses it

  • The user asks to analyze/understand/document a codebase
  • Build a code wiki
  • Create project documentation from source
  • Update an existing .llm-wiki

Example prompts

  • “build wiki”
  • “analyze this codebase”
  • “document this project”
  • “/llm-wiki”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Reconnaissance
  2. Skeleton
  3. Core Articles
  4. Index and Cross-link
  5. Lint

What it can do on your machine

Read from SKILL.md and the folder at commit 66e02d2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • gist.github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

LLM Wiki loads about 1.6k tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 697 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from staruhub/ClaudeSkills at commit 66e02d2, republished under its MIT licence (© staruhub). 697 words, ~1,630 tokens.

Download SKILL.mdSave it as .claude/skills/llm-wiki/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
llm-wiki
description
Build and maintain a structured LLM-generated wiki for any codebase. Use when the user asks to analyze/understand/document a codebase, build a code wiki, create project documentation from source, or update an existing .llm-wiki. Triggers on phrases like "build wiki", "analyze this codebase", "document this project", "update wiki", "llm-wiki", or when entering an unfamiliar project that has no .llm-wiki yet.

LLM Wiki for Codebases

Build a persistent, interlinked markdown wiki that captures the architecture, modules, patterns, and APIs of a codebase. The wiki lives in .llm-wiki/ at the project root. Humans curate and direct; the LLM handles all bookkeeping.

Based on Andrej Karpathy's LLM Wiki pattern: raw sources are "compiled" into a structured wiki that compounds over time.

Mode Detection

Determine the mode based on current state:

  • No .llm-wiki/ directory exists -> Full Build mode
  • .llm-wiki/ exists -> Update mode (diff and refresh)

Full Build Workflow

Phase 1: Reconnaissance
  1. Read top-level files: README, package.json/Cargo.toml/go.mod/pyproject.toml/build.gradle etc.
  2. Run find or Glob to map the directory tree (ignore node_modules, .git, vendor, dist, build, pycache, .venv)
  3. Identify: language(s), framework(s), build system, entry point(s), test framework
  4. Count files per directory to gauge module boundaries
  5. Read CLAUDE.md / AGENTS.md / .cursor/rules if present - they contain valuable architectural context

Record findings in .llm-wiki/_schema.md (see references/wiki-schema.md for format).

Phase 2: Skeleton

Create the directory structure:

.llm-wiki/
  _schema.md          # Wiki conventions and project metadata
  _index.md           # Content-oriented catalog by category
  _log.md             # Chronological build/update log
  architecture/       # High-level design docs
  modules/            # Per-module deep dives
  concepts/           # Cross-cutting concepts (auth, caching, error handling...)
  apis/               # API surface docs (REST endpoints, CLI commands, exported functions)
  guides/             # How-to guides (setup, deployment, testing)
Phase 3: Core Articles

Write articles in priority order. See references/article-templates.md for templates.

Priority 1 - Architecture:

  • architecture/overview.md - System architecture, component diagram (ASCII), tech stack
  • architecture/data-flow.md - How data flows through the system
  • architecture/directory-structure.md - Annotated directory tree

Priority 2 - Modules:

  • One modules/<name>.md per major module/package/directory
  • Cover: purpose, key files, public interface, internal patterns, dependencies

Priority 3 - Concepts:

  • Cross-cutting concerns that span modules (auth, logging, error handling, state management, config)
  • One concepts/<name>.md per concept

Priority 4 - APIs:

  • External-facing API surfaces (REST routes, CLI commands, SDK exports)
  • One apis/<name>.md per API group

Priority 5 - Guides:

  • guides/setup.md - Dev environment setup
  • guides/testing.md - How to run and write tests
  • Other guides as relevant
  1. Build _index.md - organized by category with one-line descriptions and links
  2. Ensure every article has a ## See Also section linking to related articles
  3. Add backlinks: if A references B, B should reference A
Phase 5: Lint

Run a health check over the wiki:

  • Broken internal links (references to non-existent .md files)
  • Orphan pages (not linked from _index.md or any other page)
  • Missing coverage (directories/modules with no corresponding article)
  • Stale references (mentions of files/functions that don't exist in codebase)
  • Inconsistent terminology

Fix issues found. Log the lint run in _log.md.

Update Workflow

When .llm-wiki/ already exists:

  1. Read _schema.md to understand project metadata and conventions
  2. Read _log.md to see last update timestamp
  3. Detect changes since last wiki build:
    • git log --since="<last_update>" --name-status if git available
    • Otherwise, compare directory tree against architecture/directory-structure.md
  4. Triage changes:
    • New files/directories -> create new articles or update existing ones
    • Modified files -> re-read and update affected articles
    • Deleted files -> remove references, mark articles for cleanup
    • Renamed/moved files -> update paths in all referencing articles
  5. Update affected articles - re-read source, rewrite sections as needed
  6. Update _index.md if new articles added or old ones removed
  7. Run lint (same as Phase 5 above)
  8. Append to _log.md with timestamp, summary of changes
Show full SKILL.md (230 more words)Show less

Writing Guidelines

  • Be factual: describe what the code does, not what it should do. Cite file paths and line ranges.
  • Use code snippets: short inline examples from actual source, not invented ones.
  • Link aggressively: every mention of another module/concept should be a markdown link to its article.
  • Keep articles focused: one topic per article, 100-500 lines. Split if longer.
  • Frontmatter: every article starts with a YAML frontmatter block:
    yaml
    ---
    title: Module Name
    updated: 2026-04-09
    sources:
      - src/module/index.ts
      - src/module/utils.ts
    ---
  • ASCII diagrams over external images - they live in version control and render anywhere.
  • Language: match the project's primary language. If the codebase comments are in English, write in English. If Chinese, write in Chinese.

Agent Coordination

For large codebases (>500 source files), consider dispatching parallel agents:

  • Agent per top-level module to write module articles concurrently
  • One agent for architecture overview after modules are documented
  • One agent for cross-linking and lint

Gitignore

Add .llm-wiki/ to .gitignore only if the user prefers it. By default, the wiki is intended to be committed alongside the code so the team benefits.

Key Principles (from Karpathy)

  1. The wiki is the LLM's domain - humans rarely edit it directly
  2. Knowledge compounds - each query and exploration enriches the wiki
  3. Index files are critical - _index.md enables the LLM to navigate efficiently
  4. Lint regularly - catch rot before it spreads
  5. Log everything - _log.md provides temporal context for future updates

© staruhub, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in llm-wiki of staruhub/ClaudeSkills.

  • SKILL.md
  • references/article-templates.md
  • references/wiki-schema.md

Open the folder on GitHubat commit 66e02d2

Compare with similar skills

LLM Wiki next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

LLM Wiki compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
LLM Wiki this skillstaruhub/ClaudeSkills728—~1.6kAutomated safety check: PassMIT
Karpathy LLM WikiAstro-Han/karpathy-llm-wiki2.5k—~3.6kAutomated safety check: PassMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
Wiki Builderrohitg00/pro-workflow2.9k—~1kAutomated safety check: PassNone
Codex History IngestAr9av/obsidian-wiki3.5k—~2.2kAutomated safety check: NotesMIT
Arkon Editnduckmink/arkon1.5k—~1.6kAutomated safety check: PassCustom licence

Similar skills

  • Karpathy LLM Wiki

    Astro-Han/karpathy-llm-wiki

    A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.

    2.5k GitHub stars~3.6k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed
  • LLM Wiki

    lewislulu/llm-wiki-skill

    Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…

    655 GitHub stars~3.7k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed
  • Wiki Builder

    rohitg00/pro-workflow

    Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base.

    2.9k GitHub stars~1k tokensUpdated 11 days ago
    Knowledge ManagementAuto-check passed
  • Codex History Ingest

    Ar9av/obsidian-wiki

    Ingest Codex CLI conversation/session history into Obsidian as distilled knowledge.

    3.5k GitHub stars~2.2k tokensUpdated 2 days ago
    Knowledge ManagementAuto-check: notes
  • Arkon Edit

    nduckmink/arkon

    Propose or directly apply edits to Arkon wiki pages, including proposing brand new pages.

    1.5k GitHub stars~1.6k tokensUpdated 4 mo ago
    Knowledge ManagementAuto-check passed
  • Research Wiki Builder

    dair-ai/dair-academy-plugins

    Creates and maintains configurable research wikis: scaffold a folder, add sources, compile pages and indexes, and file query answers back.

    614 GitHub stars~1.3k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed

More from staruhub/ClaudeSkills

All 20 skills in this repo
  • Deep Research

    staruhub/ClaudeSkills

    A skill your agent uses when the user wants an evidence-based research memo, literature review, market/policy/technical landscape, or a multi-source decision brief with citations, trade-offs, and a…

    728 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Wechat Article Writer

    staruhub/ClaudeSkills

    专业微信公众号文章助手,支持四个独立且可组合模式:article 写正文;image-prompts 从文章生成版本化、provider-neutral 的图片提示词 manifest 与稳定占位符,但不调用生图;layout 把文章和 manifest 确定性转换为微信安全的内联 HTML;full-pipeline…

    728 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • A Share Analyst

    staruhub/ClaudeSkills

    A股分析研究助手,提供行情数据获取与技术面/基本面分析框架(仅供研究参考,不构成投资建议)。适用于:(1) 获取A股行情和历史数据,(2) 技术面分析(K线形态、MACD、KDJ、RSI、布林带等),(3) 基本面分析(财务指标、估值分析),(4) 板块热点追踪,(5) 选股策略筛选与量化因子分析,(6)…

    728 GitHub stars~871 tokensUpdated 1 mo ago
    Auto-check passed
  • C Drive Cleaner

    staruhub/ClaudeSkills

    Windows C盘清理和磁盘空间管理。当用户说C盘满了、磁盘空间不足、清理临时文件/缓存/回收站/系统日志、查找大文件、分析磁盘占用时使用。仅适用于 Windows 环境。不用于:macOS/Linux 磁盘清理、卸载软件(引导用户走系统卸载)、清理用户个人文件(只报告位置,删除决定权在用户)。

    728 GitHub stars~518 tokensUpdated 1 mo ago
    Auto-check passed
  • Gaokao Expert

    staruhub/ClaudeSkills

    资深高考命题专家助手,提供专业的命题指导和评审服务。适用于创作高考试题、评审试题质量、分析试卷结构、了解命题趋势等场景。结合文档工具提取解压文件,使用网络搜索了解当年最新命题趋势,使用分析工具评估题目质量和试卷结构。涵盖"一核四层四翼"评价体系、题型规范、评分标准、命题流程等多个维度。不用于:大学/考研/中考命题(体系不同,仅可借鉴)、日常作业题编写、直接替考生解题。

    728 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Mineru PDF Parser

    staruhub/ClaudeSkills

    用 MinerU 将复杂PDF文档转换为LLM友好的Markdown/JSON格式。适用于:(1) PDF转Markdown/JSON,(2) 提取PDF中的文本、表格、公式、图像,(3) 解析学术论文、技术文档、商业报告,(4) 为RAG应用准备文档数据,(5) 批量处理PDF。触发关键词:"PDF解析"、"PDF转Markdown"、"提取PDF表格/公式"、"MinerU"、"parse…

    728 GitHub stars~671 tokensUpdated 1 mo ago
    Auto-check passed

Questions about LLM Wiki

What does LLM Wiki do?

Build and maintain a structured LLM-generated wiki for any codebase. LLM Wiki is an agent skill from staruhub/ClaudeSkills. Build and maintain a structured LLM-generated wiki for any codebase.

When should I use LLM Wiki?

LLM Wiki fits situations like: the user asks to analyze/understand/document a codebase; build a code wiki; create project documentation from source; update an existing .llm-wiki.

How do I install LLM Wiki in Claude Code?

Run `npx skills add staruhub/ClaudeSkills --skill llm-wiki -a claude-code`. Or copy the skill folder (llm-wiki in staruhub/ClaudeSkills) into .claude/skills/llm-wiki in your project. Claude Code loads it when a task matches its description.

How do I install LLM Wiki in Codex?

Run `npx skills add staruhub/ClaudeSkills --skill llm-wiki -a codex`. Or copy the skill folder (llm-wiki in staruhub/ClaudeSkills) into .agents/skills/llm-wiki in your project. Codex loads it when a task matches its description.

Can I use LLM Wiki in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add staruhub/ClaudeSkills --skill llm-wiki -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/llm-wiki, .gemini/skills/llm-wiki, .github/skills/llm-wiki and .opencode/skills/llm-wiki in your project.

What does LLM Wiki need to run?

Going by SKILL.md and its folder, LLM Wiki needs the command-line tools its instructions call (git).

Does LLM Wiki access the network?

SKILL.md names 1 domain. As links in the text: gist.github.com. This is read from the text; nothing was executed.

Is LLM Wiki safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does LLM Wiki use?

LLM Wiki is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does LLM Wiki use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2k tokens, read only when the agent opens those files.

What are the alternatives to LLM Wiki?

Skills that share tags, products or a category with LLM Wiki: Karpathy LLM Wiki (Astro-Han/karpathy-llm-wiki, 2.5k stars), LLM Wiki (lewislulu/llm-wiki-skill, 655 stars), Wiki Builder (rohitg00/pro-workflow, 2.9k stars) and Codex History Ingest (Ar9av/obsidian-wiki, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains LLM Wiki?

staruhub (a GitHub user) maintains it in staruhub/ClaudeSkills, which has 728 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on August 13, 2026.

Source: staruhub/ClaudeSkills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.