Karpathy LLM Wiki
Astro-Han/karpathy-llm-wiki
A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.
Build a persistent compounding wiki from raw sources using the LLM Wiki pattern
$ npx skills add jellydn/my-ai-tools --skill llm-wiki -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jellydn/my-ai-tools llm-wiki --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jellydn/my-ai-tools.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/llm-wiki .claude/skills/llm-wiki && rm -rf skills-srcUse ~/.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/
Install the "llm-wiki" agent skill from https://github.com/jellydn/my-ai-tools/tree/main/skills/llm-wiki into .claude/skills/llm-wiki/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-wiki", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jellydn/my-ai-tools/tree/main/skills/llm-wikiType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jellydn/my-ai-tools --skill llm-wiki -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jellydn/my-ai-tools llm-wiki --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jellydn/my-ai-tools.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/llm-wiki .agents/skills/llm-wiki && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "llm-wiki" agent skill from https://github.com/jellydn/my-ai-tools/tree/main/skills/llm-wiki into .agents/skills/llm-wiki/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-wiki", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jellydn/my-ai-tools --skill llm-wiki -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jellydn/my-ai-tools llm-wiki --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jellydn/my-ai-tools.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/llm-wiki .cursor/skills/llm-wiki && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "llm-wiki" agent skill from https://github.com/jellydn/my-ai-tools/tree/main/skills/llm-wiki into .cursor/skills/llm-wiki/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-wiki", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jellydn/my-ai-tools.git --path skills/llm-wiki--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jellydn/my-ai-tools --skill llm-wiki -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jellydn/my-ai-tools llm-wiki --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jellydn/my-ai-tools.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/llm-wiki .gemini/skills/llm-wiki && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "llm-wiki" agent skill from https://github.com/jellydn/my-ai-tools/tree/main/skills/llm-wiki into .gemini/skills/llm-wiki/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-wiki", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jellydn/my-ai-tools llm-wikiInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jellydn/my-ai-tools --skill llm-wiki -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jellydn/my-ai-tools.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/llm-wiki .github/skills/llm-wiki && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "llm-wiki" agent skill from https://github.com/jellydn/my-ai-tools/tree/main/skills/llm-wiki into .github/skills/llm-wiki/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-wiki", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jellydn/my-ai-tools --skill llm-wiki -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jellydn/my-ai-tools llm-wiki --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jellydn/my-ai-tools.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/llm-wiki .opencode/skills/llm-wiki && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "llm-wiki" agent skill from https://github.com/jellydn/my-ai-tools/tree/main/skills/llm-wiki into .opencode/skills/llm-wiki/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "llm-wiki", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
llm-wikiBuild a persistent compounding wiki from raw sources using the LLM Wiki pattern
LLM Wiki is an agent skill from jellydn/my-ai-tools. Build a persistent compounding wiki from raw sources using the LLM Wiki pattern
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `templates/index.md`, `templates/log.md` and `templates/schema.md`). Compatibility notes: cline, claude, opencode, amp, codex, gemini, cursor, pi
It sits in Knowledge Management, covering LLM wikis. The repository describes itself as: Comprehensive configuration management for AI coding tools - Replicate my complete setup for Claude Code, OpenCode, Amp, Li, Codex and Claude Code Switch with custom… The licence is MIT.
6 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 62c9227. It shows what the files ask for, not the result of running them.
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.
Shell commands in SKILL.md call:
bunFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
gist.github.comgithub.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
cline, claude, opencode, amp, codex, gemini, cursor, pi
From compatibility in the SKILL.md frontmatter.
LLM Wiki loads about 1.5k tokens when it runs. Until then it costs about 22 tokens; SKILL.md has 659 words of instructions outside code blocks.
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.
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.
The full file from jellydn/my-ai-tools at commit 62c9227, republished under its MIT licence (© jellydn). 659 words, ~1,542 tokens.
.claude/skills/llm-wiki/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.Build and maintain a persistent, compounding knowledge wiki from raw sources.
Based on Karpathy's LLM Wiki pattern: the LLM incrementally integrates each new source into a structured wiki of markdown files — updating entity pages, flagging contradictions, strengthening cross-references. Synthesis is compiled once and kept current, not re-derived on every query.
/llm-wiki <ACTION> [ARGUMENTS]
wiki/)<SOURCE> - Process a source file and integrate it into the wiki<QUESTION> - Answer a question using the wiki as the knowledge baseyour-wiki/
├── raw/ # Immutable source documents — you add, LLM never modifies
│ └── assets/ # Downloaded images referenced by sources
├── wiki/ # LLM-generated and maintained pages
│ ├── index.md # Catalog of all pages with one-line summaries
│ ├── log.md # Append-only record of all operations
│ ├── overview.md
│ ├── entities/ # People, places, organizations
│ ├── concepts/ # Ideas, topics, themes
│ └── sources/ # One summary page per source
└── CLAUDE.md # Schema: wiki conventions and per-operation workflowsTemplates for all three layers are in $SKILL_PATH/templates/.
raw/, wiki/, wiki/entities/, wiki/concepts/, wiki/sources/$SKILL_PATH/templates/schema.md to CLAUDE.md (or AGENTS.md)wiki/index.md from $SKILL_PATH/templates/index.mdwiki/log.md from $SKILL_PATH/templates/log.mdwiki/overview.md stating the wiki's domain and purposeraw/ and run /llm-wiki ingest <file> nextDone when: all five files and directories exist and the user has been told the next step.
<SOURCE>":wiki/sources/<slug>.md with a structured summarywiki/overview.md if the source shifts the big picturewiki/entities/ for key people, places, organizationswiki/concepts/ for key ideas and themeswiki/index.md — every new or modified page must appear with a one-line summarywiki/log.md: ## [YYYY-MM-DD] ingest | <Source Title>Done when: every affected page is updated, every new or changed page appears in index.md, and the log entry is appended. A single ingest typically touches 5–15 pages.
<QUESTION>":wiki/index.md to identify the most relevant pageswiki/index.md and append to wiki/log.mdDone when: the question is answered with citations, and any filing decision (page created or skipped) is resolved.
Scan the entire wiki and report on each of the following:
[[Page Name]] links pointing to non-existent pagesSuggest new questions and sources. Ask before making any fixes.
Append to wiki/log.md: ## [YYYY-MM-DD] lint | health check
Done when: all six issue types are checked and reported, suggestions are given, and the log entry is appended.
Report: source count in raw/, wiki page count, last 10 entries in wiki/log.md, and any obvious health issues (orphan pages, missing index entries).
Done when: all four items are reported.
wiki/index.md — content catalog, updated on every ingest. Every page with a link and one-line summary, organized by category. The LLM reads this first when answering queries.
wiki/log.md — append-only operation log. Entry format: ## [YYYY-MM-DD] <operation> | <title>. Grep-parseable:
grep "^## \[" wiki/log.md | tail -5 # last 5 operations
grep "^## \[.*\] ingest" wiki/log.md # all ingests
grep "^## \[.*\] query" wiki/log.md # all queriesFor larger wikis, add qmd — local hybrid BM25/vector search with an MCP server:
bun install -g @tobilu/qmd
qmd collection add ./wiki --name my-wiki
qmd embed
qmd query "how does X relate to Y" -c my-wikiraw/.© jellydn, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files in skills/llm-wiki of jellydn/my-ai-tools.
Open the folder on GitHubat commit 62c9227
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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| LLM Wiki this skilljellydn/my-ai-tools | 123 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Karpathy LLM WikiAstro-Han/karpathy-llm-wiki | 2.5k | — | ~3.6k | Automated safety check: Pass | MIT | |
| LLM Wikilewislulu/llm-wiki-skill | 655 | — | ~3.7k | Automated safety check: Pass | None | |
| Wiki Builderrohitg00/pro-workflow | 2.9k | — | ~1k | Automated safety check: Pass | None | |
| Codex History IngestAr9av/obsidian-wiki | 3.5k | — | ~2.2k | Automated safety check: Notes | MIT | |
| Arkon Editnduckmink/arkon | 1.5k | — | ~1.6k | Automated safety check: Pass | Custom licence |
Astro-Han/karpathy-llm-wiki
A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.
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…
rohitg00/pro-workflow
Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base.
Ar9av/obsidian-wiki
Ingest Codex CLI conversation/session history into Obsidian as distilled knowledge.
nduckmink/arkon
Propose or directly apply edits to Arkon wiki pages, including proposing brand new pages.
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.
jellydn/my-ai-tools
A skill your agent uses when monitoring an open GitHub PR for CI failures, review feedback, mergeability, and safe retries or fixes.
jellydn/my-ai-tools
Posts a concise visual outline as a GitHub pull request comment.
jellydn/my-ai-tools
Manage project knowledge with qmd — captures learnings, decisions, and conventions
jellydn/my-ai-tools
Generate Product Requirements Documents from feature ideas — plans specs and requirements
jellydn/my-ai-tools
Build an interactive report or experiment when the user asks to explore model capabilities.
jellydn/my-ai-tools
Fix PR review comments by implementing requested changes. An agent skill from jellydn/my-ai-tools.
Categories
Build a persistent compounding wiki from raw sources using the LLM Wiki pattern. LLM Wiki is an agent skill from jellydn/my-ai-tools.
LLM Wiki fits situations like: tasks that involve LLM wikis.
Run `npx skills add jellydn/my-ai-tools --skill llm-wiki -a claude-code`. Or copy the skill folder (skills/llm-wiki in jellydn/my-ai-tools) into .claude/skills/llm-wiki in your project. Claude Code loads it when a task matches its description.
Run `npx skills add jellydn/my-ai-tools --skill llm-wiki -a codex`. Or copy the skill folder (skills/llm-wiki in jellydn/my-ai-tools) into .agents/skills/llm-wiki in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jellydn/my-ai-tools --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.
Going by SKILL.md and its folder, LLM Wiki needs the command-line tools its instructions call (bun). Compatibility (from SKILL.md): cline, claude, opencode, amp, codex, gemini, cursor, pi.
SKILL.md names 2 domains. As links in the text: gist.github.com and github.com. This is read from the text; nothing was executed.
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.
LLM Wiki is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.5k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
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.
jellydn (a GitHub user) maintains it in jellydn/my-ai-tools, which has 123 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 10, 2026.
Source: jellydn/my-ai-tools on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.