Karpathy LLM Wiki
Astro-Han/karpathy-llm-wiki
A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.
A skill your agent uses when an LLM Wiki operation issue asks a question.
Install Wiki Query
$ npx skills add paperclipai/paperclip --skill wiki-query -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install paperclipai/paperclip wiki-query --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/paperclipai/paperclip.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/plugins/plugin-llm-wiki/skills/wiki-query .claude/skills/wiki-query && 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 "wiki-query" agent skill from https://github.com/paperclipai/paperclip/tree/master/packages/plugins/plugin-llm-wiki/skills/wiki-query into .claude/skills/wiki-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wiki-query", 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/paperclipai/paperclip/tree/master/packages/plugins/plugin-llm-wiki/skills/wiki-queryType 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 paperclipai/paperclip --skill wiki-query -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install paperclipai/paperclip wiki-query --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/paperclipai/paperclip.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/plugins/plugin-llm-wiki/skills/wiki-query .agents/skills/wiki-query && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "wiki-query" agent skill from https://github.com/paperclipai/paperclip/tree/master/packages/plugins/plugin-llm-wiki/skills/wiki-query into .agents/skills/wiki-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wiki-query", 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 paperclipai/paperclip --skill wiki-query -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install paperclipai/paperclip wiki-query --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/paperclipai/paperclip.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/plugins/plugin-llm-wiki/skills/wiki-query .cursor/skills/wiki-query && 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 "wiki-query" agent skill from https://github.com/paperclipai/paperclip/tree/master/packages/plugins/plugin-llm-wiki/skills/wiki-query into .cursor/skills/wiki-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wiki-query", 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/paperclipai/paperclip.git --path packages/plugins/plugin-llm-wiki/skills/wiki-query--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 paperclipai/paperclip --skill wiki-query -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install paperclipai/paperclip wiki-query --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/paperclipai/paperclip.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/plugins/plugin-llm-wiki/skills/wiki-query .gemini/skills/wiki-query && 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 "wiki-query" agent skill from https://github.com/paperclipai/paperclip/tree/master/packages/plugins/plugin-llm-wiki/skills/wiki-query into .gemini/skills/wiki-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wiki-query", 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 paperclipai/paperclip wiki-queryInstalls 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 paperclipai/paperclip --skill wiki-query -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/paperclipai/paperclip.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/plugins/plugin-llm-wiki/skills/wiki-query .github/skills/wiki-query && 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 "wiki-query" agent skill from https://github.com/paperclipai/paperclip/tree/master/packages/plugins/plugin-llm-wiki/skills/wiki-query into .github/skills/wiki-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wiki-query", 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 paperclipai/paperclip --skill wiki-query -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install paperclipai/paperclip wiki-query --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/paperclipai/paperclip.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/plugins/plugin-llm-wiki/skills/wiki-query .opencode/skills/wiki-query && 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 "wiki-query" agent skill from https://github.com/paperclipai/paperclip/tree/master/packages/plugins/plugin-llm-wiki/skills/wiki-query into .opencode/skills/wiki-query/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "wiki-query", 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.
Facts
- Skill name
wiki-query- GitHub stars
- 99k
- Token cost
- ~682 tokens
- SKILL.md length
- 367 words
- Files
- 1
- Skills in repo
- 60
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when an LLM Wiki operation issue asks a question.
- Works in 6 steps: Open the target space's wiki/index.md… → Read the candidate pages end to end with… → Inspect raw sources when a wiki page's… → …
- An LLM Wiki operation issue asks a question
- SKILL.md covers Inputs, Workflow, Voice and Verification, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Wiki Query is an agent skill from paperclipai/paperclip. Use when an LLM Wiki operation issue asks a question. Answer from wiki pages and raw sources with citations, name gaps plainly, and offer to file durable synthesis when the answer should compound.
Its SKILL.md is about 680 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Knowledge Management, covering LLM wikis. The repository describes itself as: The open-source app everyone uses to manage agents at work. The licence is MIT.
When your agent uses it
- An LLM Wiki operation issue asks a question
- Tasks that involve LLM wikis
Example prompts
- “/wiki-query”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Open the target space's wiki/index.md first — it is the navigation aid. Identify candidate pages.
- Read the candidate pages end to end with wiki_read_page, always passing the operation issue's wikiId and spaceSlug. Follow [[wiki-links]]…
- Inspect raw sources when a wiki page's claim feels thin. The wiki points to raw/ precisely so you can verify before answering. Use…
- Answer the question in the operation issue thread. Structure
- Decide whether the answer is durable. If the question forced you to do real synthesis (a comparison, a tradeoff, a definition of something…
- When the wiki cannot answer, say so plainly. Suggest a source the user should ingest, a Paperclip project that would help if distilled, or…
What it can do on your machine
Read from SKILL.md and the folder at commit b9750b1. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Wiki Query loads about 682 tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 367 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.
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 paperclipai/paperclip at commit b9750b1, republished under its MIT licence (© paperclipai). 367 words, ~682 tokens.
Download SKILL.mdSave it as
.claude/skills/wiki-query/SKILL.md (or your agent's skills folder).- name
- wiki-query
- description
- Use when an LLM Wiki operation issue asks a question. Answer from wiki pages and raw sources with citations, name gaps plainly, and offer to file durable synthesis when the answer should compound.
Wiki Query
Answer a question from what the wiki actually contains, with citations.
Inputs
- An operation issue with
operationType: "query"and the question in the body. - The operation issue's target
wikiId,spaceSlug, and space root.
Workflow
- Open the target space's
wiki/index.mdfirst — it is the navigation aid. Identify candidate pages. - Read the candidate pages end to end with
wiki_read_page, always passing the operation issue'swikiIdandspaceSlug. Follow[[wiki-links]]to neighbouring pages when the question spans entities or concepts. - Inspect raw sources when a wiki page's claim feels thin. The wiki points to
raw/precisely so you can verify before answering. Usewiki_read_source. - Answer the question in the operation issue thread. Structure:
- Direct answer first, in 1–4 sentences.
- Then the supporting facts as bullet points, each with an inline citation:
(see [[wiki/concepts/managed-resources]])or(see raw/<filename>). - If you needed to read a raw source the wiki did not summarise, name that as a gap.
- Decide whether the answer is durable. If the question forced you to do real synthesis (a comparison, a tradeoff, a definition of something that isn't already a page), offer to file it under
wiki/synthesis/<slug>.md. Do not write the synthesis page silently — it is opt-in. If the user accepts, write the page, link it fromwiki/index.md, and append aquery | filed synthesislog entry. - When the wiki cannot answer, say so plainly. Suggest a source the user should ingest, a Paperclip project that would help if distilled, or a web lookup. Never bluff.
Show full SKILL.md (116 more words)Show less
Voice
- Lead with the answer.
- Cite as you go, not in a footnote block at the end.
- Use the wiki's terse, factual voice. The query response is itself a candidate for filing into
wiki/synthesis/.
Verification
Before closing the operation issue:
- Every claim in the answer cites a wiki page or raw source.
- If the wiki was insufficient, that is stated directly with a concrete next step (ingest source X, distill project Y, web search Z).
- If you wrote a synthesis page,
wiki/index.mdlists it andwiki/log.mdhas aquery | filed synthesisentry. - No file under
raw/was modified.
Tools
wiki_search, wiki_read_page, wiki_list_sources, wiki_read_source, wiki_write_page (only when filing synthesis). Always include the operation issue's wikiId and spaceSlug.
© paperclipai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in packages/plugins/plugin-llm-wiki/skills/wiki-query of paperclipai/paperclip.
Open the folder on GitHubat commit b9750b1
Compare with similar skills
Wiki Query 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 |
|---|---|---|---|---|---|---|
| Wiki Query this skillpaperclipai/paperclip | 99k | — | ~682 | Automated safety check: Pass | MIT | |
| Karpathy LLM WikiAstro-Han/karpathy-llm-wiki | 2.4k | — | ~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 |
Similar skills
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…
Wiki Builder
rohitg00/pro-workflow
Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base.
Codex History Ingest
Ar9av/obsidian-wiki
Ingest Codex CLI conversation/session history into Obsidian as distilled knowledge.
Arkon Edit
nduckmink/arkon
Propose or directly apply edits to Arkon wiki pages, including proposing brand new pages.
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.
More from paperclipai/paperclip
All 60 skills in this repoGarden Inbox
paperclipai/paperclip
Scan a Paperclip user's Mine inbox, classify reversible archive candidates, request checkbox confirmation, and archive only accepted selections.
Paperclip
paperclipai/paperclip
Interact with the Paperclip control plane API for task coordination and governance.
Paperclip
paperclipai/paperclip
A skill your agent uses for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and…
Design Guide
paperclipai/paperclip
Paperclip UI design system guide for building consistent, reusable frontend components.
Paperclip Page
paperclipai/paperclip
Publish static HTML pages and asset folders to the Paperclip S3/CloudFront page host.
Paperclip Create Agent
paperclipai/paperclip
Create new agents in Paperclip with governance-aware hiring.
Related
Categories
Questions about Wiki Query
What does Wiki Query do?
A skill your agent uses when an LLM Wiki operation issue asks a question. Wiki Query is an agent skill from paperclipai/paperclip. Use when an LLM Wiki operation issue asks a question.
When should I use Wiki Query?
Wiki Query fits situations like: an LLM Wiki operation issue asks a question; tasks that involve LLM wikis.
How do I install Wiki Query in Claude Code?
Run `npx skills add paperclipai/paperclip --skill wiki-query -a claude-code`. Or copy the skill folder (packages/plugins/plugin-llm-wiki/skills/wiki-query in paperclipai/paperclip) into .claude/skills/wiki-query in your project. Claude Code loads it when a task matches its description.
How do I install Wiki Query in Codex?
Run `npx skills add paperclipai/paperclip --skill wiki-query -a codex`. Or copy the skill folder (packages/plugins/plugin-llm-wiki/skills/wiki-query in paperclipai/paperclip) into .agents/skills/wiki-query in your project. Codex loads it when a task matches its description.
Can I use Wiki Query 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 paperclipai/paperclip --skill wiki-query -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/wiki-query, .gemini/skills/wiki-query, .github/skills/wiki-query and .opencode/skills/wiki-query in your project.
What does Wiki Query need to run?
SKILL.md names no scripts, command-line tools or credentials: Wiki Query is instructions for the agent only.
Does Wiki Query access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Wiki Query 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 Wiki Query use?
Wiki Query 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 Wiki Query use?
About 682 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Wiki Query?
Skills that share tags, products or a category with Wiki Query: Karpathy LLM Wiki (Astro-Han/karpathy-llm-wiki, 2.4k 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 Wiki Query?
paperclipai (a GitHub organization) maintains it in paperclipai/paperclip, which has 98,967 GitHub stars. The repository holds 60 skills in this directory. The repository was last updated on October 9, 2026.
Source: paperclipai/paperclip on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.