add-karpathy-llm-wiki
Skill1 starsChanged 6 months agoMITView on GitHub
Add a persistent wiki knowledge base to a ClawBridge group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm wiki", "karpathy wiki".
- Reads credentials
7 other projects use a version of this, 7 of them edited.
Adopted by
Most recently taken up by
- nanocoai/nanoclawedited, first seen Nov 15, 2026
- ss2code/nanoclaw-opsedited, first seen Oct 15, 2026
- prathish-ks/isthmusedited, first seen Oct 12, 2026
- gavrielc/nanoclawedited, first seen Oct 8, 2026
- qwibitai/nanoclawedited, first seen Oct 8, 2026
- TomGranot/groupguardedited, first seen Sep 3, 2026
Used with
Projects with it also use add-anydoc, add-clidash and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
TomGranotSkilladd-anydoc
Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.
Also in 5 projects that use this
TomGranotSkilladd-clidash
Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.
Also in 5 projects that use this
qwibitaiSkilladd-iron-proxy
Install or refresh Iron Proxy and its official Iron Control web console for NanoClaw. Use when selecting the Iron gateway, adding its management UI, configuring credentials and grants, or restoring the proxy, approval bridge, and agent guidance.
Also in 4 projects that use this
qwibitaiSkilladd-mattermost
Add a self-hosted or cloud Mattermost bot channel through the Chat SDK bridge, reusing a healthy server when available and linking to official server setup guidance when needed.
Also in 4 projects that use this
b1rdmaniaSkillmigrate-memory
Migrate from monolith CLAUDE.md to the three-file memory system (identity + state + log). Non-destructive — backs up the original first.
Also in 6 projects that use this
nanocoaiSkilladd-cursor
Use Cursor (local Agent SDK) as a full agent provider — planning, tool orchestration, MCP tools, session resume — alongside or instead of Claude. Cursor-account sign-in or API key, held by the credential gateway. Per-group via `ncl groups config update --provider cursor`. Distinct from using Cursor as a cloud agent (those run on Cursor VMs and are not this provider).
Also in 3 projects that use this
- +5 more from TomGranot
- +1 more from qwibitai
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 7
- gavrielc/nanoclaw★ 31k72% same
- nanocoai/nanoclaw★ 31k72% same
- qwibitai/nanoclaw★ 31k72% same
- microsoft/amplifier-app-nanoclaw★ 592% same
- TomGranot/groupguard★ 372% same
- prathish-ks/isthmus★ 272% same
- ss2code/nanoclaw-ops★ 172% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- container/AGENTS.mdAGENTS.md
- add-atomic-chat-toolSkill
- add-dashboardSkill
- add-discordSkill
- add-emacsSkill
- add-gcal-toolSkill
- add-gchatSkill
- add-githubSkill
- add-gmail-toolSkill
- add-imessageSkill
- add-linearSkill
- add-macos-statusbarSkill
- add-matrixSkill
- add-ollama-providerSkill
- add-ollama-toolSkill
- add-parallelSkill
- add-resendSkill
- add-signalSkill
- add-slackSkill
- add-teamsSkill
- add-telegramSkill
- add-vercelSkill
- add-webexSkill
- add-wechatSkill
- add-whatsapp-cloudSkill
- add-whatsappSkill
- clawSkill
- convert-to-apple-containerSkill
- customizeSkill
- debugSkill
- get-qodo-rulesSkill
- init-first-agentSkill
- manage-channelsSkill
- manage-mountsSkill
- migrate-from-openclawSkill
- migrate-clawbridgeSkill
- qodo-pr-resolverSkill
- setupSkill
- update-clawbridgeSkill
- update-skillsSkill
- x-integrationSkill
The file
We split this skill into the rules it gives an agent
7 rules. 1 is common, 1 is distinctive, and 5 are very specific to this project.
1
Common
Most of the 7 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 12
Read ${CLAUDE_SKILL_DIR}/llm-wiki.md — this is the full LLM Wiki idea as written by Karpathy.
- Very specific: line 22
If dedicated: ask which channel and chat, then register with pnpm exec tsx setup/index.ts --step register.
- Common: line 29
Do they want the full three-layer architecture or a lighter version?
- Very specific: line 36
Create wiki/ and sources/ directories in the group folder.
- Very specific: line 63
If the document is a webpage, then claude can use fetch or agent-browser to open the page and extract full text if available.
- Distinctive: line 74
If yes, create a ClawBridge scheduled task that runs in the wiki group.
- Very specific: line 99
Use the group's folder and chat_jid from the registered groups table.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Add Karpathy LLM Wiki
Set up a persistent wiki knowledge base on ClawBridge, based on Karpathy's LLM Wiki pattern.
Step 1: Read the pattern
Read ${CLAUDE_SKILL_DIR}/llm-wiki.md — this is the full LLM Wiki idea as written by Karpathy. Understand it thoroughly before proceeding. Summarize the core idea to the user briefly, then discuss what they want to build.
Step 2: Choose a group
AskUserQuestion: "Which group should have the wiki?"
- Main group — add to your existing main chat
- Dedicated group — create a new group just for the wiki
- Other — pick an existing group
If dedicated: ask which channel and chat, then register with pnpm exec tsx setup/index.ts --step register.
Step 3: Design collaboratively
Discuss with the user based on the pattern:
- What's the wiki's domain or topic?
- What kinds of sources will they add? (URLs, PDFs, images, voice notes, books, transcripts)
- Do they want the full three-layer architecture or a lighter version?
- Any specific conventions they care about? (The pattern intentionally leaves this open.)
Based on this discussion, create three things:
3a. Directory structure
Create wiki/ and sources/ directories in the group folder. Create initial index.md and log.md per the pattern's Indexing and Logging section. Adapt to the user's domain.
3b. Container skill
Create a container/skills/wiki/SKILL.md tailored to this user's wiki. This is the schema layer from the pattern — it tells the agent how to maintain the wiki. Base it on the pattern's Operations section (ingest, query, lint) and the conventions you agreed on with the user. Don't over-prescribe — the pattern says "your LLM figures out the rest."
3c. Group CLAUDE.md
Edit the group's CLAUDE.md to add a wiki section. This is critical — it's what turns the agent into a wiki maintainer. It should:
- Explain the wiki system concisely: what it is, the three layers (sources, wiki, schema), the three operations (ingest, query, lint)
- Index the key files and folders (
wiki/,sources/,wiki/index.md,wiki/log.md) - Point to the container skill for detailed workflow
- Ingest discipline: Be very explicit that when the user provides multiple files or points at a folder with many files, the agent MUST process them one at a time. For each file: read it, discuss takeaways, create/update all wiki pages (summary, entities, concepts, cross-references, index, log), and completely finish with that file before moving to the next. Never batch-read all files and then process them together — this produces shallow, generic pages instead of the deep integration the pattern requires.
Step 4: Source handling capabilities
Based on the source types the user plans to ingest (discussed in Step 3), check whether the agent can already handle those formats — some are supported natively, others need a skill (e.g. /add-image-vision, /add-pdf-reader, /add-voice-transcription). If a needed capability isn't installed, check if there's an available skill for it and help the user get it set up.
URL handling note
claude has built-in WebFetch, but it returns a summary, not the full document. For wiki ingestion of a URL where the full text matters, the container skill and CLAUDE.md should instruct claude to use bash commands to download full files instead. For example:
curl -sLo sources/filename.pdf "<url>"If the document is a webpage, then claude can use fetch or agent-browser to open the page and extract full text if available. The container skill and CLAUDE.md should note this so claude gets full content for sources rather than summaries.
Step 5: Optional lint schedule
AskUserQuestion: "Want periodic wiki health checks?"
- Weekly
- Monthly
- Skip — lint manually
If yes, create a ClawBridge scheduled task that runs in the wiki group. This is NOT a Claude Code cron job — it's a ClawBridge group task that runs in the agent container. Insert it into the SQLite database:
pnpm exec tsx -e "
const Database = require('better-sqlite3');
const { CronExpressionParser } = require('cron-parser');
const db = new Database('store/messages.db');
const interval = CronExpressionParser.parse('<cron-expr>', { tz: process.env.TZ || 'UTC' });
const nextRun = interval.next().toISOString();
db.prepare('INSERT INTO scheduled_tasks (id, group_folder, chat_jid, prompt, schedule_type, schedule_value, context_mode, next_run, status, created_at) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)').run(
'wiki-lint',
'<group_folder>',
'<chat_jid>',
'Run a wiki lint pass per the wiki container skill. Check for contradictions, orphan pages, stale content, missing cross-references, and gaps. Report findings and offer to fix issues.',
'cron',
'<cron-expr>',
'group',
nextRun,
'active',
new Date().toISOString()
);
db.close();
"Use the group's folder and chat_jid from the registered groups table. Cron expressions: 0 10 * * 0 (weekly Sunday 10am) or 0 10 1 * * (monthly 1st at 10am).
Step 6: Build and restart
pnpm run build
./container/build.sh
launchctl kickstart -k gui/$(id -u)/com.clawbridge # macOS
# Linux: systemctl --user restart clawbridgeTell the user to test by sending a source to the wiki group.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

