Agent skill

NanoClaw LLM Wiki Setup

by nanocoai in nanocoai/nanoclaw

Adds a persistent wiki knowledge base to a NanoClaw group following Karpathy's LLM Wiki pattern, with folders, a tailored container skill and a CLAUDE.md section.

MITAuto-check passedKnowledge Management

Install NanoClaw LLM Wiki Setup

skills CLI
$ npx skills add nanocoai/nanoclaw --skill add-karpathy-llm-wiki -a claude-code

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

GitHub CLI
$ gh skill install nanocoai/nanoclaw add-karpathy-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/nanocoai/nanoclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/add-karpathy-llm-wiki .claude/skills/add-karpathy-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
add-karpathy-llm-wiki
GitHub stars
31k
Token cost
~1.3k tokens
SKILL.md length
730 words
Files
3
Skills in repo
59
Repo updated
First seen
Licence
MIT

At a glance

Adds a persistent wiki knowledge base to a NanoClaw group following Karpathy's LLM Wiki pattern, with folders, a tailored container skill and a CLAUDE.md section.

  • Works in 6 steps: Read the pattern → Choose a group → Design collaboratively → …
  • Giving a NanoClaw chat group its own long-lived wiki of ingested sources
  • SKILL.md covers Step 1: Read the pattern, Step 2: Choose a group, Step 3: Design collaboratively and Step 4: Source handling…, plus 2 more sections
  • Calls curl and pnpm

What it does

The setup is built to be re-run safely. The agent reads the bundled pattern file and summarizes it for you, then asks which group gets the wiki: the main group, a new dedicated group registered with `pnpm exec tsx setup/index.ts --step register`, or an existing one. Next it discusses the wiki's topic, the kinds of sources you will add, whether you want the full three-layer design or something lighter, and any conventions you care about.

From that conversation it creates `wiki/` and `sources/` folders in the group, plus starter `index.md` and `log.md` files only if they are missing. It writes a container skill at `container/skills/wiki/SKILL.md` covering ingest, query and lint, and asks before overwriting an existing one. Finally it edits the group's CLAUDE.md, wrapping a wiki section in marker comments so a later run replaces it in place. A REMOVE.md file ships with the skill.

When your agent uses it

  • Giving a NanoClaw chat group its own long-lived wiki of ingested sources
  • Customizing the wiki's structure and maintenance conventions for a domain
  • Re-running setup to update the wiki section without losing existing pages

Example prompts

  • “Add a wiki to my main NanoClaw group for my reading notes.”
  • “Create a dedicated group with an LLM wiki for our product research PDFs and transcripts.”
  • “Set up the Karpathy wiki, but use a lighter version without the full three-layer structure.”

Requirements

  • A NanoClaw installation
  • pnpm, if you register a dedicated group

Workflow steps

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

  1. Read the pattern
  2. Choose a group
  3. Design collaboratively
  4. Source handling capabilities
  5. Optional lint schedule
  6. Restart

What it can do on your machine

Read from SKILL.md and the folder at commit a0c79dd. 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:

    • curl
    • pnpm

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

  • Network

    No URLs in SKILL.md. Its commands use curl and pnpm, which can reach the network depending on how they are called.

    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

NanoClaw LLM Wiki Setup loads about 1.3k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 730 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 nanocoai/nanoclaw at commit a0c79dd, republished under its MIT licence (© nanocoai). 730 words, ~1,326 tokens.

Download SKILL.mdSave it as .claude/skills/add-karpathy-llm-wiki/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
add-karpathy-llm-wiki
description
Add a persistent wiki knowledge base to a NanoClaw group. Based on Karpathy's LLM Wiki pattern. Triggers on "add wiki", "wiki", "knowledge base", "llm wiki", "karpathy wiki".

Add Karpathy LLM Wiki

Set up a persistent wiki knowledge base on NanoClaw, based on Karpathy's LLM Wiki pattern.

Each step is safe to re-run: directory creation uses mkdir -p, initial wiki files are created only if absent, the container skill is preserved unless the user opts to update it, and the group CLAUDE.md section is replaced in place via marker comments rather than duplicated.

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?"

  1. Main group — add to your existing main chat
  2. Dedicated group — create a new group just for the wiki
  3. 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 (mkdir -p — safe if they already exist). Create initial index.md and log.md per the pattern's Indexing and Logging section, adapted to the user's domain. Skip any of these files that already exist so a populated wiki is never clobbered on re-run.

3b. Container skill

Create 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."

If container/skills/wiki/SKILL.md already exists, ask the user whether to update it before overwriting, so an existing tailored schema is preserved on re-run.

3c. Group CLAUDE.md

Edit the group's CLAUDE.md to add a wiki section, wrapped in marker comments so it can be located and replaced on re-run:

markdown
<!-- BEGIN karpathy-llm-wiki -->
## Wiki
...section body...
<!-- END karpathy-llm-wiki -->

If a <!-- BEGIN karpathy-llm-wiki --> block already exists, replace it in place rather than appending a second copy. This is critical — it's what turns the agent into a wiki maintainer. The section 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.
Show full SKILL.md (207 more words)Show less

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:

bash
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?"

  1. Weekly
  2. Monthly
  3. Skip — lint manually

If yes, ask the agent to schedule the lint task using the schedule_task MCP tool in conversation.

Step 6: Restart

Run from your NanoClaw project root:

bash
source setup/lib/install-slug.sh
launchctl kickstart -k gui/$(id -u)/$(launchd_label)  # macOS
systemctl --user restart $(systemd_unit)              # Linux

Tell the user to test by sending a source to the wiki group.

© nanocoai, 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 in .claude/skills/add-karpathy-llm-wiki of nanocoai/nanoclaw.

  • SKILL.md
  • REMOVE.md
  • llm-wiki.md

Open the folder on GitHubat commit a0c79dd

Compare with similar skills

NanoClaw LLM Wiki Setup 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.

NanoClaw LLM Wiki Setup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
NanoClaw LLM Wiki Setup this skillnanocoai/nanoclaw31k—~1.3kAutomated safety check: PassMIT
Company Braincoreyhaines31/makerskills851—~4.9kAutomated safety check: PassMIT
Obsidian Wiki Vault SetupAgriciDaniel/claude-obsidian15k—~1.3kAutomated safety check: PassMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
Icm ArchitectRinDig/icm-architect1.8k—~3.2kAutomated safety check: PassMIT
Wiki Builderrohitg00/pro-workflow2.9k—~1kAutomated safety check: PassNone

Similar skills

  • Company Brain

    coreyhaines31/makerskills

    Your team's shared, AI-ready knowledge base — people, companies, meetings, SOPs, and decisions structured so an agent can answer on your team's behalf.

    851 GitHub stars~4.9k tokensUpdated 2 days ago
    Knowledge ManagementAuto-check passed
  • Obsidian Wiki Vault Setup

    AgriciDaniel/claude-obsidian

    Sets up or adopts a separate Obsidian knowledge vault through the claude-obsidian core script and routes follow-up work to the right wiki sub-skill.

    15k GitHub stars~1.3k tokensUpdated 1 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
  • Icm Architect

    RinDig/icm-architect

    Design any process, idea, problem, or body of knowledge into an ICM (Interpretable Context Methodology) workspace — folder structure as agent architecture — or restructure an existing folder, repo…

    1.8k GitHub stars~3.2k tokensUpdated 1 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 12 days ago
    Knowledge ManagementAuto-check passed
  • 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

More from nanocoai/nanoclaw

All 59 skills in this repo
  • Installs or refreshes Iron Proxy and its Iron Control web console for NanoClaw, with a local Docker setup, database, credentials and a human approval bridge.

    31k GitHub stars~4.6k tokensUpdated yesterday
    Auto-check: notes
  • Installs or refreshes OneCLI as the gateway provider for NanoClaw, copying the adapter files, registering the provider and running the setup script.

    31k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check: notes
  • Agent Browser

    nanocoai/nanoclaw

    Drives a web browser from the shell with the agent-browser CLI: open pages, read an element snapshot, click and fill by reference, grab text and screenshots.

    31k GitHub starsUsed in 2 repos~1.6k tokens
    Auto-check passed
  • Add Dial Tool

    nanocoai/nanoclaw

    Installs the `dial` CLI and a credential in NanoClaw agent containers so chosen agents can send SMS, place AI voice calls and receive verification codes.

    31k GitHub stars~4.8k tokensUpdated yesterday
    Auto-check passed
  • Guides a conversational migration from an OpenClaw install to NanoClaw v2, carrying over identity, channel credentials, scheduled tasks and workspace files.

    31k GitHub stars~6k tokensUpdated yesterday
    Auto-check: notes
  • Wires up an additional phone number onto an already-installed Dial channel, so one NanoClaw install answers SMS and AI voice calls on more than one line.

    31k GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

Questions about NanoClaw LLM Wiki Setup

What does NanoClaw LLM Wiki Setup do?

Adds a persistent wiki knowledge base to a NanoClaw group following Karpathy's LLM Wiki pattern, with folders, a tailored container skill and a CLAUDE.md section. The setup is built to be re-run safely.ts --step register`, or an existing one.

When should I use NanoClaw LLM Wiki Setup?

NanoClaw LLM Wiki Setup fits situations like: giving a NanoClaw chat group its own long-lived wiki of ingested sources; customizing the wiki's structure and maintenance conventions for a domain; re-running setup to update the wiki section without losing existing pages.

How do I install NanoClaw LLM Wiki Setup in Claude Code?

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

How do I install NanoClaw LLM Wiki Setup in Codex?

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

Can I use NanoClaw LLM Wiki Setup 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 nanocoai/nanoclaw --skill add-karpathy-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/add-karpathy-llm-wiki, .gemini/skills/add-karpathy-llm-wiki, .github/skills/add-karpathy-llm-wiki and .opencode/skills/add-karpathy-llm-wiki in your project.

What does NanoClaw LLM Wiki Setup need to run?

Going by SKILL.md and its folder, NanoClaw LLM Wiki Setup needs the command-line tools its instructions call (curl and pnpm). Our summary lists: A NanoClaw installation; pnpm, if you register a dedicated group.

Does NanoClaw LLM Wiki Setup access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is NanoClaw LLM Wiki Setup 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 NanoClaw LLM Wiki Setup use?

NanoClaw LLM Wiki Setup 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 NanoClaw LLM Wiki Setup use?

About 1.3k tokens (SKILL.md is roughly 5.3k 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 NanoClaw LLM Wiki Setup?

Skills that share tags, products or a category with NanoClaw LLM Wiki Setup: Company Brain (coreyhaines31/makerskills, 851 stars), Obsidian Wiki Vault Setup (AgriciDaniel/claude-obsidian, 15k stars), LLM Wiki (lewislulu/llm-wiki-skill, 655 stars) and Icm Architect (RinDig/icm-architect, 1.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains NanoClaw LLM Wiki Setup?

nanocoai (a GitHub organization) maintains it in nanocoai/nanoclaw, which has 30,915 GitHub stars. The repository holds 59 skills in this directory. The repository was last updated on October 10, 2026.

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