EJClaw/.claude/skills/setup/SKILL.md

name, description

name	description
setup	Run initial NanoClaw setup. Use when user wants to install dependencies, authenticate messaging channels, register their main channel, or start the background services. Triggers on "setup", "install", "configure nanoclaw", or first-time setup requests.

NanoClaw Setup

Run setup steps automatically. Only pause when user action is required (channel authentication, configuration choices). Setup uses bash setup.sh for bootstrap, then npx tsx setup/index.ts --step <name> for all other steps. Steps emit structured status blocks to stdout. Verbose logs go to logs/setup.log.

Principle: When something is broken or missing, fix it. Don't tell the user to go fix it themselves unless it genuinely requires their manual action (e.g. authenticating a channel, pasting a secret token). If a dependency is missing, install it. If a service won't start, diagnose and repair. Ask the user for permission when needed, then do the work.

UX Note: Use AskUserQuestion for all user-facing questions.

Architecture: NanoClaw runs agents as direct host processes (no Docker/containers). Each agent type (Claude Code, Codex) has its own runner in container/agent-runner/ and container/codex-runner/.

0. Git & Fork Setup

Check the git remote configuration to ensure the user has a fork and upstream is configured.

Run:

• git remote -v

Case A — origin points to qwibitai/nanoclaw (user cloned directly):

The user cloned instead of forking. AskUserQuestion: "You cloned NanoClaw directly. We recommend forking so you can push your customizations. Would you like to set up a fork?"

• Fork now (recommended) — walk them through it
• Continue without fork — they'll only have local changes

If fork: instruct the user to fork qwibitai/nanoclaw on GitHub (they need to do this in their browser), then ask them for their GitHub username. Run:

git remote rename origin upstream
git remote add origin https://github.com/<their-username>/nanoclaw.git
git push --force origin main

Verify with git remote -v.

If continue without fork: add upstream so they can still pull updates:

git remote add upstream https://github.com/qwibitai/nanoclaw.git

Case B — origin points to user's fork, no upstream remote:

Add upstream:

git remote add upstream https://github.com/qwibitai/nanoclaw.git

Case C — both origin (user's fork) and upstream (qwibitai) exist:

Already configured. Continue.

Verify: git remote -v should show origin → user's repo, upstream → qwibitai/nanoclaw.git.

1. Bootstrap (Node.js + Dependencies)

Run bash setup.sh and parse the status block.

• If NODE_OK=false → Node.js is missing or too old. Use AskUserQuestion: Would you like me to install Node.js 22? If confirmed:
  • macOS: brew install node@22 (if brew available) or install nvm then nvm install 22
  • Linux: curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs, or nvm
  • After installing Node, re-run bash setup.sh
• If DEPS_OK=false → Read logs/setup.log. Try: delete node_modules and package-lock.json, re-run bash setup.sh. If native module build fails, install build tools (xcode-select --install on macOS, build-essential on Linux), then retry.
• If NATIVE_OK=false → better-sqlite3 failed to load. Install build tools and re-run.
• Record PLATFORM and IS_WSL for later steps.

2. Check Environment

Run npx tsx setup/index.ts --step environment and parse the status block.

• If HAS_AUTH=true → WhatsApp is already configured, note for step 5
• If HAS_REGISTERED_GROUPS=true → note existing config, offer to skip or reconfigure

3. Build Agent Runners

Run npx tsx setup/index.ts --step runners and parse the status block.

This builds the agent runners that execute as host processes:

• container/agent-runner/ — Claude Code agent (via Claude Agent SDK)
• container/codex-runner/ — Codex agent (via Codex CLI)

If BUILD_OK=false: Read logs/setup.log for the error. Common fix: cd container/agent-runner && npm install && npm run build.

If CODEX_RUNNER=false but AGENT_RUNNER=true: Codex runner failed to build. Not critical if you only use Claude Code. Fix: cd container/codex-runner && npm install && npm run build.

4. Claude Authentication (No Script)

If HAS_ENV=true from step 2, read .env and check for CLAUDE_CODE_OAUTH_TOKEN or ANTHROPIC_API_KEY. If present, confirm with user: keep or reconfigure?

AskUserQuestion: Claude subscription (Pro/Max) vs Anthropic API key?

Subscription: Tell user to run claude setup-token in another terminal, copy the token, add CLAUDE_CODE_OAUTH_TOKEN=<token> to .env. Do NOT collect the token in chat.

API key: Tell user to add ANTHROPIC_API_KEY=<key> to .env.

Codex Authentication (Optional)

AskUserQuestion: Do you also want to use Codex (OpenAI) agents?

If yes: Tell user to add OPENAI_API_KEY=<key> (or CODEX_OPENAI_API_KEY=<key>) to .env. The Codex runner will use this key.

Voice Transcription (Optional)

AskUserQuestion: Do you want voice message transcription in Discord/WhatsApp?

If yes: Tell user to get a free API key at https://console.groq.com (no credit card needed) and add GROQ_API_KEY=<key> to .env. Uses Groq Whisper (whisper-large-v3-turbo, ~200x faster than OpenAI). Falls back to OpenAI Whisper (OPENAI_API_KEY) if Groq key is not set.

5. Install Skills Marketplace

Register and install the NanoClaw skills marketplace plugin so all feature skills (channel integrations, add-ons) are available:

claude plugin marketplace add qwibitai/nanoclaw-skills
claude plugin marketplace update nanoclaw-skills
claude plugin install nanoclaw-skills@nanoclaw-skills --scope project

The marketplace update ensures the local cache is fresh before installing. This is hot-loaded — no restart needed. All feature skills become immediately available.

6. Set Up Channels

AskUserQuestion (multiSelect): Which messaging channels do you want to enable?

• WhatsApp (authenticates via QR code or pairing code)
• Telegram (authenticates via bot token from @BotFather)
• Slack (authenticates via Slack app with Socket Mode)
• Discord (authenticates via Discord bot token)

Delegate to each selected channel's own skill. Each channel skill handles its own code installation, authentication, registration, and JID resolution. This avoids duplicating channel-specific logic and ensures JIDs are always correct.

For each selected channel, invoke its skill:

• WhatsApp: Invoke /add-whatsapp
• Telegram: Invoke /add-telegram
• Slack: Invoke /add-slack
• Discord: Invoke /add-discord

Each skill will:

1. Install the channel code (via git merge of the skill branch)
2. Collect credentials/tokens and write to .env
3. Authenticate (WhatsApp QR/pairing, or verify token-based connection)
4. Register the chat with the correct JID format
5. Build and verify

After all channel skills complete, install dependencies and rebuild — channel merges may introduce new packages:

npm install && npm run build

If the build fails, read the error output and fix it (usually a missing dependency). Then continue to step 7.

7. Mount Allowlist

AskUserQuestion: Agent access to external directories?

No: npx tsx setup/index.ts --step mounts -- --empty Yes: Collect paths/permissions. npx tsx setup/index.ts --step mounts -- --json '{"allowedRoots":[...],"blockedPatterns":[],"nonMainReadOnly":true}'

8. Start Service

If service already running: unload first.

• macOS: launchctl unload ~/Library/LaunchAgents/com.nanoclaw.plist
• Linux: systemctl --user stop nanoclaw (or systemctl stop nanoclaw if root)

Run npx tsx setup/index.ts --step service and parse the status block.

If FALLBACK=wsl_no_systemd: WSL without systemd detected. Tell user they can either enable systemd in WSL (echo -e "[boot]\nsystemd=true" | sudo tee /etc/wsl.conf then restart WSL) or use the generated start-nanoclaw.sh wrapper.

If SERVICE_LOADED=false:

• Read logs/setup.log for the error.
• macOS: check launchctl list | grep nanoclaw. If PID=- and status non-zero, read logs/nanoclaw.error.log.
• Linux: check systemctl --user status nanoclaw.
• Re-run the service step after fixing.

9. Verify

Run npx tsx setup/index.ts --step verify and parse the status block.

If STATUS=failed, fix each:

• SERVICE=stopped → npm run build, then restart: launchctl kickstart -k gui/$(id -u)/com.nanoclaw (macOS) or systemctl --user restart nanoclaw (Linux) or bash start-nanoclaw.sh (WSL nohup)
• SERVICE=not_found → re-run step 8
• CREDENTIALS=missing → re-run step 4
• CHANNEL_AUTH shows not_found for any channel → re-invoke that channel's skill (e.g. /add-telegram)
• REGISTERED_GROUPS=0 → re-invoke the channel skills from step 6
• MOUNT_ALLOWLIST=missing → npx tsx setup/index.ts --step mounts -- --empty

Tell user to test: send a message in their registered chat. Show: tail -f logs/nanoclaw.log

Troubleshooting

Service not starting: Check logs/nanoclaw.error.log. Common: wrong Node path (re-run step 8), missing .env (step 4), missing channel credentials (re-invoke channel skill).

Agent fails ("Claude Code process exited with code 1"): Check agent logs in groups/<folder>/logs/agent-*.log. Common causes: missing credentials in .env, codex CLI not in PATH, stale session IDs.

Codex agent not responding: Ensure OPENAI_API_KEY is set in .env and codex CLI is installed globally (npm install -g @openai/codex). The runner needs codex in PATH.

Voice transcription not working: Check GROQ_API_KEY (primary) or OPENAI_API_KEY (fallback) is set in .env. Test: send a voice message in Discord and check logs/nanoclaw.log for Audio transcribed entries with provider and elapsed fields.

No response to messages: Check trigger pattern. Main channel doesn't need prefix. Check DB: npx tsx setup/index.ts --step verify. Check logs/nanoclaw.log.

Channel not connecting: Verify the channel's credentials are set in .env. Channels auto-enable when their credentials are present. For WhatsApp: check store/auth/creds.json exists. For token-based channels: check token values in .env. Restart the service after any .env change.

Unload service: macOS: launchctl unload ~/Library/LaunchAgents/com.nanoclaw.plist | Linux: systemctl --user stop nanoclaw