asets-gobizit/nanoclaw
skills/nanoclaw/SKILL.md
Start, stop, restart, and check status of NanoClaw (personal Claude assistant) running in WSL
testing
Updated Apr 15, 2026
$ install --global
skillsauthnpx skillsauth add asets-gobizit/claude-skills nanoclawInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 15, 2026, 6:07 PM6.7s2 files scanned
SKILL.md
- name:
- nanoclaw
- description:
- Start, stop, restart, and check status of NanoClaw (personal Claude assistant) running in WSL
- version:
- 1.1
- author:
- Danny / Claude
- created:
- 2026-04-09
- updated:
- 2026-04-10
NanoClaw Skill
Manage the NanoClaw personal assistant process running in WSL2 from Windows.
When to Use
- User says "start nanoclaw", "run nanoclaw", "nanoclaw start"
- User says "stop nanoclaw", "kill nanoclaw", "nanoclaw stop"
- User says "restart nanoclaw", "nanoclaw restart"
- User says "nanoclaw status", "is nanoclaw running", "check nanoclaw"
- User says "nanoclaw logs", "show nanoclaw logs"
- User says "nanoclaw dev" (hot-reload development mode)
HOW TO INVOKE
/nanoclaw → check status (default)
/nanoclaw start → start via systemd
/nanoclaw stop → stop via systemd
/nanoclaw restart → restart via systemd
/nanoclaw status → show if running + recent logs
/nanoclaw logs → tail recent log output
/nanoclaw dev → start in dev mode (foreground, hot-reload)
Technical Specification
Environment
- Install path:
/home/dansk/nanoclaw(WSL2 Ubuntu) - Runtime: Node.js v22+ (at
/home/dansk/.local/bin/node) - Service:
nanoclaw.service(systemd user service, enabled on boot) - Service file:
/home/dansk/.config/systemd/user/nanoclaw.service - Entry point:
node dist/index.js(production) ornpm run dev(development) - Env file:
/home/dansk/nanoclaw/.env(contains ASSISTANT_NAME=Nio) - Logs:
/home/dansk/nanoclaw/logs/ - Data:
/home/dansk/nanoclaw/data/and/home/dansk/nanoclaw/store/ - Trigger:
@Nioin WhatsApp groups - Auto-restart: Yes (systemd
Restart=always, 5s delay) - WhatsApp: Connected, 104 groups synced
All commands run via WSL from Windows
Every command must be prefixed with wsl -e bash -lc "..." to ensure Node.js is on PATH.
Start
wsl -e bash -lc "systemctl --user start nanoclaw"
Stop
wsl -e bash -lc "systemctl --user stop nanoclaw"
Restart
wsl -e bash -lc "systemctl --user restart nanoclaw"
Status
wsl -e bash -lc "systemctl --user status nanoclaw"
Logs (systemd journal)
wsl -e bash -lc "journalctl --user -u nanoclaw -n 50 --no-pager"
Logs (file)
wsl -e bash -lc "tail -50 /home/dansk/nanoclaw/logs/nanoclaw.log"
Dev mode (foreground)
wsl -e bash -lc "systemctl --user stop nanoclaw; cd /home/dansk/nanoclaw && npm run dev"
Note: Stop the service first, then run dev mode. Dev mode runs in foreground — the terminal will be occupied.
Build (if needed after code changes)
wsl -e bash -lc "cd /home/dansk/nanoclaw && npm run build"
Known Limitation
loginctl enable-linger failed in WSL — if all WSL sessions close, the service may stop. As long as WSL stays running, the service is fine.
SECURITY — NEVER PUSH
NEVER run git push in the NanoClaw repo. The git config contains Danny's personal name/email. A pre-push hook is installed as a safeguard, but Claude must catch this BEFORE reaching the hook.
Dependencies
- WSL2 with Ubuntu
- Node.js v22+ (installed in WSL)
- NanoClaw already cloned and built at
/home/dansk/nanoclaw - systemd user service enabled (
nanoclaw.service)
Related Skills
asets-gobizit/pka-backup
data-ai
VerifiedTrustedCommunity
Automated backup skill for PKA + Obsidian + Claude memory. Snapshots pka.db (via SQLite .backup so WAL is handled safely), the Obsidian vault, Claude memory files, agent profiles, and the help-content Excel into a single timestamped zip in Zoho WorkDrive. Daily/weekly/monthly retention rotation built in. USE WHEN Danny says "backup", "run backup", "snapshot pka", or to recover from a snapshot.
SKILL.mdUpdated Apr 27, 2026
asets-gobizit/stress-test
testing
VerifiedTrustedCommunity
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology, packaged as the stress-test skill. MANDATORY TRIGGERS: 'stress-test this', 'stress test this', 'pressure-test this', 'pressure test this', 'war room this', 'council this', 'run the council', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a stress-test question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.
SKILL.mdUpdated Apr 25, 2026
asets-gobizit/obsidian-tidy
content-media
VerifiedTrustedCommunity
Weekly scan of Obsidian vault for empty/low-content notes. Moves them to zToBeDeleted/ for user review. Use when the user says "tidy obsidian", "clean obsidian", "obsidian cleanup", or on scheduled weekly run.
SKILL.mdUpdated Apr 18, 2026
asets-gobizit/make-website-design
development
VerifiedTrustedCommunity
Design-first website builder. Accepts a Claude Design export (HTML or screenshot) as a visual blueprint, collects business inputs, calls Claude API to generate a design-matched index.html, and publishes to GitHub Pages. Falls back to vibe-based generation if no design is provided. Use when the user says "make-website-design", "design website", "build from design", or provides a Claude Design export for website generation.
SKILL.mdUpdated Apr 18, 2026