asets-gobizit/n8n-doctor
skills/n8n-doctor/SKILL.md
Diagnostic, auto-fix, and monitoring skill for n8n workflows. Checks health, fixes known issues automatically, logs results, monitors weekly.
testing
Updated Apr 15, 2026
$ install --global
skillsauthnpx skillsauth add asets-gobizit/claude-skills n8n-doctorInstall 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 PM13.2s4 files scanned
SKILL.md
- name:
- n8n-doctor
- description:
- Diagnostic, auto-fix, and monitoring skill for n8n workflows. Checks health, fixes known issues automatically, logs results, monitors weekly.
- version:
- 1.1
- author:
- Claude Code
n8n Doctor
When to Use
- User says "check n8n", "fix n8n", "debug n8n", "n8n doctor"
- User reports n8n workflow errors
- Before/after modifying n8n workflows via API
- Weekly scheduled health check
HOW TO INVOKE
/n8n-doctor # Full scan — all workflows
/n8n-doctor Product Story Engine # Scan specific workflow by name
/n8n-doctor qCLsVULa3yH8vnI5 # Scan specific workflow by ID
/n8n-doctor restore <workflow-name> # Restore workflow from backup
/n8n-doctor update # Check for n8n updates and schedule upgrade
What It Does
Diagnostic Checks (21 total)
- n8n running on port 5678
- API key valid
- Workflow(s) active
- fs module enabled (NODE_FUNCTION_ALLOW_BUILTIN)
- Chain node data loss detection
- OpenRouter rate limit check
- Credential IDs valid
- Node type versions compatible
- promptType set correctly on chain nodes
- Model IDs current (not deprecated)
- File write paths exist
- Recent execution errors (API + event log)
- Read-only fields in workflow JSON
- Form webhook responds
- Execution success rate (warn if <70%)
- Credential API keys alive (test calls)
- n8n update available
- Zoho Campaigns credential type (generic OAuth2, not built-in Zoho)
- Zoho Campaigns endpoint names (case-sensitive, correct API version)
- Zoho Campaigns list_details format validation
- Webhook helper workflow availability (for live API tests)
Self-Healing Mode
When issues are found, the skill tries to fix them automatically (up to 3 attempts) before alerting the user. Known auto-fixes:
- Set NODE_FUNCTION_ALLOW_BUILTIN=fs,path as permanent Windows user env var (prevents recurring "Module 'fs' is disallowed" errors after reboot)
- Restart n8n with correct env vars
- Activate inactive workflows
- Fix promptType on chain nodes
- Swap rate-limited models to fallback
- Create missing output directories
fs Module Fix (Important)
n8n 2.x sandboxes Code nodes and blocks built-in Node modules (fs, path) by default. Any Code node that writes files (like "Save Local Archive") will fail with Module 'fs' is disallowed.
Root cause: NODE_FUNCTION_ALLOW_BUILTIN env var not set when n8n starts.
n8n-doctor auto-fix:
- Sets
NODE_FUNCTION_ALLOW_BUILTIN=fs,pathas a permanent Windows user environment variable (survives reboots) - Flags that n8n needs a restart to pick up the new env var
- If run with
--fix, will restart n8n automatically
Logging
Every run writes a timestamped log to skills/n8n-doctor/logs/ with:
- DateTime, mode, n8n version
- Per-workflow: PASS/FAIL/WARN per check
- Auto-fixes applied and their results
- Summary with counts
- Update availability
Weekly Monitoring
Scheduled via Windows Task Scheduler — runs full diagnostic every Sunday night. Sends summary email via Himalaya if issues found.
n8n Installation Details
- Installed via Volta:
C:\Users\dansk\AppData\Local\Volta\tools\image\packages\n8n\n8n - Git Bash:
/c/Users/dansk/AppData/Local/Volta/bin/n8n - Required env:
NODE_FUNCTION_ALLOW_BUILTIN=fs,path - Port: 5678 | Data:
~/.n8n/ - API docs:
GET/PUT/POST /api/v1/workflows,/api/v1/executions,/api/v1/credentials
Dependencies
- Node.js (via Volta)
- curl (for API calls)
- netstat (for process detection)
- Himalaya CLI (for email alerts, optional)
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