agentleFS
Sign inStart free
tonydzitonydzi/second-brain-starter-kit/skills/n8n/SKILL.md

n8n

Skill6 starsChanged 2 months agoMITView on GitHub

Health-check, audit and, on approval, fix a self-hosted n8n automation stack. Health is read-only; any workflow edit goes preview, approval, apply. Triggers: "/n8n", "/n8n health", "/n8n fix <id>", "which workflows are failing".

  • Reads credentials

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use albert-dm, new-client-system 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.
  • yawningwhaleAISkill

    albert-dm

    Reply to DMs and messages the way Albert would. Use when the user asks "how would Albert reply to this", pastes a conversation and wants an Albert-style response, or asks you to draft/write a DM in Albert's voice. Albert sells AI voice agents / automations to local service businesses (Go High Level, lead follow-up, bookings).

    Also in 5 projects that use this

  • yawningwhaleAISkill

    new-client-system

    Scaffold a new client's full stack — Next.js 16 frontend dashboard + Trigger.dev backend worker — from the Shiney automations template. Use when the user says "new client", "onboard a client", "scaffold a client system", "set up <client-name>", or wants to start a fresh frontend+backend project styled and structured like the Shiney automations dashboard. Produces structure only; no automations are scaffolded — those are added later.

    Also in 6 projects that use this

  • xfstudioSkill

    trigger-dev

    Trigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background task, ai background job, long running task.

    Also in 12 projects that use this

  • huyvpSkill

    cost-reducer

    Reduce cloud, infrastructure, and operational costs while maintaining performance. Use when writing database queries, configuring cloud resources, optimizing bundles, setting up caching, choosing between services, sizing instances, configuring CDN, managing storage, or reviewing code for cost inefficiencies. Covers AWS/GCP/Vercel pricing, database optimization, serverless tuning, image pipelines, observability costs, and FinOps practices.

    Also in 10 projects that use this

  • ffsshhttiikkSkill

    scalability

    Core foundational concepts and principles for Scalability

    Also in 10 projects that use this

  • RoxenRobloxSkill

    youtube-broll-maker

    Generate 10-second B-roll footage of yourself doing an action using the Higgsfield MCP (Seedance 2.0). Upload one photo of yourself, describe the action ("typing on laptop", "walking at night"), pick from 5 cinematography style presets, get an MP4. Use when the user wants B-roll, cutaway footage, "me doing X" video, YouTube B-roll, or any image-to-video of themselves performing an action.

    Also in 3 projects that use this

  • +4 more from yawningwhaleAI

The file

Create a free account to mount
Files
SKILL.md

/n8n — automation-stack health & repair

🧒 When reporting to Anton end with a child-simple "In plain words" recap. (memory eli5-always)

Anton's operational nervous system = self-hosted n8n at https://n8n.example.com (v2.14.2, 89 workflows). n8n = event bus, NOT the brain. Full state + every gotcha = memory [[n8n-stack]] (read it first). Workflows fail SILENTLY → this skill makes failure visible and fixes it safely.

Access: REST https://n8n.example.com/api/v1/, header X-N8N-API-KEY; key in $USERPROFILE/.claude/secrets/n8n.env ⚠️ expires 2026-07-15 (recreate non-expiring; warn if near). API needs a browser User-Agent header or returns 403 (WAF). The n8n MCP (mcp__n8n__*) is wired BUT can drop mid-session (it disconnected 2026-07-04) — do NOT depend on it.

MCP-down fallback = build/edit straight over REST (proven 2026-07-04): $IMPORTS_ROOT/n8n\n8n_build.py — create_workflow(name,nodes,connections), post_webhook(path,payload) (fire a webhook for /tt), set_active(id,on); and n8n_edit.py — get_workflow/update_workflow (backup-before-PUT), list_workflows, _req. Both reuse the WAF User-Agent. The resilience workflows built this way — WATCHDOG IdSRNxfOT9Mo7Qse (dead-man's-switch), ERROR CATCHER 5X7xsGlwz44AO8Wf (set as settings.errorWorkflow to make a workflow's failures scream in chat 03), INBOUND DOOR 5e8JGjnVSvnkrRSX, bus-bridge U96y7qLDLufGpbUf — plus their builders (watchdog_build.py/catcher_build.py/inbound_build.py) live in _imports\n8n\. Full map = memory [[n8n-watchdog]].

Step 0 — key liveness (run BEFORE anything else)

First check the API key is still alive: compare today's date to N8N_KEY_EXPIRES in n8n.env (see Access above for the date). If today is past it the key is DEAD → every call silently 403s, so recreate the key first (n8n UI → Settings → API → new key, paste into n8n.env, bump N8N_KEY_EXPIRES) — a Tier-2 write, so pause for Anton's "+" (see Safety). Within ~7 days → warn but proceed.

Modes

  • health (default, READ-ONLY) — mcp__n8n__n8n_health_check for liveness, then scan recent executions for errors (mcp__n8n__n8n_executions status=error, or python $IMPORTS_ROOT/n8n/fetch_n8n.py). Report RED (persistent code-level failures), FLAKY (transient 503/aborted → just enable node auto-retry), and IDLE-but-active (cron not firing). ALWAYS prove a failure from a real execution (resultData.runData[node].error) before naming a cause — the failing node may differ from the first suspect.
  • dashboard — python $IMPORTS_ROOT/n8n/build_dashboard.py → open _Dashboards\n8n-Automation-Audit.html (Anton works by eye). Re-run fetch_n8n.py → enrich_n8n.py → build_dashboard.py to refresh (all 0 LLM tokens; cluster summaries on FREE Sonnet subagents per [[model-routing-sonnet-grunt]]).
  • fix <id> — repair ONE workflow. BACKUP FIRST always: python $IMPORTS_ROOT/n8n/n8n_edit.py backup-all (→ raw/backup_<ts>/; per-edit before/after to raw/edits/, restore via restore_workflow). Show Anton the diff (BEFORE→AFTER), get his "+", then apply. PUT needs ONLY {name,nodes,connections,settings} (strip read-only fields).

Known scars (verify still true before acting — memory may be stale)

  • Events Posting — was name '_input' is not defined (Python task-runner bug); FIXED 2026-06-16 by converting Code nodes Python→JavaScript. Rule: when a Python code node mysteriously fails on _input, convert to JS rather than debugging Pyodide.
  • Gitbook Pavel — was 11% err on empty-sessionId; FIXED with an additive guard Filter before the memory chain.
  • Codex cron / aaaZeroInbound — abandoned/standalone (awaiting Anton's archive call).

Safety

  • Health = read-only, run freely. Editing/activating a workflow, recreating the API key, deleting workflows = pause + confirm (Tier-2, [[operating-agreement]]).
  • Backup BEFORE every edit (backup-all); never edit without the snapshot.

Output

RED/FLAKY/IDLE counts + the worst offender with its proven error + suggested fix. Then 🧒 recap. Related: [[platinum-crm-import]] (CHARM CRM engine), [[automation-inventory]] (that = LOCAL jobs; this = REMOTE n8n).

<!--kit-footer-->

Like this skill? It is one of 100 in second-brain-starter-kit: the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with npx skills add tonydzi/second-brain-starter-kit. Everything is open source and free, so take what you need.

Flagships worth a look on their own: secondop-panel (a second opinion from a panel of external models), claude-memory-tidy (stop your agent's memory from rotting), telegram-mcp-kit (your own Telegram over MCP in about 15 minutes).

Author: Anton Dziatkovskii, Palo Alto AI Research Lab. Telegram @tonydzi - WhatsApp +1 341 222 9178 - X @Tony_Stef_

Engineers: want to test-drive this setup? Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free