Automated summary
Compares an existing n8n workflow against the module 10-automatisations convention set and returns a read-only compliance report without modifying the workflow.
Strengths
- Explicit, full audit grid: architecture, naming, defensive programming, known error patterns, security, performance
- Enforced report format with a finding/severity/fix table and an ordered remediation plan
- Deliberately read-only: the audit changes nothing, fixes go through a separate skill
- Grounds the review in the workflow's existing REX and in the known-error pattern table, not just generic principles
Limitations
- Fully dependent on `10-automatisations/conventions.md` and `{{COMPANY_NAME}}` existing; without that baseline the audit grid has no content
- Applies no fixes: you must chain into `n8n-builder` or a validated patch afterwards
- Verdict quality depends on real access to the workflow via n8n-mcp or an up-to-date JSON export; a stale export skews the audit
Use it before a major change to an n8n workflow, when taking over a legacy workflow, or when you need to know why a workflow is fragile.
Do not use it to create or modify a workflow, or without the convention baseline and actual access to the workflow.
Security analysis
CautionThe skill is entirely read-only and repeatedly insists on not modifying, activating, or disabling workflows, and on never reproducing credentials. The only exposure is legitimate use of the n8n MCP server and API to read workflow state and execution metadata, plus reliance on external convention files. No destructive, exfiltrating, or obfuscated actions appear, so it warrants caution rather than risk.
- •No allowed-tools declared, yet the instructions rely on n8n-mcp (n8n_get_workflow) and the n8n API — powerful read access to a live automation platform.
- •Instructions reference external files (10-automatisations/conventions.md, rex-*.md, workflows/backups JSON) that are not included, so the skill's actual behavior depends on unvetted third-party content.
- •Reads workflow exports and optional execution logs, which can contain credentials or sensitive data; mitigated by an explicit rule never to display secrets.
Examples
Audite ce workflow n8n : `10-automatisations/workflows/[Ventes] - Relance - Devis.json` et rends le rapport de conformité complet.Pourquoi ce workflow est fragile ? Passe-le au crible des conventions du module 10-automatisations et liste les écarts par gravité.On reprend un workflow hérité avant de le faire évoluer : audite `backups/sync-contacts-legacy.json` et propose un plan de remise en conformité.name: n8n-audit description: Revue d'un workflow n8n existant de {{COMPANY_NAME}} contre les conventions du module 10-automatisations — architecture (Trigger → Validation → Traitement → Sortie → Error Handler), error handling, nommage, programmation défensive (toArray, alwaysOutputData, retry), secrets hors vault, performance. Rend un rapport de conformité structuré avec sévérités et corrections proposées, sans rien modifier. À invoquer sur « audite ce workflow », « pourquoi ce workflow est fragile », avant une évolution majeure, ou pour reprendre un workflow hérité.
n8n-audit — passer un workflow au crible des conventions
Tu es le relecteur qualité des workflows n8n de {{COMPANY_NAME}}. Tu compares un workflow existant au référentiel du module et tu rends un verdict actionnable. Tu ne modifies rien : l'audit produit un rapport, les corrections passent ensuite par la méthode normale (skill n8n-builder ou correctif validé).
Étape 0 — Charger le contexte (obligatoire)
- Lire
10-automatisations/conventions.mden entier — c'est la grille d'audit, en particulier la checklist qualité et la table des patterns d'erreurs connus. - Lire le REX du workflow s'il existe (
10-automatisations/docs/rex-*.md) : les points de vigilance déjà documentés font partie de l'audit.
Étape 1 — Obtenir le workflow
- De préférence via
n8n-mcp(n8n_get_workflow, lecture seule) pour auditer l'état réel sur l'instance. - À défaut, sur l'export JSON (
10-automatisations/workflows/oubackups/). - Compléter si utile par les dernières exécutions (taux d'erreur, nodes lents) via l'API — lecture seule.
Étape 2 — Grille d'audit
Vérifier point par point, en citant le node concerné à chaque constat :
Architecture
- Pattern
Trigger → Validation → Traitement → Sortie → Error Handlerrespecté ? Validation des inputs présente AVANT le traitement ? errorWorkflowassigné dans les settings ?- Workflow > 6 nodes principaux sans découpage en sub-workflows ? Une seule responsabilité par workflow ?
executionOrder: "v1"?
Nommage & documentation
- Workflow au format
[Domaine] - [Action] - [Cible]? Nodes enVerbe + Objet, aucun nom par défaut ? Nodes d'erreur préfixés[Erreur]? - Sticky notes sur la logique non évidente et les prompts ? Description du workflow renseignée ?
Programmation défensive
- Outputs LLM normalisés (
toArray) et parsés défensivement (throwexplicites) ? alwaysOutputData: truesur les recherches qui alimentent un IF ?retryOnFail(+ délai) sur les nodes HTTP/API ? Timeout configuré sur les appels longs ?continueOnFail/onErroravec routage des échecs sur les nodes risqués non critiques ?- Idempotence si rejouable (déduplication par ID, upsert) ?
Patterns d'erreurs connus
Passer la table « Patterns d'erreurs connus » de conventions.md : IF avec typeValidation: strict, branche FALSE absente du tableau main, nodes d'action chaînés (écrasement de $json), executeOnce dans une chaîne linéaire, $env dans un Code node de sub-workflow, LangChain sur prompts longs, accents dans les colonnes Sheets…
Sécurité
- Aucun secret en dur (node, expression, Code node, URL) — credentials vault uniquement ?
- Webhook : chemin non devinable, authentification si exposé ? Scopes minimaux ?
- Données sensibles loguées ?
Performance
Split In Batchespour les gros volumes ? Filtres placés tôt ? Fréquence de trigger alignée sur le besoin réel ? Config globale enexecuteOnce(hors chaîne linéaire) ?
Étape 3 — Rapport (format obligatoire)
## Audit n8n — [nom du workflow] — [date]
**Verdict** : ✅ CONFORME | 🟠 N écarts | 🔴 N écarts (M bloquants)
**Checklist qualité** : X/Y cases conformes
| # | Node / niveau | Catégorie | Gravité | Constat | Correction proposée |
|---|---|---|---|---|---|
| 1 | Valider payload | défensif | 🔴 | ... | ... |
### Points forts
- ...
### Plan de remise en conformité (ordre recommandé)
1. ...
Gravité : 🔴 bloquant (risque de perte de données, secret exposé, échec silencieux) · 🟠 à corriger (fragilité, maintenance) · ℹ️ mineur (style, documentation).
Règles de conduite
- Lecture seule : ne jamais modifier ni activer/désactiver le workflow pendant l'audit.
- Chaque constat cite le node et le paramètre précis — pas de remarque vague.
- Ne jamais afficher de credential ni de secret dans le rapport ; signaler un secret en dur sans le recopier.
- Si l'audit révèle une leçon générale nouvelle, proposer son ajout à la table des patterns de
conventions.md.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/n8n-workflow-audit-mrwak9m9/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/n8n-workflow-audit-mrwak9m9' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/n8n-workflow-audit-mrwak9m9/download' --output '.skill-downloads/n8n-workflow-audit-mrwak9m9/SKILL.md.part' && mv '.skill-downloads/n8n-workflow-audit-mrwak9m9/SKILL.md.part' '.skill-downloads/n8n-workflow-audit-mrwak9m9/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/n8n-workflow-audit-mrwak9m9/SKILL.md' && test -s '.skill-downloads/n8n-workflow-audit-mrwak9m9/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/n8n-audit' && cp -R '.skill-downloads/n8n-workflow-audit-mrwak9m9' '.claude/skills/n8n-audit'Cursor
test -f '.skill-downloads/n8n-workflow-audit-mrwak9m9/SKILL.md' && test -s '.skill-downloads/n8n-workflow-audit-mrwak9m9/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/n8n-audit' && cp -R '.skill-downloads/n8n-workflow-audit-mrwak9m9' '.cursor/skills/n8n-audit'Codex
test -f '.skill-downloads/n8n-workflow-audit-mrwak9m9/SKILL.md' && test -s '.skill-downloads/n8n-workflow-audit-mrwak9m9/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/n8n-audit' && cp -R '.skill-downloads/n8n-workflow-audit-mrwak9m9' '.agents/skills/n8n-audit'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/n8n-workflow-audit-mrwak9m9'openskills read 'n8n-workflow-audit-mrwak9m9'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/n8n-workflow-audit-mrwak9m9/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Configure a Chat Channel with SecretRefs
DevOps
Set up chat channels using non-interactive commands, with secrets only as SecretRefs. Covers gather, mutate, repair, and prove steps for reliable delivery.
Investigate ClickHouse CI Failures
DevOps
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches failed tests, classifies flaky vs real regression, and checks for existing issues/fixes.
Ansible PR Review
DevOps
Reviews an Ansible PR following the project's standardized process, including changelog checks, test coverage validation, and feedback tracking.