agentleFS
GlamgarOnDiscordGlamgarOnDiscord/claude-saas-blueprint/.claude/skills/api-gen/SKILL.md

api-gen

Skill2 starsChanged 6 months agoMITView on GitHub

Génère un endpoint API complet avec validation, auth, error handling et tests.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Test unitaire par use case

    line 39
  2. Distinctive:

    Test d'intégration par route (si framework de test dispo)

    line 40

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Arguments

  • resource : Nom de la ressource (ex: "invoices", "projects")
  • operations : CRUD complet par défaut, ou spécifier (ex: "create,read,list")

Instructions

1. Analyse

  • Lire rules/api-routes.md + rules/security.md avant toute modification
  • Lire le schema DB pour la ressource (si existant)
  • Identifier le pattern API utilisé dans le projet (REST, tRPC, GraphQL)
  • Lire un endpoint existant comme référence de style

2. Génération

Pour chaque opération demandée, créer :

Validation (Zod) dans shared/validators/ :

  • Schema de création (tous les champs requis)
  • Schema de mise à jour (tous les champs optionnels via .partial())
  • Schema de query params (pagination, filtres, tri)

Use Case dans core/usecases/ :

  • Un fichier par opération : create-{resource}.ts, list-{resources}.ts, etc.
  • Injection du port repository via paramètre
  • Vérification d'autorisation intégrée

Route/Controller dans adapters/api/ :

  • Middleware d'auth appliqué
  • Validation du body/params/query avec le schema Zod
  • Réponse standardisée : { data, error, meta: { page, total } }
  • Gestion d'erreur avec codes HTTP appropriés

Tests :

  • Test unitaire par use case
  • Test d'intégration par route (si framework de test dispo)

3. Validation

  • tsc --noEmit
  • Exécuter les tests générés
  • Vérifier qu'il n'y a pas de routes dupliquées

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.