docs-gen
Skill2 starsChanged 6 months agoMITView on GitHub
Génère la documentation du projet : API docs, README, architecture. Utilise les scripts Python et l'analyse du code réel.
- Reads credentials
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Vyrnexis/nim-agent-templatetheir own version, first seen Oct 15, 2026
- Jinbae10/skillstheir own version, first seen Jul 7, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Vyrnexis/nim-agent-template★ 4same name
- Jinbae10/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- apexSkill
- api-genSkill
- assets-pipelineSkill
- brainstormSkill
- debugSkill
- deep-updateSkill
- deploy-checkSkill
- depsSkill
- e2e-testsSkill
- env-setupSkill
- featureSkill
- fixSkill
- forkSkill
- meta-promptSkill
- migrateSkill
- onboardSkill
- oneshotSkill
- perfSkill
- prdSkill
- qualitySkill
- refactorSkill
- reviewSkill
- saas-initSkill
- schema-genSkill
- scope-taskSkill
- session-startSkill
- stripeSkill
- ui-auditSkill
- uiSkill
- variationsSkill
The file
Files
Modes
/docs-gen api — Documentation API
- Scanner les routes :
Grep "export.*async function (GET|POST|PUT|DELETE|PATCH)" app/api/ - Pour chaque route, lire le fichier et extraire : méthode, auth requise, body Zod schema, réponses
- Format de chaque endpoint :
### POST /api/invoices **Auth** : Requis — `session.user.organizationId` **Body** : `{ amount: number, clientId: string }` (Zod schema: `CreateInvoiceSchema`) **201** : `{ data: Invoice }` **400** : `{ error: string, details: ZodError[] }` **401** : `{ error: "Unauthorized" }` **Rate limit** : 10 req/min - Écrire dans
docs/api.md
/docs-gen readme — README du projet
- Lire
.claude/memory/stack.md+project-scan.md+package.json - Lire la structure réelle avec Glob
- Générer un README avec :
- Description + stack (versions réelles du lockfile)
- Prérequis (Node, pnpm, Supabase CLI, Vercel CLI)
- Setup en 5 commandes : clone → install →
.env.local→supabase start→pnpm dev - Scripts disponibles (depuis
package.json) - Architecture hexagonale (
src/core/,src/adapters/, etc.) - Commandes Python utiles (
scripts/README.md)
/docs-gen architecture — Diagramme d'architecture
- Scanner la structure réelle avec Glob
- Générer un diagramme Mermaid des flux principaux :
- Auth flow (login → session → middleware → route)
- Data flow (request → Zod → usecase → port → adapter → DB)
- Multi-tenancy flow (
organizationIddans chaque query)
- Documenter les choix techniques depuis
.claude/memory/decisions.mdetdocs/adr/ - Écrire dans
docs/architecture.md
/docs-gen schema — Documentation DB
- Lire les fichiers de migration
supabase/migrations/*.sql - Extraire toutes les tables, colonnes, FK, index
- Générer un diagramme ERD en Mermaid
- Documenter les policies RLS pour chaque table
- Écrire dans
docs/db-schema.md
/docs-gen onboarding — Guide développeur
Générer docs/ONBOARDING.md step-by-step :
- Prérequis + setup env (pointer vers
/env-setup) - Architecture expliquée (hexagonale : core vs adapters)
- Conventions (kebab-case, types, erreurs typées)
- Workflow de contribution (branch → APEX → PR → deploy)
- Commandes du quotidien :
project_health.py,supabase_migrate.py, etc.
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
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.

