agentleFS
GlamgarOnDiscordGlamgarOnDiscord/claude-saas-blueprint/.claude/skills/onboard/SKILL.md

onboard

Skill2 starsChanged 6 months agoMITView on GitHub

Onboarding complet sur un projet existant. Analyse, comprend et documente le projet pour que l'agent soit immédiatement productif.

  • Reads credentials

171 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use soak-test, team-live-ops 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.
  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 10 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 10 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 18 projects that use this

  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 12 projects that use this

  • CoralGameSkill

    playtest-report

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

    Also in 12 projects that use this

  • HK-hubSkill

    arrange

    Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.

    Also in 13 projects that use this

  • +5 more from lilangMax
  • +1 more from CoralGame

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 159 edited versions we read keep these.

  • 1

    Distinctive

    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 runner + config (vitest.config, jest.config, playwright.config)

    line 23

“Common” is measured: kept by at least 6 in 10 of the 159 edited versions of this file we could read. “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

Instructions

Phase 1 — Scan Rapide (4 agents parallèles)

Agent 1 — Structure & Stack :

  • Lire package.json / pyproject.toml (dépendances = stack réelle)
  • Identifier framework, runtime, ORM, auth, paiements
  • Détecter package manager (pnpm/bun/npm via lockfile)

Agent 2 — Architecture & Patterns :

  • Arborescence 2 niveaux max
  • Pattern architectural : hexagonal | MVC | feature-based | flat
  • Conventions de nommage (kebab, camel, PascalCase sur les fichiers)
  • Détecter si organizationId présent sur les tables → multi-tenant

Agent 3 — Tests & Qualité :

  • Test runner + config (vitest.config, jest.config, playwright.config)
  • Ratio fichiers test / fichiers source
  • Chercher console.log et any (indicateurs de dette rapide)
  • Chercher secrets hardcodés : patterns sk_, pk_, password=, secret=

Agent 4 — Infra & Deploy :

  • CI/CD : .github/workflows/, .gitlab-ci.yml
  • Provider déploiement (Vercel, Railway, Docker, AWS)
  • DB et auth provider
  • Variables .env.example présentes ?

Phase 2 — Health Check (script unifié)

python scripts/project_health.py

Retourne : erreurs TS, lint, tests, console.log count, any count, structure hexagonale, audit sécurité.

Phase 3 — Deep Dive (si nécessaire)

Lire les fichiers critiques :

  1. Point d'entrée principal (app/layout.tsx, main.ts, server.ts)
  2. Schema DB / dernières migrations
  3. Middleware d'auth
  4. 1-2 features complètes comme référence de style

Phase 4 — Documentation

Générer/mettre à jour :

  1. .claude/memory/project-scan.md — scan complet
  2. .claude/memory/stack.md — stack + versions
  3. .claude/memory/domains.md — domaines et entités détectés
  4. .claude/memory/patterns.md — patterns de code observés

Phase 5 — Recommandations

Basé sur le scan, identifier et prioriser :

  • Critique : secrets hardcodés, tables sans RLS, 0 tests
  • Warning : dette TS (any), console.log en prod, migrations non appliquées
  • Nice to have : structure hexagonale absente, README vide

Output Final

Projet analysé : [nom]
Stack : [framework] + [DB] + [auth]
Architecture : [pattern] — [conforme/non-conforme hexagonale]
Fichiers : X source, Y tests (ratio Z%)
Multi-tenant : oui/non (organizationId détecté : oui/non)
Secrets scan : OK / ⚠️ [X patterns suspects]

Santé : X/10
  - TS errors : X
  - console.log : X
  - any : X
  - Tests : X%

Priorité 1 : [action critique]
Priorité 2 : [action importante]

Prêt à travailler. → /feature ou /fix pour commencer.

Critères Santé 10/10 : 0 erreur TS, 0 console.log, <5% any, >60% coverage, RLS sur toutes les tables, 0 secret hardcodé.

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.