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

deps

Skill2 starsChanged 6 months agoMITView on GitHub

Analyse, audite et gère les dépendances du projet intelligemment.

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use diagnose, retro and 2 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.
  • MicrosoftSkill

    diagnose

    Use to systematically diagnose why scenarios fail — identifies root causes by analyzing agent traces, codebase, and behavioral patterns

    Also in 3 projects that use this

  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 3 projects that use this

  • OpenAISkill

    audit

    Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

    Also in 3 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 projects that use this

The file

Files
SKILL.md

Instructions

Mode: Audit

Exécuter en parallèle :

  1. Outdated Check
    • npm outdated ou bun outdated ou équivalent
    • Lister les packages avec mises à jour majeures disponibles
    • Vérifier les changelogs des mises à jour majeures (breaking changes)
  2. Security Audit
    • npm audit ou équivalent + python scripts/scan_secrets.py
    • Vérifier Socket.dev pour supply-chain (malware, typosquatting)
    • Lister les vulnérabilités par sévérité
    • Proposer les fixes automatiques quand possible
  3. Bundle Analysis
    • Identifier les dépendances les plus lourdes
    • Proposer des alternatives plus légères si pertinent
    • Exemples : moment.js → dayjs, lodash → lodash-es ou natif
  4. Dead Dependencies
    • Scanner les imports du projet
    • Identifier les packages dans package.json qui ne sont jamais importés
    • Proposer leur suppression

Mode: Add

Quand l'utilisateur veut ajouter une dépendance :

  1. Vérifier la popularité et maintenance (dernière release, stars, issues)
  2. Vérifier la taille du bundle (bundlephobia)
  3. Vérifier les vulnérabilités connues
  4. Proposer des alternatives si pertinent
  5. Installer avec la bonne commande (--save-dev si outil de dev)

Mode: Recommandations SaaS

Packages recommandés par catégorie :

UI : shadcn/ui (pas une dépendance, copié), tailwindcss, lucide-react Forms : react-hook-form, zod State : zustand, jotai Data Fetching : @tanstack/react-query Date : date-fns ou dayjs Email : resend, react-email Auth : next-auth, @supabase/ssr (si stack Supabase) DB : drizzle-orm, @supabase/supabase-js (Supabase) ou @neondatabase/serverless (Neon) Paiements : stripe Upload : uploadthing Analytics : @posthog/next Logging : pino Testing : vitest, @playwright/test

Montée majeure avec veille changelog complète

  • Si une seule dépendance ou API nécessite lecture des release notes officielles, breaking changes et migration propre → /deep-update (voir docs/processus-mise-a-jour-profonde.md) plutôt que seulement ce mode Audit.

Rapport

## Dépendances : X total (Y prod, Z dev)
## Vulnérabilités : X critical, Y high, Z moderate
## Outdated : X packages (Y majeurs)
## Dead : X packages non utilisés
## Bundle : Xkb (top 5 plus lourds)
## Recommandation : [actions à prendre]

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.