# Quality

> Audit qualité approfondi du codebase. Identifie les problèmes, propose des fixes.

- **Type:** Skill
- **Install:** `agentstack add skill-glamgarondiscord-claude-saas-blueprint-quality`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [GlamgarOnDiscord](https://agentstack.voostack.com/s/glamgarondiscord)
- **Installs:** 0
- **Category:** [Databases](https://agentstack.voostack.com/c/databases)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [GlamgarOnDiscord](https://github.com/GlamgarOnDiscord)
- **Source:** https://github.com/GlamgarOnDiscord/claude-saas-blueprint/tree/main/.claude/skills/quality

## Install

```sh
agentstack add skill-glamgarondiscord-claude-saas-blueprint-quality
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Instructions

### 1. Scan Structurel
Utiliser l'agent Explore pour :
- Mapper l'arborescence complète du projet
- Identifier les fichiers > 200 lignes (candidats au split)
- Détecter les imports circulaires
- Vérifier le respect de l'architecture hexagonale (core n'importe pas adapters)

### 2. Scan de Code
Utiliser Grep pour détecter :
- `any` dans les fichiers TypeScript
- `console.log` / `console.error` hors logger
- `TODO` / `FIXME` / `HACK` non résolus
- Fonctions > 50 lignes
- Fichiers sans export (dead code potentiel)
- Duplications évidentes (patterns copiés-collés)

### 3. Scan de Sécurité
- Secrets hardcodés
- SQL non paramétré
- Injection de HTML non sanitisé (innerHTML, etc.)
- Dépendances avec vulnérabilités connues

### 4. Scan DX
- Scripts npm/bun manquants (dev, build, test, lint)
- `.env.example` à jour
- README avec instructions de setup

### 5. Dashboard global
Lancer `python scripts/project_health.py` — retourne en une passe : erreurs TS, lint, tests, console.log/any counts, audit sécurité, structure hexagonale.

### 6. Rapport
Générer un rapport structuré :
- **Critiques** (bloquants)
- **Warnings** (à traiter)
- **Suggestions** (nice to have)
- **Métriques** : Fichiers, Lignes, Coverage, Score qualité (A/B/C/D)

Proposer de fix automatiquement les issues simples (unused imports, console.log, etc.)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [GlamgarOnDiscord](https://github.com/GlamgarOnDiscord)
- **Source:** [GlamgarOnDiscord/claude-saas-blueprint](https://github.com/GlamgarOnDiscord/claude-saas-blueprint)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-glamgarondiscord-claude-saas-blueprint-quality
- Seller: https://agentstack.voostack.com/s/glamgarondiscord
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.