launch-auditlisted

Run a comprehensive pre-launch quality audit on any web application. Explores the codebase first, then generates project-specific audit prompts that reference the actual files, routes, hooks, and functions found. Covers 7 areas: security, functionality, domain data coherence, visual consistency, performance, test coverage, and UX polish. Produces per-area audit reports and a final scorecard with 0-10 grades and launch readiness verdict. Use this skill whenever someone says "audit", "launch readiness", "pre-launch review", "quality check", "is this ready to ship", "review before launch", "pente fino", "revisão pré-lançamento", "está pronto pra lançar", "qa completa", "score the codebase", or any variation of checking whether a project is ready for production. Also triggers for deep-dive flow audits: "audita o wizard", "deep dive no checkout", "rastreia os dados do fluxo X", or any request to audit a specific multi-step flow in detail. Works with any web stack (React, Next.js, Vue, Svelte, etc + any backend).
parisgroup-ai/imersao-ia-setup · ★ 1 · Web & Frontend · score 77

Install: claude install-skill parisgroup-ai/imersao-ia-setup

# Pre-Launch Quality Audit ## How to Use This skill activates automatically — no special commands needed. Just say what you want in natural language. ### Full Audit (reviews the entire app) Say any of these: - "faz um pente fino no projeto" - "está pronto pra lançar?" - "roda uma auditoria completa" - "is this ready to ship?" - "quality check before launch" - "score the codebase" What happens: explores the project → runs 7 audit phases (security, functional, domain data, visual, performance, tests, polish) → generates a scorecard with grades and a launch verdict. ### Deep Dive (audits one specific flow in detail) Say any of these: - "audita o wizard" - "deep dive no fluxo de checkout" - "rastreia os dados do onboarding" - "revisa o fluxo de pagamento" - "audita o fluxo de cadastro de paciente" What happens: explores the project → maps every file in that specific flow → traces each data field step by step → audits every button and interaction → checks AI calls and external services → generates a focused report. ### Running both You can run a Full Audit first, then ask for a Deep Dive on a specific flow that needs more attention. They complement each other. --- ## Mode Detection (for the AI) Detect which mode to use based on the user's request: **Full Audit** — user mentions the whole app or general quality: - → Run Stage 1 (Discovery) → Stage 2 (7-Phase Audit) → Stage 3 (Scorecard) **Deep Dive** — user mentions a specific flow, feature, or multi-step process: -