AI improvement prompts

Como funciona

Dúas pezas de datos combínanse ao facer clic:

• O achado — título, descrición, evidencia, remediación, CWE — xa cargado co informe.
• O framework da túa base de código — detectado a partir dos achados discovery.tech-fingerprint do escaneo (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Cae nunha receita xenérica cando non se detecta framework (o prompt do axente entón pide ao LLM que o detecte desde o estado do repo).

Templates live in lib/scanner/fix-prompts.ts. The registry has check-specific guidance for crawlability, search presentation, semantic content, structured data, media, performance, accessibility, forms, mobile/i18n, runtime, owner journeys, and repo-quality issues. For everything else, the existing remediation field on the finding becomes the generic recipe.

Como se ve o prompt

Fix the "Hero image is lazy-loaded and missing dimensions" finding on /pricing.

Issue: The largest above-the-fold image is marked loading="lazy" and has
no explicit width/height. That can delay LCP and create layout shift.

Codebase context: Next.js.

Recommended fix:
Use next/image or the existing image component with explicit width/height,
responsive sizes, meaningful alt text, and priority/fetchPriority for the
first major visual on the page.

Constraints:
- Don't break existing tests; run the test suite after the change.
- Match the codebase's existing style and lint config.
- Add a brief comment explaining the performance reasoning only where the
  fix would otherwise look arbitrary.
- If the fix needs a new dependency, install it via the project's
  package manager (npm / pnpm / pip / bundle / composer).

Reference: Core Web Vitals / Largest Contentful Paint guidance.

Frameworks compatibles

Mostramos snippets específicos por framework para:

• Next.js, React, Vue, Nuxt, Svelte (frontend)
• Express, Fastify (Node.js backend)
• Django, Flask (Python)
• Ruby on Rails
• Laravel (PHP)
• ASP.NET Core (planificado, hoxe fallback a xenérico)

A detección de framework é best-effort. Ollamos tags __NEXT_DATA__, __NUXT__, cookies hash (laravel_session), cabeceiras X-Powered-By e algúns sinais máis. Se executas un framework personalizado, o prompt cae na receita xenérica e o axente dedúceo desde o teu package.json.

Úsao desde o teu axente de IA

Se conectaches o servidor MCP, o mesmo prompt expóñese como slash command. Desde Claude Desktop:

/fixweb-fix finding_id=550e8400-e29b-41d4-a716-446655440000

The renderer looks up the finding, detects the framework from the parent scan when available, renders the templated prompt, and injects it into your conversation as the user message. No round-trip to our Claude API; templates are pure and free.

Por que non chamamos a Claude en cada clic

No lanzamento consideramos chamar á Anthropic API por cada clic para refinar o prompt con contexto da base de código. Non o fixemos porque:

• O axente no que pega o usuario xa ten contexto da base de código: está usando Cursor / Claude Desktop co repo aberto.
• Modelar por (check × framework) cobre ~80% do valor sen custo por clic.
• Un opt-in “Refine with AI for my codebase” podería disparar a API máis tarde se os usuarios o queren. Hoxe, non.