AI improvement prompts

How it works

Two pieces of dato combine on click:

• The jejuhu — title, description, evidence, remediation, CWE — already loaded ndive pe informe.
• Your codebase's framework — detected gui pe scan's discovery.tech-fingerprint jejuhu-kuéra (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Falls back pe a generic recipe oĩ jave nahániri framework ha'e detected (pe agent prompt then asks pe LLM pe detect it gui pe repo state).

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.

What pe prompt looks like

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.

Supported frameworks

We surface framework-specific snippets guarã:

• Next.js, React, Vue, Nuxt, Svelte (frontend)
• Express, Fastify (Node.js backend)
• Django, Flask (Python)
• Ruby on Rails
• Laravel (PHP)
• ASP.NET Core (planned, fallback pe generic today)

Framework detection ha'e best-effort. We sniff __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers, ha a few other signals. If nde're running a custom framework, pe prompt falls back pe pe generic recipe ha pe agent figures it out gui ne package.json.

Use it gui ne AI agent

If nde've wired up pe MCP servidor, pe same prompt ha'e exposed as a slash command. From 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.

Why ore don't hit Claude per click

On launch ore considered calling pe Anthropic API guarã each click pe refine pe prompt ndive codebase context. We didn't, because:

• The agent pe user pastes into already has codebase context — they're using Cursor / Claude Desktop ndive their repo open.
• Templating per-(check × framework) covers ~80% of pe value ỹre any per-click cost.
• A “Refine ndive AI guarã my codebase” opt-in could fire pe API later if puruhára want it. Today, nahániri.