AI improvement prompts

How it works

Two pieces of done combine on click:

• The konklizyon — title, description, evidence, remediation, CWE — already loaded ak la rapò.
• Your codebase's framework — detected soti nan la eskan's discovery.tech-fingerprint konklizyon yo (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Falls back pou a generic recipe lè non framework se detected (la agent prompt then asks la LLM pou detect it soti nan la 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 la 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 pou:

• 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 pou generic today)

Framework detection se best-effort. We sniff __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers, ak a few other signals. If ou're running a custom framework, la prompt falls back pou la generic recipe ak la agent figures it out soti nan ou package.json.

Use it soti nan ou AI agent

If ou've wired up la Sèvè MCP, la same prompt se 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 nou don't hit Claude per click

On launch nou considered calling la Anthropic API pou each click pou refine la prompt ak codebase context. We didn't, because:

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