AI improvement prompts

Kako radi

Dva komada podataka kombinuju se na click:

• Finding — title, description, evidence, remediation, CWE — već loaded s report.
• Framework vaše codebase — detected iz scan findings discovery.tech-fingerprint (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Falls back na generic recipe kada framework nije detected (agent prompt tada traži od LLM da ga detect from 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.

Kako prompt izgleda

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.

Podržani frameworks

Prikazujemo framework-specific snippets za:

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

Framework detection je best-effort. Sniffujemo __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers i nekoliko drugih signals. Ako koristite custom framework, prompt falls back to generic recipe i agent to shvati iz vašeg package.json.

Koristite iz vašeg AI agent

Ako ste wired up MCP server, isti prompt je izložen kao slash command. Iz 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.

Zašto ne zovemo Claude po svakom click

Na launch smo razmatrali Anthropic API call za svaki click da refine prompt s codebase context. Nismo, jer:

• Agent u koji user paste prompt već ima codebase context — koriste Cursor / Claude Desktop s otvorenim repo.
• Templating per-(check × framework) pokriva ~80% value bez per-click cost.
• Opt-in “Refine with AI for my codebase” mogao bi fire API kasnije ako users to žele. Danas, ne.