AI improvement prompts

Kako funkcionira

Dva se podatka kombiniraju na klik:

• Nalaz - naslov, opis, dokaz, sanacija, CWE - već učitano s izvješćem.
• Framework vaše baze koda - otkriven iz nalaza discovery.tech-fingerprint skeniranja (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Ako framework nije otkriven, koristi se generički recept (upit agenta zatim traži od LLM-a da ga otkrije iz stanja repozitorija).

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 upit 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 frameworkovi

Prikazujemo isječke specifične za framework 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 na generički)

Otkrivanje frameworka je best-effort. Prepoznajemo __NEXT_DATA__ tagove, __NUXT__, hash kolačiće (laravel_session), X-Powered-By zaglavlja i nekoliko drugih signala. Ako koristite prilagođeni framework, upit se vraća na generički recept, a agent to razaznaje iz vašeg package.json.

Koristite iz svog AI agenta

Ako ste povezali MCP poslužitelj, isti upit izložen je kao slash naredba. 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 na svaki klik

Pri lansiranju smo razmatrali pozivanje Anthropic API-ja za svaki klik kako bismo doradili upit kontekstom baze koda. Nismo, jer:

• Agent u koji korisnik lijepi već ima kontekst baze koda - koristi Cursor / Claude Desktop s otvorenim repozitorijem.
• Predlošci po paru (provjera × framework) pokrivaju ~80% vrijednosti bez ikakvog troška po kliku.
• Opcija “Dorada AI-jem za moju bazu koda” mogla bi kasnije pokrenuti API ako korisnici to žele. Danas, ne.