AI improvement prompts

Si funksionon

Dy pjesë të dhënash kombinohen në click:

• Finding — title, description, evidence, remediation, CWE — tashmë loaded me report.
• Framework i codebase tuaj — detected nga findings discovery.tech-fingerprint të scan (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Falls back te generic recipe kur nuk detected framework (agent prompt pastaj i kërkon LLM ta detect nga 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.

Si duket 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 të mbështetura

Ne shfaqim framework-specific snippets për:

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

Framework detection është best-effort. Ne sniff tags __NEXT_DATA__, __NUXT__, hash cookies (laravel_session), headers X-Powered-By dhe disa signals të tjera. Nëse përdorni custom framework, prompt falls back te generic recipe dhe agent e kupton nga package.json juaj.

Përdoreni nga AI agent juaj

Nëse keni wired up MCP server, i njëjti prompt ekspozohet si slash command. Nga 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.

Pse nuk e godasim Claude për çdo click

Në launch menduam të thërrisnim Anthropic API për çdo click për ta refine prompt me codebase context. Nuk e bëmë, sepse:

• Agent ku user paste-on prompt tashmë ka codebase context — ata përdorin Cursor / Claude Desktop me repo hapur.
• Templating per-(check × framework) mbulon ~80% të value pa per-click cost.
• Një opt-in “Refine with AI for my codebase” mund të fire API më vonë nëse users e duan. Sot, jo.