AI improvement prompts

Qanday ishlaydi

Click paytida ikki data piece combine bo‘ladi:

• The finding — title, description, evidence, remediation, CWE — report bilan already loaded.
• Your codebase's framework — scan’ning discovery.tech-fingerprint findings’dan detected (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Framework detected bo‘lmasa generic recipe’ga falls back bo‘ladi (agent prompt keyin LLM’dan repo state’dan detect qilishni so‘raydi).

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.

Prompt qanday ko‘rinadi

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.

Qo‘llab-quvvatlanadigan frameworks

Biz framework-specific snippets’ni quyidagilar uchun ko‘rsatamiz:

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

Framework detection best-effort. Biz __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers va yana bir necha signals sniff qilamiz. Custom framework ishlatsangiz, prompt generic recipe’ga falls back bo‘ladi va agent uni package.json dan o‘zi aniqlaydi.

AI agentingizdan foydalaning

Agar MCP server ulangan bo‘lsa, xuddi shu prompt slash command sifatida exposed. Claude Desktop’dan:

/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.

Nega har click’da Claude’ga bormaymiz

Launch’da har click uchun Anthropic API chaqirib, prompt’ni codebase context bilan refine qilishni ko‘rib chiqqanmiz. Qilmadik, chunki:

• User paste qiladigan agent’da codebase context already bor — ular repo ochiq turgan Cursor / Claude Desktop ishlatadi.
• Per-(check × framework) templating hech qanday per-click cost’siz ~80% value beradi.
• “Refine with AI for my codebase” opt-in keyin users xohlasa API fire qilishi mumkin. Bugun — yo‘q.