FixWeb

// docs / ai fix prompts

AI improvement prompts

Every finding has a Copy prompt button beneath the remediation. Click it, paste into Claude / Cursor / Copilot, and the agent gets the canonical improvement recipe for that website-quality issue β€” no Claude API call from us.

Cara ia berfungsi

Dua keping data bergabung apabila diklik:

  • Dapatan β€” tajuk, penerangan, bukti, remediasi, CWE β€” sudah dimuatkan bersama laporan.
  • Framework codebase anda β€” dikesan daripada dapatan discovery.tech-fingerprint imbasan (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Fallback kepada resipi generik apabila tiada framework dikesan (prompt agen kemudian meminta LLM mengesannya daripada keadaan repo).

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.

Rupa 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.

Framework disokong

Kami memaparkan snippet khusus framework untuk:

  • Next.js, React, Vue, Nuxt, Svelte (frontend)
  • Express, Fastify (backend Node.js)
  • Django, Flask (Python)
  • Ruby on Rails
  • Laravel (PHP)
  • ASP.NET Core (dirancang, fallback kepada generik hari ini)

Pengesanan framework ialah usaha terbaik. Kami menghidu tag __NEXT_DATA__, __NUXT__, hash cookie (laravel_session), header X-Powered-By, dan beberapa isyarat lain. Jika anda menjalankan framework tersuai, prompt fallback kepada resipi generik dan agen memikirkannya daripada package.json anda.

Gunakan daripada agen AI anda

Jika anda telah menyambungkan server MCP, prompt yang sama didedahkan sebagai slash command. Daripada 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.

Mengapa kami tidak memanggil Claude setiap klik

Semasa pelancaran, kami mempertimbangkan untuk memanggil Anthropic API bagi setiap klik untuk memperhalusi prompt dengan konteks codebase. Kami tidak melakukannya, kerana:

  • Agen tempat pengguna menampal prompt sudah mempunyai konteks codebase β€” mereka menggunakan Cursor / Claude Desktop dengan repo terbuka.
  • Templating per-(check Γ— framework) meliputi ~80% nilai tanpa sebarang kos per klik.
  • Opt-in β€œPerhalusi dengan AI untuk codebase saya” boleh memanggil API kemudian jika pengguna mahukannya. Hari ini, tidak.
AI improvement prompts β€” Docs Β· FixWeb