// 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 kerjanya
Dua potongan data digabung saat diklik:
- Temuan β judul, deskripsi, bukti, remediasi, CWE β sudah dimuat bersama laporan.
- Framework codebase kamu β dideteksi dari temuan
discovery.tech-fingerprintmilik pemindaian (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Jika tidak ada framework yang terdeteksi, fallback ke resep generik (prompt agen lalu meminta LLM mendeteksinya dari state 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.
Seperti apa prompt-nya
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 yang didukung
Kami menampilkan 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 (direncanakan, saat ini fallback ke generik)
Deteksi framework bersifat best-effort. Kami mengendus tag __NEXT_DATA__, __NUXT__, hash cookie (laravel_session), header X-Powered-By, dan beberapa sinyal lain. Jika kamu menjalankan framework kustom, prompt fallback ke resep generik dan agen akan mencari tahu dari package.json kamu.
Gunakan dari agen AI kamu
Jika kamu sudah menyambungkan server MCP, prompt yang sama diekspos sebagai slash command. Dari 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 per klik
Saat peluncuran kami sempat mempertimbangkan memanggil Anthropic API untuk setiap klik agar prompt dipoles dengan konteks codebase. Kami tidak melakukannya, karena:
- Agen tempat pengguna menempelkan prompt sudah punya konteks codebase β mereka memakai Cursor / Claude Desktop dengan repo terbuka.
- Templating per-(check Γ framework) mencakup ~80% nilai tanpa biaya per klik.
- Opt-in βPoles dengan AI untuk codebase sayaβ dapat memicu API nanti jika pengguna menginginkannya. Saat ini, tidak.
