// 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 — no Claude API call from us.
આ કેવી રીતે કામ કરે છે
Click પર બે data pieces જોડાય છે:
- Finding — title, description, evidence, remediation, CWE — report સાથે પહેલેથી loaded.
- તમારા codebase નું framework — scan ના
discovery.tech-fingerprintfindings માંથી detected (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Framework detect ન થાય ત્યારે generic recipe પર fall back થાય છે (agent prompt પછી repo state માંથી detect કરવા LLM ને પૂછે છે).
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 કેવો દેખાય છે
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.
સમર્થિત frameworks
અમે framework-specific snippets આ માટે surface કરીએ છીએ:
- Next.js, React, Vue, Nuxt, Svelte (frontend)
- Express, Fastify (Node.js backend)
- Django, Flask (Python)
- Ruby on Rails
- Laravel (PHP)
- ASP.NET Core (planned, fallback to generic today)
Framework detection best-effort છે. અમે __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers, અને થોડા બીજા signals sniff કરીએ છીએ. તમે custom framework ચલાવો છો તો prompt generic recipe પર fall back થાય છે અને agent તમારા package.json માંથી તેને figure out કરે છે.
તમારા AI agent માંથી વાપરો
જો તમે MCP server wire કર્યો હોય, તો એ જ prompt slash command તરીકે exposed છે. Claude Desktop માંથી:
/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.
અમે દરેક click પર Claude ને hit કેમ કરતા નથી
Launch સમયે અમે codebase context સાથે prompt refine કરવા દરેક click પર Anthropic API call કરવાનો વિચાર કર્યો હતો. અમે ન કર્યું, કારણ કે:
- User paste કરે છે તે agent પાસે codebase context already છે: તેઓ repo open રાખીને Cursor / Claude Desktop વાપરે છે.
- Per-(check × framework) templating કોઈ per-click cost વિના ~80% value cover કરે છે.
- Users ઇચ્છે તો “Refine with AI for my codebase” opt-in પછી API fire કરી શકે. આજે, નહીં.
