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 — no Claude API call from us.

Как работи

Две части данни се комбинират при click:

  • Откритият проблем: title, description, evidence, remediation, CWE, вече заредени с отчета.
  • Framework-ът на твоя codebase: засечен от откритите проблеми discovery.tech-fingerprint в сканирането (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Връща се към generic recipe, когато не бъде засечен framework (prompt-ът за агента тогава иска от LLM да го засече от 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.

Как изглежда prompt-ът

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.

Поддържани framework-и

Показваме framework-specific snippets за:

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

Framework detection е best-effort. Sniff-ваме __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers и още няколко сигнала. Ако използваш custom framework, prompt-ът fallback-ва към generic recipe и агентът го разбира от твоя package.json.

Използвай го от своя AI агент

Ако си свързал MCP сървъра, същият prompt е изложен като slash command. От 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.

Защо не удряме Claude при всеки click

При launch обмисляхме да викаме Anthropic API за всеки click, за да refine-нем prompt-а с codebase context. Не го направихме, защото:

  • Агентът, в който потребителят paste-ва, вече има codebase context: използва Cursor / Claude Desktop с отворено repo.
  • Templating по (check × framework) покрива ~80% от стойността без per-click cost.
  • Опция “Refine with AI for my codebase” би могла да fire-не API по-късно, ако потребителите я искат. Днес: не.
AI improvement prompts — Docs · FixWeb