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.

Hvernig þetta virkar

Tvö gagnastykki sameinast við smell:

  • Fundurinn — titill, lýsing, sönnunargögn, úrbót, CWE — þegar hlaðið með skýrslunni.
  • Framework kóðagrunnsins þíns — greint úr discovery.tech-fingerprint fundum skönnunarinnar (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Fellur til baka í almenna uppskrift þegar ekkert framework greinist (agent promptið biður þá LLM að greina það úr stöðu 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.

Hvernig promptið lítur út

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.

Studd frameworks

Við sýnum framework-sértæk snippets fyrir:

  • Next.js, React, Vue, Nuxt, Svelte (frontend)
  • Express, Fastify (Node.js backend)
  • Django, Flask (Python)
  • Ruby on Rails
  • Laravel (PHP)
  • ASP.NET Core (áætlað, fellur í almennt í dag)

Framework greining er best-effort. Við sniffum __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By hausa og nokkur önnur merki. Ef þú keyrir custom framework fellur promptið í almennu uppskriftina og agentinn finnur út úr því út frá package.json.

Notaðu þetta úr AI agentinum þínum

Ef þú hefur tengt MCP þjóninn er sama promptið opnað sem slash command. Úr 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.

Af hverju við hittum ekki Claude í hverjum smelli

Við íhuguðum við ræsingu að kalla Anthropic API fyrir hvern smell til að fínstilla promptið með kóðagrunnssamhengi. Við gerðum það ekki, því:

  • Agentinn sem notandinn límir inn í hefur þegar kóðagrunnssamhengi: hann er að nota Cursor / Claude Desktop með repo opið.
  • Sniðmát fyrir hvert (check × framework) dekka ~80% af virðinu án kostnaðar fyrir hvern smell.
  • Val um “Refine with AI for my codebase” gæti kveikt á API síðar ef notendur vilja það. Í dag, nei.
AI improvement prompts — Docs · FixWeb