// 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.
Nola funtzionatzen duen
Bi datu-pieza konbinatzen dira klik egitean:
- Aurkikuntza — titulua, deskribapena, ebidentzia, konponketa, CWE — dagoeneko txostenarekin kargatuta.
- Zure kodebasearen frameworka — eskaneatzearen
discovery.tech-fingerprintaurkikuntzetatik detektatua (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Frameworkik detektatzen ez denean errezeta generiko batera erortzen da (orduan agentearen promptak LLMri repo egoeratik detektatzeko eskatzen dio).
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.
Nolakoa den prompta
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.
Onartutako frameworkak
Framework espezifikoetako snippetak erakusten ditugu honetarako:
- Next.js, React, Vue, Nuxt, Svelte (frontend)
- Express, Fastify (Node.js backend)
- Django, Flask (Python)
- Ruby on Rails
- Laravel (PHP)
- ASP.NET Core (planifikatuta, gaur generikora erortzen da)
Framework detekzioa ahalegin onenekoa da. __NEXT_DATA__ tagak, __NUXT__, hash cookieak (laravel_session), X-Powered-By goiburuak eta beste seinale batzuk usaintzen ditugu. Framework pertsonalizatu bat erabiltzen baduzu, prompta errezeta generikora erortzen da eta agenteak zure package.json fitxategitik asmatzen du.
Erabili zure AI agentetik
MCP zerbitzaria konektatuta baduzu, prompt bera slash command gisa agertzen da. Claude Desktop-etik:
/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.
Zergatik ez dugun Claude jotzen klik bakoitzean
Abiaraztean pentsatu genuen klik bakoitzean Anthropic APIra deitzea prompta kodebasearen testuinguruarekin fintzeko. Ez genuen egin, arrazoi hauengatik:
- Erabiltzaileak itsasten duen agenteak dagoeneko badu kodebasearen testuingurua: Cursor / Claude Desktop erabiltzen ari da repo irekita duela.
- Check × framework bakoitzeko txantiloitzeak balioaren ~80% estaltzen du klik bakoitzeko kosturik gabe.
- “Refine with AI for my codebase” aukerako botoi batek APIa geroago piztu lezake erabiltzaileek nahi badute. Gaur, ez.
