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.

Sut mae'n gweithio

Mae dau ddarn o ddata yn cyfuno wrth glicio:

  • Y canfyddiad — teitl, disgrifiad, tystiolaeth, adferiad, CWE — eisoes wedi'i lwytho gyda'r adroddiad.
  • Framework eich codebase — wedi'i ganfod o ganfyddiadau discovery.tech-fingerprint y sgan (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Yn cwympo'n ôl i rysáit generig pan na ganfyddir framework (yna mae prompt yr asiant yn gofyn i'r LLM ei ganfod o gyflwr y 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.

Sut olwg sydd ar y prompt

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.

Frameworks a gefnogir

Rydym yn dangos snippets penodol i framework ar gyfer:

  • Next.js, React, Vue, Nuxt, Svelte (frontend)
  • Express, Fastify (Node.js backend)
  • Django, Flask (Python)
  • Ruby on Rails
  • Laravel (PHP)
  • ASP.NET Core (wedi'i gynllunio, fallback i generig heddiw)

Mae canfod framework yn best-effort. Rydym yn sniffio tagiau __NEXT_DATA__, __NUXT__, cookies hash (laravel_session), penawdau X-Powered-By, ac ychydig o signalau eraill. Os ydych yn rhedeg framework custom, mae'r prompt yn cwympo'n ôl i'r rysáit generig ac mae'r asiant yn ei ddatrys o'ch package.json.

Defnyddiwch ef o'ch asiant AI

Os ydych wedi cysylltu'r gweinydd MCP, mae'r un prompt yn cael ei amlygu fel slash command. O 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.

Pam nad ydym yn taro Claude fesul clic

Ar lansio gwnaethom ystyried galw'r Anthropic API ar gyfer pob clic i fireinio'r prompt gyda chyd-destun codebase. Ni wnaethom, oherwydd:

  • Mae gan yr asiant mae'r defnyddiwr yn gludo iddo gyd-destun codebase eisoes: maent yn defnyddio Cursor / Claude Desktop gyda'u repo ar agor.
  • Mae templedu fesul (check × framework) yn cwmpasu ~80% o'r gwerth heb gost fesul clic.
  • Gallai opt-in “Refine with AI for my codebase” danio'r API yn nes ymlaen os yw defnyddwyr eisiau hynny. Heddiw, na.
AI improvement prompts — Docs · FixWeb