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.

Як гэта працуе

Пры click аб'ядноўваюцца два блокі даных:

  • Знаходка — title, description, evidence, remediation, CWE — ужо загружана са справаздачай.
  • Framework вашай codebase — выяўляецца з findings discovery.tech-fingerprint гэтага scan (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Калі framework не знойдзены, выкарыстоўваецца generic recipe (agent prompt тады просіць LLM вызначыць яго з 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.

Як выглядае 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.

Падтрыманыя frameworks

Мы паказваем framework-specific snippets для:

  • Next.js, React, Vue, Nuxt, Svelte (frontend)
  • Express, Fastify (Node.js backend)
  • Django, Flask (Python)
  • Ruby on Rails
  • Laravel (PHP)
  • ASP.NET Core (запланавана, сёння fallback to generic)

Framework detection — best-effort. Мы шукаем tags __NEXT_DATA__, __NUXT__, hash cookies (laravel_session), headers X-Powered-By і некалькі іншых signals. Калі вы карыстаецеся custom framework, prompt falls back to generic recipe, а agent разбіраецца па вашым package.json.

Выкарыстоўвайце з вашага AI agent

Калі вы падключылі MCP server, той самы prompt адкрыты як slash command. З 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.

Чаму мы не выклікаем Claude на кожны click

На launch мы разглядалі Anthropic API call для кожнага click, каб удакладняць prompt з codebase context. Мы гэтага не зрабілі, бо:

  • Agent, у які user устаўляе prompt, ужо мае codebase context — яны выкарыстоўваюць Cursor / Claude Desktop з адкрытым repo.
  • Templating па (check × framework) пакрывае ~80% карысці без per-click cost.
  • Опцыя “Refine with AI for my codebase” можа пазней запускаць API, калі users гэтага захочуць. Сёння — не.
AI improvement prompts — Docs · FixWeb