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.

ಇದು ಹೇಗೆ ಕೆಲಸ ಮಾಡುತ್ತದೆ

Click ಮಾಡಿದಾಗ ಎರಡು data pieces ಸೇರಿಕೊಳ್ಳುತ್ತವೆ:

  • Finding — title, description, evidence, remediation, CWE — report ಜೊತೆ ಈಗಾಗಲೇ loaded.
  • ನಿಮ್ಮ codebase framework — scan ನ discovery.tech-fingerprint findings ನಿಂದ detected (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Framework detect ಆಗದಿದ್ದರೆ generic recipe ಗೆ fall back ಆಗುತ್ತದೆ (agent prompt ನಂತರ repo state ನಿಂದ detect ಮಾಡಲು LLM ಗೆ ಕೇಳುತ್ತದೆ).

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.

Prompt ಹೇಗೆ ಕಾಣುತ್ತದೆ

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.

ಬೆಂಬಲಿತ frameworks

ನಾವು framework-specific snippets ಅನ್ನು ಇವುಗಳಿಗೆ surface ಮಾಡುತ್ತೇವೆ:

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

Framework detection best-effort. ನಾವು __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers, ಮತ್ತು ಇನ್ನೂ ಕೆಲವು signals sniff ಮಾಡುತ್ತೇವೆ. ನೀವು custom framework run ಮಾಡುತ್ತಿದ್ದರೆ, prompt generic recipe ಗೆ fall back ಆಗುತ್ತದೆ ಮತ್ತು agent ನಿಮ್ಮ package.json ನಿಂದ ಅದನ್ನು figure out ಮಾಡುತ್ತದೆ.

ನಿಮ್ಮ AI agent ನಿಂದ ಬಳಸಿ

ನೀವು MCP server wire ಮಾಡಿದ್ದರೆ, ಅದೇ prompt slash command ಆಗಿ exposed. Claude Desktop ನಿಂದ:

/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.

ಪ್ರತಿ click ಗೆ Claude ಅನ್ನು ಯಾಕೆ hit ಮಾಡುವುದಿಲ್ಲ

Launch ಸಮಯದಲ್ಲಿ, codebase context ಜೊತೆ prompt refine ಮಾಡಲು ಪ್ರತಿ click ಗೆ Anthropic API call ಮಾಡುವುದನ್ನು ನಾವು ಪರಿಗಣಿಸಿದ್ದೇವೆ. ಮಾಡಲಿಲ್ಲ, ಏಕೆಂದರೆ:

  • User paste ಮಾಡುವ agent ಗೆ codebase context already ಇದೆ: ಅವರು repo open ಮಾಡಿಕೊಂಡ Cursor / Claude Desktop ಬಳಸುತ್ತಿದ್ದಾರೆ.
  • ಪ್ರತಿ (check × framework) templating ಯಾವುದೇ per-click cost ಇಲ್ಲದೆ ~80% value cover ಮಾಡುತ್ತದೆ.
  • Users ಬಯಸಿದರೆ “Refine with AI for my codebase” opt-in ಮುಂದೆ API fire ಮಾಡಬಹುದು. ಇಂದು, ಇಲ್ಲ.
AI improvement prompts — Docs · FixWeb