AI improvement prompts

Nähili işleýär

Click wagty iki data bölegi birleşýär:

• Finding — title, description, evidence, remediation, CWE — hasabat bilen eýýäm loaded.
• Codebase-iňiziň framework-i — scan-yň discovery.tech-fingerprint findings-inden detected bolýar (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Framework detected bolmasa generic recipe-e fallback bolýar (agent prompt soň LLM-den repo state boýunça tapmagy soraýar).

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 nähili görünýär

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.

Supported frameworks

Framework-specific snippets şular üçin görkezilýär:

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

Framework detection best-effort. Biz __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers we başga birnäçe signal sniff edýäris. Custom framework işledýän bolsaňyz, prompt generic recipe-e fallback bolýar we agent ony package.json-yňyzdan çözer.

AI agent-iňizden ulanyň

MCP server wire up edilen bolsa, şol prompt slash command hökmünde exposed. Claude Desktop-dan:

/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.

Näme üçin her click-de Claude çagyrmaýarys

Launch wagty her click üçin Anthropic API çagyrmak we prompt-y codebase context bilen refine etmek barada pikir etdik. Etmedik, sebäbi:

• User-iň paste edýän agent-i eýýäm codebase context-e eýe — olar repo açyk ýagdaýda Cursor / Claude Desktop ulanýar.
• Her (check × framework) boýunça templating per-click cost bolmazdan value-niň ~80%-ini ýapýar.
• “Refine with AI for my codebase” opt-in soň API fire edip biler, users islese. Şu gün ýok.