AI improvement prompts

Яаж ажилладаг вэ

Click хийхэд хоёр data piece combine болно:

• The finding — title, description, evidence, remediation, CWE — report-той хамт already loaded.
• Your codebase's framework — scan-ийн discovery.tech-fingerprint findings-аас detected (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Framework detected биш бол generic recipe рүү falls back болно (agent prompt дараа нь LLM-ээс repo state-аас detect хийхийг хүснэ).

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 ямар харагддаг вэ

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

Бид framework-specific snippets-ийг дараахад харуулдаг:

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

Framework detection нь best-effort. Бид __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers болон бусад signals sniff хийнэ. Custom framework ажиллуулж байвал prompt generic recipe рүү falls back болж, agent үүнийг таны package.json-аас ойлгоно.

AI agent-аасаа ашиглах

MCP server холбогдсон бол ижил prompt slash command хэлбэрээр exposed байна. Claude Desktop-аас:

/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.

Яагаад click бүрт Claude руу очдоггүй вэ

Launch дээр бид click бүрт Anthropic API call хийж prompt-ыг codebase context-оор refine хийхийг бодсон. Гэхдээ тэгээгүй, учир нь:

• User paste хийдэг agent-д codebase context already байгаа — тэд repo нээлттэй Cursor / Claude Desktop ашиглаж байна.
• Per-(check × framework) templating нь per-click cost байхгүйгээр ~80% value өгнө.
• “Refine with AI for my codebase” opt-in дараа нь users хүсвэл API fire хийж болно. Өнөөдөр бол үгүй.