AI improvement prompts

Кантип иштейт

Click кезинде еки data piece combine болот:

• The finding — title, description, evidence, remediation, CWE — report-пен бирге already loaded.
• Your codebase's framework — scan-ның discovery.tech-fingerprint findings ичинен detected (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Framework detected болмаса generic recipe-ге falls back болот (agent prompt содан кийин LLM-нен repo state бойынша detect етуди сурайт).

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 кандай көринеди

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.

Колдоого алынган frameworks

Биз framework-specific snippets-ти мыналар үчүн көрсөтөбүз:

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

Framework detection best-effort. Биз __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers жана тагы бирнеше signals sniff етемиз. Custom framework колдансаңыз, prompt generic recipe-ге falls back болот жана agent оны package.json ичинен өзи аныктайды.

AI agent аркылуу колдонуңуз

Егер MCP server косылган болсо, сол prompt slash command ретинде exposed. Claude Desktop ичинен:

/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.

Эмне үчүн ар бир click сайын Claude-ка бармаймыз

Launch кезинде ар бир click үчүн Anthropic API шакырып, prompt-ты codebase context-пен refine етуди карастырдык. Оны истемедик, себеби:

• User paste ететин agent-те codebase context already бар — олар repo ачык турган Cursor / Claude Desktop колданады.
• Per-(check × framework) templating ешкандай per-click cost жок ~80% value жабады.
• “Refine with AI for my codebase” opt-in кийин users каласа API fire ете алады. Бүгин — жок.