AI improvement prompts

यसले कसरी काम गर्छ

Click गर्दा data का दुई टुक्रा जोडिन्छन्:

• Finding — title, description, evidence, remediation, CWE — report सँग पहिले नै loaded।
• तपाईंको codebase framework — scan का discovery.tech-fingerprint findings बाट detected (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask)। Framework detect नभए generic recipe मा fallback हुन्छ (agent prompt ले त्यसपछि LLM लाई repo state बाट detect गर्न भन्छ)।

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 कस्तो देखिन्छ

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

हामी यीका लागि framework-specific snippets surface गर्छौँ:

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

Framework detection best-effort हो। हामी __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers, र केही अरू signals sniff गर्छौँ। तपाईं custom framework चलाइरहनुभएको छ भने prompt generic recipe मा fallback हुन्छ र agent ले तपाईंको package.json बाट पत्ता लगाउँछ।

तपाईंको AI agent बाट प्रयोग गर्नुहोस्

तपाईंले MCP server wire गर्नुभएको छ भने त्यही prompt slash command रूपमा exposed हुन्छ। Claude Desktop बाट:

/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.

हामी हरेक click मा Claude किन hit गर्दैनौँ

Launch मा हामीले प्रत्येक click का लागि codebase context सहित prompt refine गर्न Anthropic API call गर्ने विचार गरेका थियौँ। गरेनौँ, किनभने:

• User ले paste गर्ने agent सँग पहिले नै codebase context हुन्छ — उनीहरूले Cursor / Claude Desktop मा repo open गरेर प्रयोग गरिरहेका हुन्छन्।
• प्रति-(check × framework) templating ले per-click cost बिना ~80% value cover गर्छ।
• “Refine with AI for my codebase” opt-in ले users चाहन्छन् भने पछि API fire गर्न सक्छ। आज, छैन।