AI improvement prompts

එය ක්‍රියා කරන ආකාරය

Click කරන විට data කෑලි දෙකක් combine වේ:

• Finding එක — title, description, evidence, remediation, CWE — report එක සමඟ දැනටමත් loaded.
• ඔබගේ codebase framework එක — scan එකේ discovery.tech-fingerprint findings වලින් detect කළ (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Framework එකක් detect නොවූ විට generic recipe එකකට fallback වේ (agent prompt එක LLM එකට repo state වෙතින් එය detect කරන ලෙස ඉල්ලා සිටී).

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 එක පෙනෙන ආකාරය

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.

සහාය දක්වන frameworks

අපි framework-specific snippets surface කරන්නේ:

• 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 වේ. අපි __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers, සහ තවත් signals කිහිපයක් sniff කරමු. ඔබ custom framework එකක් run කරන්නේ නම්, prompt එක generic recipe වෙත fallback වන අතර agent ඔබගේ package.json වෙතින් එය තේරුම් ගනී.

ඔබගේ AI agent වෙතින් එය භාවිතා කරන්න

ඔබ MCP server wire කර ඇත්නම්, එම prompt එක slash command එකක් ලෙස expose වේ. Claude Desktop වෙතින්:

/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.

අපි click එකකට Claude hit නොකරන්නේ ඇයි

Launch කිරීමේදී, prompt එක codebase context සමඟ refine කිරීමට එක් click එකකට Anthropic API call කිරීම අපි සලකා බැලුවෙමු. අපි එසේ නොකළේ:

• User paste කරන agent එකට codebase context දැනටමත් ඇත — ඔවුන් repo open කර Cursor / Claude Desktop භාවිතා කරයි.
• Per-(check × framework) templating එක per-click cost කිසිවක් නැතිව value එකෙන් ~80% ආවරණය කරයි.
• Users කැමති නම් “Refine with AI for my codebase” opt-in එකක් පසුව API fire කළ හැක. අද, නැත.