AI improvement prompts

እንዴት ይሰራል

በclick ላይ ሁለት data ይዋሃዳሉ:

• Finding — title፣ description፣ evidence፣ remediation፣ CWE — ከreport ጋር ቀድሞ loaded ነው።
• የcodebaseዎ framework — ከscan discovery.tech-fingerprint finding-ዎች detected ይሆናል (Next.js፣ React፣ Vue፣ Django፣ Express፣ Rails፣ Laravel፣ Flask)። Framework ካልተdetect ወደ generic recipe fallback ይደረጋል (ከዚያ agent prompt LLMን ከrepo state እንዲdetect ይጠይቃል)።

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 ምን ይመስላል

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 framework-ዎች

Framework-specific snippet ለእነዚህ እናሳያለን:

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

Framework detection best-effort ነው። የ__NEXT_DATA__ tag፣ __NUXT__፣ hash cookie (laravel_session)፣ X-Powered-By header፣ እና ሌሎች ጥቂት signal እናsniff እናደርጋለን። Custom framework እያስኬዱ ከሆነ prompt ወደ generic recipe fallback ይደረጋል እና agent ከpackage.jsonዎ ይረዳዋል።

ከAI agentዎ ይጠቀሙበት

MCP server ካwire አድርገውት፣ ተመሳሳይ prompt እንደ slash command expose ይሆናል። ከClaude Desktop:

/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.

በእያንዳንዱ click Claudeን ለምን አንጠራም

በlaunch ጊዜ ለእያንዳንዱ click በcodebase context prompt ለማrefine Anthropic API መጥራት አስበን ነበር። አላደረግነውም፣ ምክንያቱም:

• User የሚpaste የሚያደርገው agent ቀድሞውኑ codebase context አለው — repoውን open አድርገው Cursor / Claude Desktop እየተጠቀሙ ነው።
• Per-(check × framework) templating ያለ per-click cost የvalueውን ~80% ይcover ያደርጋል።
• User-ዎች ከፈለጉ “ለcodebaseዬ በAI refine ያድርጉ” opt-in በኋላ API fire ሊያደርግ ይችላል። ዛሬ፣ አይደለም።