AI improvement prompts

ከመይ ይሰርሕ

ኣብ click ክልተ ዳታ ይጣመሩ:

• እቲ finding — title, description, evidence, remediation, CWE — ምስ ጸብጻብ ቀዲሙ ተጻዒኑ ኣሎ።
• Framework ናይ codebaseካ — ካብ scan ናይ discovery.tech-fingerprint findings ይፍለጥ (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask)። Framework እንተዘይተረኺቡ ናብ generic recipe ይምለስ (agent prompt ድማ LLM ካብ repo state ከለልዮ ይሓትት)።

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 ከመይ ይመስል

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.

ዝድገፉ frameworks

Framework-specific snippets ንእዚኦም ነቕርብ:

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

Framework detection best-effort እዩ። Tags __NEXT_DATA__, __NUXT__, hash cookies (laravel_session), X-Powered-By headers, ን ገለ ካልኦት signals ንsniff ንገብር። Custom framework ትጥቀም እንተለኻ፣ prompt ናብ generic recipe ይምለስ፣ agent ድማ ካብ package.jsonካ ይፈልጦ።

ካብ AI agentካ ተጠቐምሉ

MCP server ኣራኺብካዮ እንተለኻ፣ ተመሳሳሊ prompt ከም slash command ይቕላዕ። ካብ Claude 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.

ስለምንታይ ንነፍሲ ወከፍ click Claude ዘይንወቅዕ

ኣብ launch ንነፍሲ ወከፍ click Anthropic API ብምጽዋዕ prompt ብ codebase context ክነጽርዮ ሓሲብና ነይርና። ኣይገበርናዮን፣ ምኽንያቱ:

• እቲ user ዝለጥፎ agent ቀዲሙ codebase context ኣለዎ፤ Cursor / Claude Desktop ምስ repo ተኸፊቱ እዮም ዝጥቀሙ።
• Templating per-(check × framework) ካብ ዋጋ ~80% ብዘይ per-click cost ይሽፍን።
• “AI ን codebaseይ ዝያዳ የጽርዮ” ዝብል opt-in ኣብ ድሕሪ ሕጂ users እንተደልዮም API ከበግስ ይኽእል። ሎሚ ግን የለን።