AI improvement prompts

Na sala e cakacaka kina

E rua na pieces of data e combine ena click:

• Na finding — title, description, evidence, remediation, CWE — sa loaded oti kei na report.
• Na framework ni nomu codebase — detected mai na scan's discovery.tech-fingerprint findings (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Falls back ki na generic recipe ni sega ni detected e dua na framework (qai kerea na agent prompt vua na LLM me detect mai na repo state).

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.

Na irairai ni prompt

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.

Frameworks e tokoni

Keitou surface framework-specific snippets me baleta:

• 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 e best-effort. Keitou sniff __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers, kei na signals tale eso. Kevaka o running e dua na custom framework, na prompt e fall back ki generic recipe ka na vakasamataka na agent mai na nomu package.json.

Vakayagataka mai nomu AI agent

Kevaka o sa wired up na MCP server, na same prompt e exposed me slash command. Mai 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.

Na vuna keitou sega ni hit Claude ena click yadua

Ena launch keitou a consider calling the Anthropic API ena click yadua me refine na prompt kei codebase context. Keitou sega, baleta:

• Na agent e paste kina na user sa tiko oti vua na codebase context — era vakayagataka tiko Cursor / Claude Desktop kei na nodra repo e open.
• Templating per-(check × framework) e cover ~80% ni value ka sega na per-click cost.
• E rawa ni fire na API e muri e dua na opt-in “Refine with AI for my codebase” kevaka era vinakata users. Nikua, sega.