AI improvement prompts

Isebenza kanjani

Izingcezu ezimbili zedatha ziyahlangana uma uchofoza:

• I-finding — title, description, evidence, remediation, CWE — isivele ilayishiwe nombiko.
• I-framework ye-codebase yakho — itholwa kuma-findings e-discovery.tech-fingerprint eskeni (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Ibuyela kuresiphi ejwayelekile uma kungekho framework etholiwe (i-agent prompt bese icela i-LLM ukuthi iyithole esimweni se-repo).

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.

I-prompt ibukeka kanjani

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.

Ama-frameworks asekelwayo

Siveza ama-snippets aqondene ne-framework ku:

• Next.js, React, Vue, Nuxt, Svelte (frontend)
• Express, Fastify (Node.js backend)
• Django, Flask (Python)
• Ruby on Rails
• Laravel (PHP)
• ASP.NET Core (kuhleliwe, okwamanje ibuyela ku-generic)

Ukutholwa kwe-framework kwenziwa ngomzamo ongcono. Sinuka ama-tags e-__NEXT_DATA__, __NUXT__, ama-hash cookies (laravel_session), ama-headers e-X-Powered-By, nezinye izimpawu ezimbalwa. Uma usebenzisa i-framework yangokwezifiso, i-prompt ibuyela kuresiphi ejwayelekile bese i-agent ikuthola ku-package.json yakho.

Yisebenzise ku-agent yakho ye-AI

Uma usuxhume iseva ye-MCP, i-prompt efanayo ivezwa njengomyalo we-slash. Kusuka ku-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.

Kungani singashayi i-Claude kuzo zonke izichofozo

Ngesikhathi sokuqala sacabanga ukubiza i-Anthropic API kuzo zonke izichofozo ukuze sicwenge i-prompt nge-context ye-codebase. Asikwenzanga, ngoba:

• I-agent umsebenzisi anamathisela kuyo ivele ine-context ye-codebase — basebenzisa i-Cursor / Claude Desktop ne-repo yabo ivuliwe.
• Ukutemplata nge-(check × framework) kumboza cishe u-80% wenani ngaphandle kwezindleko ze-click ngayinye.
• Inketho ethi “Refine with AI for my codebase” ingashisa i-API kamuva uma abasebenzisi beyifuna. Namuhla, cha.