AI improvement prompts

Çawa dixebite

Du perçeyên daneyê di clickê de tên hev:

• Finding — sernav, danasîn, evidence, remediation, CWE — jixwe bi raporê re hatiye barkirin.
• Framework-a codebase-a te — ji findingên discovery.tech-fingerprint yên scanê tê dîtin (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Dema framework neyê dîtin dikeve receta generic (prompt-a agent paşê ji LLM dixwaze wê ji rewşa repo bibîne).

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 çawa xuya dike

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.

Frameworkên piştgirîkirî

Em snippetên framework-specific ji bo van derdixin:

• Next.js, React, Vue, Nuxt, Svelte (aliyê pêş)
• Express, Fastify (backend-a Node.js)
• Django, Flask (Python)
• Ruby on Rails
• Laravel (PHP)
• ASP.NET Core (plansazkirî, îro fallback bo generic)

Dîtina frameworkê best-effort e. Em tagên __NEXT_DATA__, __NUXT__, cookieyên hash (laravel_session), headerên X-Powered-By, û çend nîşanên din sniff dikin. Heke tu frameworkek custom dimeşînî, prompt vedigere receta generic û agent wê ji package.json-a te derdixe.

Ji agentê AI ya xwe bi kar bîne

Heke te MCP server girêdaye, heman prompt wekî fermana slash tê eşkere kirin. Ji 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.

Çima em ji bo her clickê Claude naxînin

Di destpêkê de me difikirî ji bo her clickê Anthropic API bang bikin da promptê bi context-a codebaseê refine bikin. Me nekir, ji ber ku:

• Agenta ku bikarhêner paste dike jixwe context-a codebaseê heye — ew Cursor / Claude Desktop bi repo-ya xwe ya vekirî bi kar tînin.
• Templating a her-(check × framework) bê tu lêçûna her-clickê ~80% ji nirxê digire.
• Opt-in-a “Refine with AI for my codebase” dikare paşê API fire bike heke bikarhêner bixwazin. Îro, na.