AI improvement prompts

Чӣ тавр кор мекунад

Ҳангоми click ду порчаи data якҷо мешаванд:

• Finding — title, description, evidence, remediation, CWE — аллакай бо report loaded шудааст.
• Framework-и codebase-и шумо — аз finding-ҳои discovery.tech-fingerprint-и scan detected мешавад (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Вақте framework detected нашавад, ба recipe-и generic меафтад (пас prompt-и agent аз LLM талаб мекунад, ки онро аз repo state detect кунад).

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 чӣ гуна менамояд

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.

Framework-ҳои supported

Мо snippet-ҳои framework-specific-ро барои инҳо нишон медиҳем:

• Next.js, React, Vue, Nuxt, Svelte (frontend)
• Express, Fastify (Node.js backend)
• Django, Flask (Python)
• Ruby on Rails
• Laravel (PHP)
• ASP.NET Core (дар нақша, имрӯз fallback ба generic)

Framework detection best-effort аст. Мо tag-ҳои __NEXT_DATA__, __NUXT__, hash cookies (laravel_session), header-ҳои X-Powered-By ва чанд signal-и дигарро sniff мекунем. Агар шумо custom framework run кунед, prompt ба recipe-и generic меафтад ва agent онро аз package.json-и шумо мефаҳмад.

Онро аз AI agent-и худ истифода баред

Агар MCP server-ро wire up карда бошед, ҳамон prompt ҳамчун slash command expose мешавад. Аз 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.

Чаро мо барои ҳар click ба Claude намезанем

Дар launch мо фикр кардем, ки барои ҳар click Anthropic API-ро call кунем, то prompt-ро бо codebase context refine кунем. Ин корро накардем, зеро:

• Agent-е, ки user ба он paste мекунад, аллакай codebase context дорад — онҳо Cursor / Claude Desktop-ро бо repo-и кушода истифода мебаранд.
• Templating барои ҳар (check × framework) тақрибан ~80% value-ро бе per-click cost мепӯшонад.
• Opt-in-и “Refine with AI for my codebase” метавонад баъдтар API-ро fire кунад, агар users хоҳанд. Имрӯз не.