AI improvement prompts

Otú ọ si arụ ọrụ

Iberibe data abụọ na-ejikọta mgbe a pịrị:

• Finding ahụ — title, description, evidence, remediation, CWE — ebula ụzọ load na report.
• Framework nke codebase gị — achọpụtara site na findings discovery.tech-fingerprint nke scan ahụ (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Ọ na-fallback na generic recipe mgbe achọpụtaghị framework (agent prompt ahụ na-ajụ LLM ka ọ chọpụta ya site 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.

Otú prompt si dị

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 a na-akwado

Anyị na-egosi snippets pụrụ iche maka framework ndị a:

• Next.js, React, Vue, Nuxt, Svelte (frontend)
• Express, Fastify (Node.js backend)
• Django, Flask (Python)
• Ruby on Rails
• Laravel (PHP)
• ASP.NET Core (a na-eme atụmatụ, fallback na generic taa)

Framework detection bụ best-effort. Anyị na-sniff tags __NEXT_DATA__, __NUXT__, hash cookies (laravel_session), headers X-Powered-By, na signals ole na ole ọzọ. Ọ bụrụ na ị na-agba custom framework, prompt na-fallback na generic recipe, agent ahụ na-achọpụta ya site na package.json gị.

Jiri ya site na AI agent gị

Ọ bụrụ na ijikọla MCP server, otu prompt ahụ na-apụta dị ka slash command. Site na 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.

Ihe mere anyị anaghị akpọ Claude kwa click

Mgbe launch, anyị tụlere ịkpọ Anthropic API kwa click iji refine prompt na context codebase. Anyị emeghị ya, n'ihi na:

• Agent onye ọrụ na-etapawa n'ime ya enwelarị context codebase ugbua — ha na-eji Cursor / Claude Desktop na repo ha mepere emepe.
• Templating kwa (check × framework) na-ekpuchi ~80% nke uru ahụ na-enweghị cost kwa click.
• Opt-in “Refine with AI for my codebase” nwere ike ịkpọ API ma e mesịa ma ọ bụrụ na ndị ọrụ chọrọ ya. Taa, mba.