AI improvement prompts

Conas a oibríonn sé

Comhcheanglaíonn dhá phíosa sonraí ar click:

• An finding — title, description, evidence, remediation, CWE — loaded cheana leis an tuairisc.
• Framework do codebase — detected ó findings discovery.tech-fingerprint an scanadh (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Falls back chuig oideas generic nuair nach detected framework (iarrann an agent prompt ar an LLM é a detect ón repo state ansin).

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.

Cén chuma atá ar an 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 tacaithe

Nochtann muid snippets framework-specific do:

• Next.js, React, Vue, Nuxt, Svelte (taobh tosaigh)
• Express, Fastify (backend Node.js)
• Django, Flask (Python)
• Ruby on Rails
• Laravel (PHP)
• ASP.NET Core (beartaithe, fallback go generic inniu)

Is best-effort é framework detection. Sniffimid tags __NEXT_DATA__, __NUXT__, hash cookies (laravel_session), headers X-Powered-By, agus cúpla signal eile. Má tá framework custom á rith agat, falls back an prompt chuig an generic recipe agus figures an agent é ó do package.json.

Úsáid é ó d'agent AI

Má tá an freastalaí MCP wired up agat, nochtar an prompt céanna mar slash command. Ó 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.

Cén fáth nach mbuailimid Claude in aghaidh click

Ag launch mheasamar glaoch ar an Anthropic API do gach click chun an prompt a refine le context codebase. Ní dhearna muid, mar:

• Tá context codebase ag an agent a ghreamaíonn an t-úsáideoir isteach ann cheana — tá siad ag úsáid Cursor / Claude Desktop lena repo oscailte.
• Clúdaíonn templating per-(check × framework) thart ar 80% den luach gan aon chostas per-click.
• D'fhéadfadh opt-in “Refine with AI for my codebase” an API a fire níos déanaí má theastaíonn sé ó úsáideoirí. Inniu, níl.