AI improvement prompts

Mar a dh'obraicheas e

Thig dà phìos dàta còmhla air click:

• An finding — title, description, evidence, remediation, CWE — loaded mu thràth leis an aithisg.
• Framework do codebase — detected bho findings discovery.tech-fingerprint an scan (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Falls back gu reasabaidh generic nuair nach eil framework detected (iarraidh an agent prompt air an LLM a detect bhon repo state an uair sin).

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.

Cò ris a tha am prompt coltach

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 le taic

Bidh sinn a' sealltainn snippets framework-specific airson:

• Next.js, React, Vue, Nuxt, Svelte (aghaidh)
• Express, Fastify (backend Node.js)
• Django, Flask (Python)
• Ruby on Rails
• Laravel (PHP)
• ASP.NET Core (air a phlanadh, fallback gu generic an-diugh)

Tha framework detection best-effort. Bidh sinn a' sniff tags __NEXT_DATA__, __NUXT__, hash cookies (laravel_session), headers X-Powered-By, agus beagan signals eile. Ma tha thu a' ruith custom framework, falls back am prompt dhan generic recipe agus figures an agent e a-mach bhon package.json agad.

Cleachd e bhon agent AI agad

Ma tha thu air am frithealaiche MCP a wired up, tha an aon prompt fosgailte mar slash command. Bho 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.

Carson nach buail sinn Claude gach click

Aig launch smaoinich sinn air an Anthropic API a ghairm airson gach click gus am prompt a refine le context codebase. Cha do rinn sinn sin, oir:

• Tha context codebase aig an agent dhan cuir an cleachdaiche paste mu thràth — tha iad a' cleachdadh Cursor / Claude Desktop leis an repo fosgailte.
• Tha templating per-(check × framework) a' còmhdach mu 80% den luach gun chosgais per-click sam bith.
• Dh'fhaodadh opt-in “Refine with AI for my codebase” an API a fire nas fhaide air adhart ma tha luchd-cleachdaidh ga iarraidh. An-diugh, chan eil.