AI improvement prompts

How it works

Two pieces of willakuy combine on click:

• The tarisqa — title, description, evidence, remediation, CWE — already loaded wan chay willakuy.
• Your codebase's framework — detected manta chay qhaway's discovery.tech-fingerprint tarisqakuna (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Falls back man a generic recipe hayk'aq mana framework kan detected (chay agent prompt then asks chay LLM man detect it manta chay 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.

What chay prompt looks like

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.

Supported frameworks

We surface framework-specific snippets paq:

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

Framework detection kan best-effort. We sniff __NEXT_DATA__ tags, __NUXT__, hash cookies (laravel_session), X-Powered-By headers, hinallataq a few other signals. If qan're running a custom framework, chay prompt falls back man chay generic recipe hinallataq chay agent figures it out manta niyki package.json.

Use it manta niyki AI agent

If qan've wired up chay MCP sirwiq, chay same prompt kan exposed as a slash command. From 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.

Why ñuqayku don't hit Claude per click

On launch ñuqayku considered calling chay Anthropic API paq each click man refine chay prompt wan codebase context. We didn't, because:

• The agent chay user pastes into already has codebase context — they're using Cursor / Claude Desktop wan their repo open.
• Templating per-(check × framework) covers ~80% of chay value mana any per-click cost.
• A “Refine wan AI paq my codebase” opt-in could fire chay API later if ruwaqkuna want it. Today, mana.