AI improvement prompts

Fomba fiasany

Data roa no mitambatra rehefa tsindriana:

• Ilay finding: lohateny, famaritana, evidence, remediation, CWE; efa voaload miaraka amin’ny tatitra.
• Framework an’ny codebase-nao: hita avy amin’ny findings discovery.tech-fingerprint an’ilay scan (Next.js, React, Vue, Django, Express, Rails, Laravel, Flask). Raha tsy misy framework hita dia miverina amin’ny recipe ankapobeny (avy eo mangataka amin’ny LLM ny agent prompt hamantatra azy amin’ny toetry ny repo).

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.

Endriky ny 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 tohanana

Mampiseho snippets manokana isaky ny framework izahay ho an’ny:

• Next.js, React, Vue, Nuxt, Svelte (frontend)
• Express, Fastify (backend Node.js)
• Django, Flask (Python)
• Ruby on Rails
• Laravel (PHP)
• ASP.NET Core (kasaina, miverina amin’ny ankapobeny androany)

Best-effort ny fitiliana framework. Tsapainay ny tags __NEXT_DATA__, __NUXT__, hash cookies (laravel_session), headers X-Powered-By, ary famantarana vitsivitsy hafa. Raha mampiasa framework namboarinao manokana ianao, miverina amin’ny recipe ankapobeny ny prompt ary ilay agent no mamantatra azy amin’ny package.json-nao.

Ampiasao avy amin’ny AI agent-nao

Raha efa nampifandray ny MCP server ianao, aseho ho slash command ilay prompt mitovy. Avy amin’i 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.

Antony tsy iantsoanay Claude isaky ny clic

Tamin’ny fanombohana dia nodinihinay ny hiantso Anthropic API isaky ny clic mba hanatsara ny prompt amin’ny context an’ny codebase. Tsy nataonay izany satria:

• Ilay agent ametahan’ny mpampiasa ny prompt dia efa manana context an’ny codebase: mampiasa Cursor / Claude Desktop izy miaraka amin’ny repo misokatra.
• Ny templating isaky ny (check × framework) dia manarona eo amin’ny 80% ny lanja tsy misy vola lany isaky ny clic.
• Safidy opt-in “Refine with AI for my codebase” dia afaka mampandeha ny API any aoriana raha ilain’ny mpampiasa. Androany, tsia.