# Skylight Diner: Agent-Direct Score F (33.8%)

Site: https://skylightdinernyc.com/
Report: https://directindex.org/r/skylightdinernyc.com
Scanned: 2026-10-15 (Provisional: the action test and the assistant citation check still to come; the hatched part of the bar is not measured yet.)
Skylight Diner is largely invisible to agents.
AI assistants cannot open the website of Skylight Diner, so they rely on what other sites say about it.

## Direct links
- Order directly: https://www.skylightdinernyc.com/OrderOnline.tpl?cart=1792077515167931149 (on the business's own site)
- Menu: https://www.skylightdinernyc.com/ShowMenu.tpl?cart=1792077515167931149
- Phone: +1-212-244-0395

## What to fix first
- **The site turns every visitor without a browser away, AI agents included.** (+15 points) A plain fetch was refused (TimeoutError: The operation was aborted due to timeout); only a real browser got the page. Every AI crawler and agent is turned away the same way, so Reachable scores 0 and the rest is measured on the rendered page. Ask the host to let the AI user agents through. Guide: https://directindex.org/guides/blocking-ai-crawlers-without-knowing
- **No structured data for the business.** (+15 points) Add schema.org JSON-LD for the business (Restaurant, LocalBusiness or the closest type, with name, address, telephone and openingHoursSpecification, plus servesCuisine and acceptsReservations). It is the one block every assistant reads first; the fix kit below has it filled in. Guide: https://directindex.org/guides/structured-data-restaurant
- **robots.txt blocks GPTBot, ClaudeBot, PerplexityBot, Google-Extended, OAI-SearchBot, ChatGPT-User, Claude-User, Perplexity-User.** (no points, still worth doing) These are the crawlers behind ChatGPT, Claude, Perplexity and Google's AI features. Remove the Disallow lines for them, or add explicit Allow rules. Guide: https://directindex.org/guides/robots-txt-for-ai-agents

## Fix kit: What to paste

Structured data (JSON-LD). One block in the page's head, or in the builder's custom-code slot. Replace anything that is wrong.

```html
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Restaurant",
  "name": "Skylight Diner",
  "url": "https://skylightdinernyc.com/",
  "telephone": "+1-212-244-0395",
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "West 34th Street 402",
    "postalCode": "10001",
    "addressLocality": "New York"
  },
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 40.7534046,
    "longitude": -73.9967702
  },
  "openingHours": "24/7",
  "openingHoursSpecification": [
    {
      "@type": "OpeningHoursSpecification",
      "dayOfWeek": [
        "Monday",
        "Tuesday",
        "Wednesday",
        "Thursday",
        "Friday",
        "Saturday",
        "Sunday"
      ],
      "opens": "00:00",
      "closes": "23:59"
    }
  ],
  "servesCuisine": [
    "american",
    "burger",
    "soup",
    "salad",
    "omelette",
    "sandwich",
    "breakfast"
  ],
  "hasMenu": "https://www.skylightdinernyc.com/ShowMenu.tpl?cart=1792077515167931149",
  "potentialAction": [
    {
      "@type": "OrderAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://www.skylightdinernyc.com/OrderOnline.tpl?cart=1792077515167931149",
        "actionPlatform": [
          "http://schema.org/DesktopWebPlatform",
          "http://schema.org/MobileWebPlatform"
        ]
      }
    }
  ]
}
</script>
```

robots.txt. Add these lines to /robots.txt and delete any Disallow rule that names these crawlers.

```
# Let AI assistants read the site: they send people to you; a marketplace keeps them.
# Remove any Disallow lines for these names elsewhere in this file.
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Perplexity-User
Allow: /
```

## Already right
- **Menu or price list is an HTML page.** Agents can read items and prices directly.
- **Ordering on your own site.** Agents can order without a marketplace in the loop.

## Since the scan of 2026-10-14 (F then)
- Fixed: The site could not be read at all
- New: robots.txt blocked AI crawlers; The site turned every visitor without a browser away; No structured data for the business

## Where it stands
3248 of 4122 in New York. Top 79% of the sites scanned in this index.

| What the top tenth of the index does | Top 10% | This site |
|---|---|---|
| Take bookings or orders on their own domain | 100% | yes |
| Publish the menu or price list as HTML | 99% | yes |
| Let AI crawlers in (no edge block, no robots.txt block) | 94% | no |
| Structured data with address, phone and hours | 47% | no |
| Have an llms.txt | 13% | no |

Nearest places with a similar menu: The Landing (B, 442 m, https://directindex.org/r/thelanding.nyc); Pat LaFrieda Meat Purveyors (B, 548 m, https://directindex.org/r/thepennsy.nyc); Andrews NYC Diner (D, 613 m, https://directindex.org/r/andrewsnycdiner.com); Schnippers Quality Kitchen (A, 639 m, https://directindex.org/r/schnippers.com); Niles NYC (F, 649 m, https://directindex.org/r/nilesnyc.com); Bagel To Sandwiches (D, 651 m, https://directindex.org/r/bageltosandwich.com); Macaron Café (C, 673 m, https://directindex.org/r/macaroncafe.com); Pennsylvania 6 (D, 758 m, https://directindex.org/r/pennsylvania6nyc.com); Ess-a-Bagel (B, 820 m, https://directindex.org/r/ess-a-bagel32.com); The Counter (C, 863 m, https://directindex.org/r/thecounter.com).

## What assistants answer
Not asked yet. Assistants are asked about the top-ranked businesses in each city index, and about every claimed business the moment it is claimed; claim this page to be included.

See what an AI agent reads on this site: https://directindex.org/r/skylightdinernyc.com/agent-view

## Businesses like Skylight Diner in New York

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in New York | 4122 | 56% | 42% | 33.8% |

The best of the businesses of the same kind in New York: Akdeniz (A 100%, https://directindex.org/r/akdeniz46.com); Amelie Wine Bar (A 100%, https://directindex.org/r/ameliewinebar.com); Angelina's (A 100%, https://directindex.org/r/angelinasristorante.com); Antoya Korean BBQ (A 100%, https://directindex.org/r/anto.com); Betty (A 100%, https://directindex.org/r/bettynewyork.com).

With the two fixes above (The site turns every visitor without a browser away, AI agents included; No structured data for the business) the score would be about 80%: 999th of 4,122 in New York, up from 3248th.

## The direct record
What agents get for Skylight Diner, as JSON: https://directindex.org/api/direct/skylightdinernyc.com
- Book: none on record
- Order: https://www.skylightdinernyc.com/OrderOnline.tpl?cart=1792077515167931149 (own site; found by the scan of 2026-10-15, not yet tested)
- Menu: https://www.skylightdinernyc.com/ShowMenu.tpl?cart=1792077515167931149 (html_page; from the scan)
- Hours: 24/7 (open now) (from OpenStreetMap)
- Phone: +1-212-244-0395
- Stable links that count: https://directindex.org/go/skylightdinernyc.com/order, https://directindex.org/go/skylightdinernyc.com/menu

## Can an agent transact?
Measured, not scored (the score stays at spec v1.0).
- UCP profile (/.well-known/ucp, Google and Shopify's Universal Commerce Protocol): no
- ACP discovery document (/.well-known/acp.json, OpenAI and Stripe's Agentic Commerce Protocol): no
- MCP server card (/.well-known/mcp/server-card.json): no
- Ordering vendor that takes agent orders (Square, Toast, or a vendor whose terms allow agents): no

Only a real browser got this page (a plain fetch got TimeoutError: The operation was aborted due to timeout); Readable and Actionable were measured on the rendered page.

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 0 | 25 |
| Readable | 7 | 25 |
| Actionable | 15 | 15 (the action test: pending) |
| Cited | 0 | 0 (the assistant citation check: pending) |

## Agent readiness (Cloudflare)
Not measured for this scan.
- JSON-LD for the business: no

Keep watching this business (https://directindex.org/r/skylightdinernyc.com/plan): the assistants asked again every month, with what changed; 2 EUR a month or 19 EUR a year.
Deep report: https://directindex.org/r/skylightdinernyc.com/deep. Ten questions the way people ask, each assistant's full answer, the eight nearest similar places, the fix plan and a PDF: 5 EUR, one-off. Reading and scanning stay free; these few euros pay for the questions sent to the assistants and for the servers.
Methodology: https://directindex.org/methodology · Rescan now: https://directindex.org/scan?url=skylightdinernyc.com&force=1