snap

Give your agent the ability to instantly take screenshots of any website with just the URL. Cloud-based so your agent has to perform no work. Free forever, open source.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "snap" with this command: npx skills add Kav-K/snap

SnapService — Screenshot as a Service

Free screenshot API at https://snap.llm.kaveenk.com. POST a URL, get a PNG/JPEG back. Powered by headless Chromium.

Quick Start (2 steps)

Step 1: Register for an API key

curl -s -X POST https://snap.llm.kaveenk.com/api/register \
  -H "Content-Type: application/json" \
  -d '{"name":"my-agent"}'

Response:

{"key":"snap_abc123...","name":"my-agent","limits":{"per_minute":2,"per_day":200}}

IMPORTANT: Store key securely. It cannot be recovered.

Each IP address can only register one API key.

Step 2: Take screenshots

curl -s -X POST https://snap.llm.kaveenk.com/api/screenshot \
  -H "Authorization: Bearer snap_yourkey" \
  -H "Content-Type: application/json" \
  -d '{"url":"https://example.com"}' \
  -o screenshot.png

That's it. Two steps.

Screenshot Options

All options go in the POST body alongside url:

OptionTypeDefaultDescription
urlstringrequiredURL to screenshot
formatstring"png""png" or "jpeg"
full_pagebooleanfalseCapture entire scrollable page
widthinteger1280Viewport width (pixels)
heightinteger720Viewport height (pixels)
dark_modebooleanfalseEmulate dark color scheme
selectorstringCSS selector to screenshot specific element
wait_msinteger0Extra wait time after page load (max 10000)
scalenumber1Device scale factor (1-3, for retina)
cookiesarrayArray of {name, value, domain} objects
headersobjectCustom HTTP headers
block_adsbooleanfalseBlock common ad/tracker domains

Rate Limits

  • 2 screenshots per minute per key
  • 200 screenshots per day per key
  • 1 API key per IP address
  • Max page height: 16384px (full-page mode)
  • Max screenshot size: 10MB

Response

  • 200: PNG or JPEG image binary
  • 400: Invalid request (missing URL, invalid options)
  • 401: Missing or invalid API key
  • 409: IP already has an API key (on registration)
  • 429: Rate limit exceeded
  • 500: Internal error

Example with all options

curl -s -X POST https://snap.llm.kaveenk.com/api/screenshot \
  -H "Authorization: Bearer snap_yourkey" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com",
    "format": "jpeg",
    "full_page": true,
    "width": 1920,
    "height": 1080,
    "dark_mode": true,
    "wait_ms": 2000,
    "block_ads": true
  }' \
  -o screenshot.jpg

Python example

import requests

API = "https://snap.llm.kaveenk.com"

# Register (one-time)
r = requests.post(f"{API}/api/register", json={"name": "my-agent"})
key = r.json()["key"]

# Screenshot
r = requests.post(f"{API}/api/screenshot",
    headers={"Authorization": f"Bearer {key}"},
    json={"url": "https://example.com", "full_page": True})
with open("shot.png", "wb") as f:
    f.write(r.content)

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Email Excel Transfer

Pobieranie załączników z maila przez IMAP i wypełnianie plików Excel przez PowerShell. Użyj gdy użytkownik prosi o pobranie plików z email i wstawienie warto...

Registry SourceRecently Updated
Automation

CamScanner Extract Formula

Use CamScanner to extract formulas from images. Powered by OCR recognition engine that detects formula regions in images, crops them, and stitches into a sin...

Registry SourceRecently Updated
Automation

Image Marketing Brochure

A complete workflow skill for marketing brochure design, covering everything from requirements gathering, layout design, to mock-up delivery. It uses a 'layo...

Registry SourceRecently Updated
Automation

Image Social Carousel

A structured workflow skill dedicated to social-media carousel design. The core method is 'decide intent first, then execute,' using a 'single-confirmation +...

Registry SourceRecently Updated