Build a zero-code screenshot automation with Zapier. Capture any website and send the result to Slack, Google Drive, Airtable, or 6,000+ other apps.
Turn any Google Sheets spreadsheet into a screenshot automation tool. List URLs, run a script, and get screenshot links populated automatically.
Learn how to automatically capture website screenshots and save them to your Airtable base using the Allscreenshots API and Airtable scripting.
Join thousands of developers using Allscreenshots. No credit card required to get started.
OpenClaw is the popular open-source AI agent that turns your local machine into a personal assistant you control from WhatsApp, Telegram, Slack, or Discord. By adding a screenshot skill, you can capture any website with a chat message — no headless browsers, no Puppeteer setup, no local Chrome dependency.
This tutorial shows you how to create an OpenClaw skill that calls the Allscreenshots API to capture pixel-perfect website screenshots on demand.
An OpenClaw skill that lets you say things like:
Your agent will call the Allscreenshots cloud API and return the screenshot directly in your chat.
OpenClaw skills live in ~/.openclaw/skills/. Each skill is a directory with a SKILL.md file inside. Create yours:
mkdir -p ~/.openclaw/skills/allscreenshotsCreate ~/.openclaw/skills/allscreenshots/SKILL.md with the following content. This follows the standard OpenClaw skill format — YAML frontmatter for metadata, then markdown instructions with concrete curl commands the agent can execute.
---
name: allscreenshots
description: Take website screenshots, capture full pages, generate PDFs. Handles desktop, mobile, dark mode, stealth mode, cookie banner blocking, and batch URLs via the Allscreenshots cloud API.
version: 1.0.0
metadata: {"openclaw":{"emoji":"📸","requires":{"bins":["curl","jq"],"env":["ALLSCREENSHOTS_API_KEY"]},"primaryEnv":"ALLSCREENSHOTS_API_KEY"}}
---
# Allscreenshots – Website Screenshot Capture
Capture pixel-perfect website screenshots via the Allscreenshots
cloud API. No local browser needed.
## Setup
1. Get an API key at https://dashboard.allscreenshots.com
2. Add to ~/.openclaw/workspace/.env:
ALLSCREENSHOTS_API_KEY=your_api_key_here
## API Base
Endpoint: https://api.allscreenshots.com/v1/screenshots
Auth header: Bearer $ALLSCREENSHOTS_API_KEY
## Operations
### Desktop screenshot (default)
curl -s -X POST \
-H "Authorization: Bearer $ALLSCREENSHOTS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"TARGET_URL","fullPage":true,"viewport":{"width":1280,"height":800},"blockAds":true,"blockCookieBanners":true,"stealth":true,"responseType":"url"}' \
"https://api.allscreenshots.com/v1/screenshots" | jq
### Mobile screenshot
curl -s -X POST \
-H "Authorization: Bearer $ALLSCREENSHOTS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"TARGET_URL","fullPage":true,"viewport":{"width":375,"height":812},"deviceScaleFactor":3,"blockAds":true,"blockCookieBanners":true,"stealth":true,"responseType":"url"}' \
"https://api.allscreenshots.com/v1/screenshots" | jq
### Dark mode
Add "darkMode": true to any request body above.
### PDF export
Add "format": "pdf" to any request body above.
### Viewport-only screenshot
Set "fullPage": false to capture only the visible viewport.
## Parameter Reference
- fullPage: true captures the entire scrollable page
- blockAds: true removes ads and trackers
- blockCookieBanners: true hides cookie consent popups
- stealth: true uses anti-detection mode for bot-protected sites
- darkMode: true injects prefers-color-scheme: dark
- format: "pdf" returns a PDF instead of PNG
- responseType: controls what the API returns
- "binary" (default) – raw image bytes
- "base64" – JSON with base64-encoded image data
- "url" – JSON with a CDN link to the stored image
## Response
When responseType is "url" (recommended for OpenClaw):
{ "storageUrl": "https://storage.allscreenshots.com/abc.png" }
Send the storageUrl back to the user as an image.
When responseType is "binary" (default):
Raw image bytes. Pipe to a file with curl -o output.png
When responseType is "base64":
{ "data": "iVBORw0KGgo..." }
Base64 payload, useful for embedding in HTML or emails.A few things to note about this skill:
description is written as a trigger phrase — it describes the task the way you'd ask for it in chat, so OpenClaw knows when to activate it.metadata field declares dependencies (curl and jq must be installed) and the required environment variable. OpenClaw checks these before running the skill.curl commands. OpenClaw's agent reads these instructions and executes the commands directly — no wrapper code needed.Add your Allscreenshots API key to the OpenClaw workspace environment:
echo 'ALLSCREENSHOTS_API_KEY=your_api_key_here' >> ~/.openclaw/workspace/.envVerify it's set:
grep ALLSCREENSHOTS ~/.openclaw/workspace/.envRestart OpenClaw (or wait for hot-reload) and send a message on any connected platform:
Take a screenshot of https://news.ycombinator.com
OpenClaw will:
allscreenshots skill via the descriptioncurl command with your URLjqscreenshotUrl as an image in your chatSince the skill includes separate operations for each capture type, OpenClaw picks the right one based on your request:
| You say | OpenClaw does |
|---|---|
| "Screenshot example.com" | Desktop full-page capture at 1280x800 |
| "Screenshot example.com on mobile" | Mobile capture at 375x812, 3x scale |
| "Capture example.com in dark mode" | Adds darkMode: true to the request |
| "Save example.com as a PDF" | Sets format: "pdf" for PDF output |
| "Screenshot just the visible area" | Sets fullPage: false for viewport-only |
| "Capture that Cloudflare-protected site" | stealth: true bypasses bot detection |
Every request includes blockAds: true, blockCookieBanners: true, and stealth: true by default — clean screenshots of any site without cookie popups, ads, or bot-detection walls getting in the way.
You can ask OpenClaw to process multiple URLs in one go:
Screenshot these competitor sites:
OpenClaw will iterate through the list and return each screenshot.
OpenClaw supports cron scheduling for recurring tasks. Set up daily homepage monitoring:
Every morning at 9am, take a screenshot of https://mysite.com and send it here
OpenClaw creates a cron job that triggers the screenshot skill on schedule and delivers the result to your chat. This is useful for:
With the Allscreenshots API powering your OpenClaw agent, you get reliable cloud-rendered screenshots without managing any browser infrastructure locally. The API handles full-page rendering, ad blocking, dark mode, mobile viewports, and more — all triggered by a chat message.
For more details and code examples, see the OpenClaw integration page. Check out the API documentation for the full list of screenshot options.