Scrapeless Scraping Browser SkillSAFE

🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: scrapeless-scraping-browser
description: Cloud browser automation CLI for AI agents powered by Scrapeless. Use when the user needs to interact with websites using cloud browsers, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task with residential proxies and anti-detection features. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "use a proxy", "bypass detection", or any task requiring cloud browser automation.
allowed-tools: Bash(npx scrapeless-scraping-browser-skills scrapeless-scraping-browser:*), Bash(scrapeless-scraping-browser:*)
---

# Cloud Browser Automation with scrapeless-browser

## Important: Session Management with --session-id

**All browser operation commands support the `--session-id` parameter to specify which Scrapeless session to use.**

### Recommended Workflow

```bash
# Step 1: Create a session and save the session ID
SESSION_ID=$(scrapeless-scraping-browser new-session --name "workflow" --ttl 1800 --json | jq -r '.taskId')

# Step 2: Use the session ID for all operations
scrapeless-scraping-browser --session-id $SESSION_ID open https://example.com
scrapeless-scraping-browser --session-id $SESSION_ID snapshot -i
scrapeless-scraping-browser --session-id $SESSION_ID click @e1

# Step 3: Close when done
scrapeless-scraping-browser --session-id $SESSION_ID close
```

### Automatic Session Management

If you don't specify `--session-id`:
1. The CLI will query for running sessions
2. If a running session exists, it will use the latest one
3. If no running session exists, it will create a new one automatically

**For production workflows, always use `--session-id` to ensure consistency.**

## Authentication Setup

Before using scrapeless-browser, you MUST set up authentication:

```bash
# Method 1: Config file (recommended, persistent)
scrapeless-scraping-browser config set apiKey your_api_token_here

# Method 2: Environment variable
export SCRAPELESS_API_KEY=your_api_token_here

# Verify it's set
scrapeless-scraping-browser config get apiKey
```

Get your API token from https://app.scrapeless.com

## Session Management Behavior

The CLI manages Scrapeless sessions with the following behavior:

- **Session Creation**: First command creates a new Scrapeless session
- **Session Persistence**: Sessions remain active only while connection is maintained
- **Session Termination**: Sessions automatically terminate when connection closes
- **Reconnection Limitation**: Cannot reconnect to terminated sessions

**Important**: For multi-step workflows, consider using the TypeScript API to maintain persistent connections.

## Core Workflow

Every browser automation follows this pattern:

1. **Create Session**: Create a session and save the session ID
2. **Navigate**: Use `--session-id` to navigate to URL
3. **Snapshot**: Get element refs with `--session-id`
4. **Interact**: Use refs to click, fill, select with `--session-id`
5. **Re-snapshot**: After navigation or DOM changes, get fresh refs

```bash
# Set API token first
scrapeless-scraping-browser config set apiKey your_token

# Create session
SESSION_ID=$(scrapeless-scraping-browser new-session --name "form-fill" --ttl 600 --json | jq -r '.taskId')

# Start automation with session ID
scrapeless-scraping-browser --session-id $SESSION_ID open https://example.com/form
scrapeless-scraping-browser --session-id $SESSION_ID snapshot -i
# Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"

scrapeless-scraping-browser --session-id $SESSION_ID fill @e1 "[email protected]"
scrapeless-scraping-browser --session-id $SESSION_ID fill @e2 "password123"
scrapeless-scraping-browser --session-id $SESSION_ID click @e3
scrapeless-scraping-browser --session-id $SESSION_ID wait --load networkidle
scrapeless-scraping-browser --session-id $SESSION_ID snapshot -i  # Check result
```

## Command Chaining

Commands can be chained with `&&` in a single shell invocation:

```bash
# Chain open + wait + snapshot
scrapeless-scraping-browser open https://example.com && scrapeless-scraping-browser wait --load networkidle && scrapeless-scraping-browser snapshot -i

# Chain multiple interactions
scrapeless-scraping-browser fill @e1 "[email protected]" && scrapeless-scraping-browser fill @e2 "password123" && scrapeless-scraping-browser click @e3
```

**When to chain:** Use `&&` when you don't need to read intermediate output. Run commands separately when you need to parse output first (e.g., snapshot to discover refs, then interact).

## Essential Commands

**Note**: All commands below support the optional `--session-id <id>` parameter.

```bash
# Navigation & Session
scrapeless-scraping-browser new-session [options]              # Create new browser session
scrapeless-scraping-browser [--session-id <id>] open <url>      # Navigate to URL
scrapeless-scraping-browser [--session-id <id>] close           # Close browser session
scrapeless-scraping-browser sessions                           # List running sessions
scrapeless-scraping-browser stop <taskId>                      # Stop specific session
scrapeless-scraping-browser stop-all                           # Stop all sessions
```

### Session Creation with Advanced Options

The `new-session` command supports extensive customization options:

```bash
# Basic session creation
scrapeless-scraping-browser new-session --name "my-session" --ttl 1800

# Session with proxy settings
scrapeless-scraping-browser new-session \
  --name "proxy-session" \
  --proxy-country US \
  --proxy-state CA \
  --proxy-city "Los Angeles" \
  --ttl 3600

# Session with custom browser configuration
scrapeless-scraping-browser new-session \
  --name "mobile-session" \
  --platform iOS \
  --screen-width 375 \
  --screen-height 812 \
  --user-agent "Mozilla/5.0 (iPhone; CPU iPhone OS 15_0 like Mac OS X)" \
 

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (1)

<key>k5Ey9KFlkqpj+SDkUw+5ED9lTA3En/qUi0zdrydUCH3kMWTE3Eh65NXnFCaxlY2omY2JHnlEoK7Li7oOEvM7eG5VPdcO/sFlMfoCRdnLYdepJ+uLzYwOWR8W4yQVve/clxVFTVRL4DFleKInGdpAxIbHZT2yi4ADAMENls1N1XSLojRuqXePXDeAT/4Mv4TTx0s

Gates applied: no_behavioural_pass.