---
slug: "capture-skills"
source_type: "readme"
source_url: "https://cdn.jsdelivr.net/gh/techulus/capture-skills@main/README.md"
repo: "https://github.com/techulus/capture-skills"
source_file: "README.md"
branch: "main"
---
# Capture Agent Skills

Agent Skills for [Capture](https://capture.page) - screenshots, PDFs, content extraction, browser sessions, and more.

## Installation

```bash
npx skills add techulus/capture-skills
```

## Available Skills

### capture-cli

Capture screenshots, generate PDFs, extract content, fetch metadata, record animated GIFs, and drive stateful browser sessions using the Capture CLI and Sessions API.

**Prerequisites:**
1. Install the [Capture CLI](https://github.com/techulus/capture-go)
2. Set environment variables `CAPTURE_KEY` and `CAPTURE_SECRET`

**Capabilities:**
- Screenshot any website with custom viewport, dark mode, device emulation
- Generate PDFs with custom paper size, orientation, margins
- Extract content as markdown or HTML
- Fetch metadata (title, description, Open Graph data)
- Record animated GIFs
- Create, inspect, act in, and close browser sessions for multi-step browser automation
- Use session actions such as `goto`, `click`, `fill`, `query`, `content`, `screenshot`, and `batch`

**Sessions quick start:**
```bash
capture sessions create --max-ttl-seconds 300 --pretty
capture sessions action sess_123 goto --payload-json '{"url":"https://example.com"}'
capture sessions action sess_123 screenshot -X fullPage=true --pretty
capture sessions close sess_123 --pretty
```

Sessions are billed by duration, so close them as soon as the workflow is done.

## Links

- [Capture](https://capture.page)
- [Documentation](https://docs.capture.page)
- [Capture CLI](https://github.com/techulus/capture-go)