Website Screenshot Notte Agent Skill

Take screenshots of any website using Notte browser automation. Use when asked to screenshot, capture, or snap a webpage.

1.1k tokens

context cost

SKILL.md, read when the skill is used

files

plus reference files

copies elsewhere

how many repositories repackaged it

1 086

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/gooseworks-ai/goose-skills --skill website-screenshot-notte

What comes with it

303 bytes besides the instruction

skill.meta.json

The instruction itself

11 sections, as written by the author

Website Screenshot

Setup

Read your credentials from ~/.gooseworks/credentials.json:

export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")

If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login

All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"

Take screenshots of any website URL and save them as image files.

Requirements

Orthogonal CLI: npm install -g @orth/cli

Workflow

Take a screenshot of a URL in 4 steps:

Step 1: Start a browser session

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"notte","path":"/sessions/start","body":{"headless":true}}'

Save the session_id from the response.

Step 2: Navigate to the URL

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"notte","path":"/sessions/{session_id}/page/execute","body":{"type":"goto","url":"https://example.com"}}'

Step 3: Take the screenshot

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"notte","path":"/sessions/{session_id}/page/screenshot","body":{}}'

For a full-page screenshot:

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"notte","path":"/sessions/{session_id}/page/screenshot","body":{"full_page":true}}'

Step 4: Stop the session

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"notte","path":"/sessions/{session_id}/stop"}'

Full Example

# 1. Start session
SESSION=$(curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"notte","path":"/sessions/start","body":{"headless":true}}' | python3 -c "import json,sys;d=json.load(sys.stdin);print(json.dumps(d.get('data',d)))" | python3 -c "import sys,json; print(json.load(sys.stdin)['session_id'])")

# 2. Navigate
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"notte","path":"/sessions/$SESSION/page/execute","body":{"type":"goto","url":"https://example.com"}}'

# 3. Screenshot
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"notte","path":"/sessions/$SESSION/page/screenshot","body":{}}'

# 4. Cleanup
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"notte","path":"/sessions/$SESSION/stop"}'

Options

| Parameter | Description |

|-----------|-------------|

| full_page | Set to true to capture the entire scrollable page |

| headless | Set to false to see the browser window (default: true) |

| viewport_width | Custom viewport width in pixels |

| viewport_height | Custom viewport height in pixels |

Tips

Always stop the session when done to free resources
Sessions auto-expire after 3 minutes of idle time
Use -o flag to save the screenshot to a file (required for binary data)
The output file must not already exist (use a unique name or delete first)

Other skills for the same job

different authors, same section of the catalogue

Webapp Testing

by anthropics

vendor ×15

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.

A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.

| 所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、动态页面交互等。触发场景：用户要求搜索信息、查看网页内容、访问需要登录的网站、操作网页界面、抓取社交媒体内容（小红书、微博、推特等）、读取动态渲染页面、以及任何需要真实浏览器环境的网络任务。

2.7k tokens scripts zh

How to use it

Copy the folder

Take gooseworks-ai/website-screenshot-notte from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference npm, npx. Without those the skill loads but fails at the first command.