본문으로 건너뛰기
cccskills
무료GitHub에 공개

browser-automation-notte

Browser automation - control browser sessions, scrape pages, and run AI agents

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills

실행 점수 미검증

설치 방법 보기

포함된 파일(2)

  • SKILL.md9.7 KB
  • skill.meta.json303 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Notte - Browser Automation API

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"

Control browser sessions, scrape web pages, and run autonomous AI agents.

Capabilities

  • Take Screenshot: Take a screenshot of the current page
  • Get Session: Get session status and details (free)
  • Stop Session: Stop and clean up a browser session (free)
  • Get Session Cookies: Get all cookies from the browser session (free)
  • Get Network Logs: Get network request/response logs from the session (free)
  • Get Agent Status: Get agent execution status and results (free)
  • Observe Page: Observe the current page state and get available actions
  • Stop Agent: Stop a running agent (free)
  • Scrape Webpage: Scrape content from a URL without managing sessions
  • Execute Page Action: Execute an action on the page (click, type, navigate, etc
  • Set Session Cookies: Set cookies in the browser session
  • Start Session: Start a new browser session
  • Scrape from HTML: Extract structured content from raw HTML without using a browser
  • Start Agent: Start an AI agent to autonomously complete a browser task
  • Scrape Page: Scrape content from the current page in the session

Usage

Take Screenshot

Take a screenshot of the current page.

Parameters:

  • full_page (boolean) - Capture full page
  • session_id* (string)
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":{}}'

Get Session (free)

Get session status and details.

Parameters:

  • session_id* (string)
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 Session (free)

Stop and clean up a browser session.

Parameters:

  • session_id* (string) - Session ID
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"}'

Get Session Cookies (free)

Get all cookies from the browser session.

Parameters:

  • session_id* (string)
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}/cookies"}'

Get Network Logs (free)

Get network request/response logs from the session.

Parameters:

  • session_id* (string)
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}/network/logs","query":{"session_id":"example"}}'

Get Agent Status (free)

Get agent execution status and results.

Parameters:

  • agent_id* (string)
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":"/agents/{agent_id}"}'

Observe Page

Observe the current page state and get available actions.

Parameters:

  • max_nb_actions (number) - Maximum actions to return (default: 100)
  • min_nb_actions (number) - Minimum actions to return
  • instruction (string) - Optional instruction to filter actions
  • session_id* (string)
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/observe","body":{"instruction":"Find the search box"}}'

Stop Agent (free)

Stop a running agent.

Parameters:

  • session_id* (string) - Session ID the agent is running on
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":"/agents/{agent_id}/stop"}'

Scrape Webpage

Scrape content from a URL without managing sessions.

Parameters:

  • url* (string) - URL to scrape
  • schema (object) - Structured extraction schema
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":"/scrape","body":{"url":"https://example.com"}}'

Execute Page Action

Execute an action on the page (click, type, navigate, etc.).

Parameters:

  • type* (string) - Action type: goto, click, type, scroll, select, hover, wait, screenshot
  • url (string) - URL for goto action
  • ref (string) - Element reference for click/type/select actions
  • text (string) - Text for type action
  • value (string) - Value for select action
  • direction (string) - Scroll direction: up/down
  • amount (number) - Scroll amount in pixels
  • timeout (number) - Wait timeout in ms
  • session_id* (string)
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":{"instruction":"Click the search button"}}'

Set Session Cookies

Set cookies in the browser session.

Parameters:

  • cookies* (array) - Array of cookie objects
  • session_id* (string)
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}/cookies"}'

Start Session

Start a new browser session. Configure browser type, proxies, viewport, and session timeout.

Parameters:

  • headless (boolean) - Run in headless mode (default: true)
  • browser_type (string) - Browser type: chromium, chrome, firefox
  • proxies (boolean) - Enable proxy rotation
  • solve_captchas (boolean) - Auto-solve CAPTCHAs
  • idle_timeout_minutes (integer) - Idle timeout (default: 3)
  • max_duration_minutes (integer) - Max duration (default: 15)
  • viewport_width (integer)
  • viewport_height (integer)
  • user_agent (string)
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"}'
  "url": "https://example.com",
  "timeout_minutes": 5
}'

Scrape from HTML

Extract structured content from raw HTML without using a browser

Parameters:

  • frames* (array) - Array of HTML frames to parse
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":"/scrape_from_html","body":{"html":"<html><body>Hello</body></html>"}}'

Start Agent

Start an AI agent to autonomously complete a browser task.

Parameters:

  • task* (string) - Task for the AI agent to perform
  • session_id* (string) - Session ID to run the agent on
  • url (string) - Starting URL
  • max_steps (number) - Max steps (1-50, default: 20)
  • use_vision (boolean) - Use vision model (default: true)
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":"/agents/start"}'
  "task": "Search for AI news on Google and summarize the top results",
  "url": "https://google.com"
}'

Scrape Page

Scrape content from the current page in the session.

Parameters:

  • selector (string) - Playwright selector to scope the scrape
  • scrape_links (boolean) - Scrape links (default: true)
  • scrape_images (boolean) - Scrape images (default: false)
  • only_main_content (boolean) - Only main content, exclude nav/footer (default: true)
  • response_format (object) - Pydantic model or JSON Schema for structured extraction
  • instructions (string) - Additional extraction instructions
  • session_id* (string)
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/scrape","body":{}}'

Use Cases

  1. Web Scraping: Extract structured data from any webpage
  2. Browser Automation: Automate complex browser workflows
  3. Testing: Run automated browser tests
  4. AI Agents: Deploy autonomous agents for web tasks
  5. Monitoring: Track website changes and content

Discover More

For full endpoint details and parameters:

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/search \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"notte API endpoints"}' List all endpoints
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/details \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"notte","path":"/sessions"}'   # Get endpoint details

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

ad-angle-miner

무료

Research supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills1.3천2026년 10월 23일 업데이트

ad-campaign-analyzer

무료

Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills1.3천2026년 10월 23일 업데이트

ad-lead-quality-analyzer

무료

For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills1.3천2026년 10월 23일 업데이트

ad-management-intake

무료

The intake stage of a Meta ad harness. Researches the brand first, states what it assumes, and asks only what it cannot infer and what would change money, claims or legal exposure if guessed wrong — at most four questions a turn, in plain business language. Writes the brand's stable facts (ads/brand.md), the campaign brief, and a log of what was asked vs assumed. Use it when someone wants to run Meta ads and the brand's ad facts are not yet recorded.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills1.3천2026년 10월 23일 업데이트

ad-policy-check

무료

Checks paid ads against the ad platform's rules (Meta, TikTok, Google, LinkedIn and others) and the brand's category rules: the copy, on-image or on-screen text, pictures and people. Rewrites what can be fixed honestly, adds the disclosures that are needed, and flags anything that needs a human or legal review, with one pass, fixed or flag line per ad and platform. Use alone when you already have the ad text or images and know where they will run; otherwise run the playbook for the job (e.g. make-static-ads, make-content, email-lifecycle).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills1.3천2026년 10월 23일 업데이트

ad-to-landing-page-auditor

무료

Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

gooseworks-ai/goose-skills1.3천2026년 10월 23일 업데이트

gooseworks-ai의 스킬 모두 보기

이 스킬의 문제 신고