New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Browser Automation

by autopus-ai in autopus-ai/autopus-adk

터미널 환경 자동 감지 브라우저 자동화 스킬 — AI 에이전트가 직접 웹 페이지를 조작하고 검증. An agent skill from autopus-ai/autopus-adk.

MITAuto-check passedProductivity & Automation

Install Browser Automation

skills CLI
$ npx skills add autopus-ai/autopus-adk --skill browser-automation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install autopus-ai/autopus-adk browser-automation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/autopus-ai/autopus-adk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.omp/skills/browser-automation .claude/skills/browser-automation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
browser-automation
GitHub stars
110
Token cost
~2.1k tokens
SKILL.md length
500 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

터미널 환경 자동 감지 브라우저 자동화 스킬 — AI 에이전트가 직접 웹 페이지를 조작하고 검증. An agent skill from autopus-ai/autopus-adk.

  • Works in 5 steps: Detect Backend — 터미널 감지 → Open — 페이지 열기 → Snapshot — 접근성 트리 + 참조 획득 → …
  • Tasks that involve Browser automation
  • SKILL.md covers 도구 선택, 백엔드 자동 감지, 사전 조건 and 핵심 워크플로우: Snapshot-Act-Verify, plus 5 more sections
  • Calls npm; reaches autopus.co

What it does

Browser Automation is an agent skill from autopus-ai/autopus-adk. 터미널 환경 자동 감지 브라우저 자동화 스킬 — AI 에이전트가 직접 웹 페이지를 조작하고 검증

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: omp

It sits in Productivity & Automation, covering Browser automation. The repository describes itself as: Autopus-ADK is of the agents, by the agents. for the agents. Multi-model orchestration (consensus/pipeline/debate/fastest). Architecture-as-Code, Lore decision tracking… The licence is MIT.

When your agent uses it

  • Tasks that involve Browser automation

Example prompts

  • “/browser-automation”

Requirements

  • Node.js
  • Compatibility (from SKILL.md): omp

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Detect Backend — 터미널 감지
  2. Open — 페이지 열기
  3. Snapshot — 접근성 트리 + 참조 획득
  4. Act — 요소 상호작용
  5. Verify — 상태 확인 + 스크린샷

What it can do on your machine

Read from SKILL.md and the folder at commit a930e5f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • autopus.co

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    omp

    From compatibility in the SKILL.md frontmatter.

Context cost

Browser Automation loads about 2.1k tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 500 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~18
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from autopus-ai/autopus-adk at commit a930e5f, republished under its MIT licence (© autopus-ai). 500 words, ~2,079 tokens.

Download SKILL.mdSave it as .claude/skills/browser-automation/SKILL.md (or your agent's skills folder).
name
browser-automation
description
터미널 환경 자동 감지 브라우저 자동화 스킬 — AI 에이전트가 직접 웹 페이지를 조작하고 검증
compatibility
omp

Browser Automation Skill

터미널 환경을 자동 감지하여 cmux browser 또는 agent-browser CLI를 활용해 AI 에이전트가 직접 웹 페이지를 조작하고 검증하는 스킬입니다.

도구 선택

도구용도선택 기준
cmux browsercmux 환경 네이티브 조작cmux 터미널에서 자동 선택 (최우선)
agent-browser에이전트 직접 조작tmux/plain 환경 폴백
PlaywrightE2E 테스트 스위트반복 실행, CI/CD, 회귀 테스트

백엔드는 auto terminal detect 결과에 따라 자동 선택됩니다. 수동 지정하지 마세요.

백엔드 자동 감지

브라우저 백엔드는 현재 터미널 환경에 따라 자동 선택됩니다.

감지 방법:

bash
auto terminal detect
터미널백엔드명령어 접두사
cmuxcmux browsercmux browser <subcommand>
tmux / plainagent-browseragent-browser <subcommand>

IMPORTANT: 스킬 실행 시 반드시 auto terminal detect를 먼저 호출하여 백엔드를 결정해야 합니다. agent-browser를 하드코딩하지 마세요.

명령어 매핑
동작cmux browseragent-browser
페이지 열기cmux browser open <url>agent-browser open <url>
스냅샷cmux browser --surface <ref> snapshotagent-browser snapshot
클릭cmux browser --surface <ref> click --selector <sel>agent-browser click <ref>
입력cmux browser --surface <ref> fill --selector <sel> --text <text>agent-browser fill <ref> <text>
스크린샷cmux browser --surface <ref> screenshot --out <path>agent-browser screenshot <path>
대기cmux browser --surface <ref> wait --text <text>agent-browser wait --text <text>
URL 확인cmux browser --surface <ref> get urlagent-browser get url
텍스트 확인cmux browser --surface <ref> get text --selector <sel>agent-browser get text <ref>
표시 여부cmux browser --surface <ref> is visible --selector <sel>agent-browser is visible <ref>

cmux 고유 기능:

  • --surface <ref>: cmux browser는 surface 핸들로 세션을 관리합니다. open 명령이 반환하는 surface ref를 후속 명령에 사용합니다.
  • --snapshot-after: 클릭/입력 후 자동 스냅샷 (cmux browser --surface <ref> click --selector <sel> --snapshot-after)
  • --interactive: 인터랙티브 스냅샷 모드 (cmux browser --surface <ref> snapshot --interactive)

사전 조건

bash
# 터미널 감지
auto terminal detect

# cmux 환경 (자동 감지)
cmux --version

# agent-browser 환경 (폴백)
agent-browser --version
# 미설치 시
npm install -g agent-browser
agent-browser install

핵심 워크플로우: Snapshot-Act-Verify

AI 에이전트가 브라우저를 조작하는 단계별 루프:

Step 0: Detect Backend — 터미널 감지
bash
BACKEND=$(auto terminal detect)
# "cmux" → cmux browser 사용
# "tmux" or "plain" → agent-browser 사용
Step 1: Open — 페이지 열기

cmux:

bash
cmux browser open <url>
# Returns: surface reference (e.g., "surface:1")

agent-browser:

bash
agent-browser open <url>
Show full SKILL.md (215 more words)Show less
Step 2: Snapshot — 접근성 트리 + 참조 획득

cmux:

bash
cmux browser --surface <ref> snapshot

agent-browser:

bash
agent-browser snapshot

snapshot은 페이지의 접근성 트리를 반환하며, 각 요소에 @e1, @e2 등의 참조를 할당한다. AI 에이전트는 이 참조를 사용하여 요소를 조작한다.

snapshot 출력 예시:

- @e1 heading "AI Settings"
- @e2 button "Provider Mode"
- @e3 switch "Auto Fallback" [checked]
- @e4 checkbox "Anthropic" [checked]
- @e5 checkbox "OpenAI" [checked]
- @e6 checkbox "Google" [unchecked]
- @e7 button "Save"
Step 3: Act — 요소 상호작용

cmux:

bash
cmux browser --surface <ref> click --selector "@e3"
cmux browser --surface <ref> fill --selector "@e4" --text "text"
cmux browser --surface <ref> press Enter

agent-browser:

bash
agent-browser click @e3
agent-browser fill @e4 "text"
agent-browser press Enter
Step 4: Verify — 상태 확인 + 스크린샷

cmux:

bash
cmux browser --surface <ref> snapshot
cmux browser --surface <ref> screenshot --out /tmp/verify.png
cmux browser --surface <ref> is visible --selector "@e3"
cmux browser --surface <ref> is checked --selector "@e3"
cmux browser --surface <ref> get text --selector "@e1"

agent-browser:

bash
agent-browser snapshot
agent-browser screenshot /tmp/verify.png
agent-browser is visible @e3
agent-browser is checked @e3
agent-browser get text @e1

주요 명령어 레퍼런스

네비게이션

cmux:

bash
cmux browser open <url>
cmux browser --surface <ref> get url
cmux browser --surface <ref> get title
cmux browser --surface <ref> wait --load-state complete
cmux browser --surface <ref> wait --text "Welcome"

agent-browser:

bash
agent-browser open <url>
agent-browser get url
agent-browser get title
agent-browser wait --load networkidle
agent-browser wait --text "Welcome"
상호작용

cmux:

bash
cmux browser --surface <ref> click --selector <sel>
cmux browser --surface <ref> fill --selector <sel> --text <text>
cmux browser --surface <ref> hover --selector <sel>
cmux browser --surface <ref> scroll down 500
cmux browser --surface <ref> press Enter

agent-browser:

bash
agent-browser click <ref>
agent-browser fill <ref> <text>
agent-browser type <ref> <text>
agent-browser hover <ref>
agent-browser scroll down 500
agent-browser press Enter
의미론적 로케이터 (snapshot 없이 직접 찾기)

cmux:

bash
cmux browser --surface <ref> find role button --name "Save"
cmux browser --surface <ref> find text "Sign In"
cmux browser --surface <ref> find label "Email"

agent-browser:

bash
agent-browser find role button click --name "Save"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "test@test.com"
상태 확인

cmux:

bash
cmux browser --surface <ref> is visible --selector <sel>
cmux browser --surface <ref> is enabled --selector <sel>
cmux browser --surface <ref> is checked --selector <sel>
cmux browser --surface <ref> get text --selector <sel>
cmux browser --surface <ref> get html --selector <sel>

agent-browser:

bash
agent-browser is visible <ref>
agent-browser is enabled <ref>
agent-browser is checked <ref>
agent-browser get text <ref>
agent-browser get html <ref>
뷰포트 & 디바이스

cmux:

bash
cmux browser --surface <ref> viewport 1280 800

agent-browser:

bash
agent-browser set viewport 1280 800
agent-browser set device "iPhone 14"
agent-browser set media dark
쿠키 & 인증

cmux:

bash
cmux browser --surface <ref> cookies get
cmux browser --surface <ref> cookies set --name <name> --value <value>
cmux browser --surface <ref> storage local get

agent-browser:

bash
agent-browser cookies
agent-browser cookies set <name> <value>
agent-browser storage local

실행 모드

백엔드기본 모드설명
cmux browser내장 서피스cmux 터미널 내 브라우저 패널로 표시. --headed 불필요
agent-browser (기본)Headless--headed 추가 시 브라우저 창 표시
bash
# cmux — 항상 터미널 내 브라우저 패널로 표시
cmux browser open https://autopus.co

# agent-browser — 헤드리스 (기본)
agent-browser open https://autopus.co
# agent-browser — 브라우저 창 표시
agent-browser open https://autopus.co --headed

운영환경 검증 패턴

아래 예시는 cmux 백엔드 기준입니다. agent-browser 사용 시 cmux browser --surface <ref> 대신 agent-browser를 사용하세요.

패턴 1: UI 컴포넌트 존재 확인
bash
SURFACE=$(cmux browser open https://example.com/settings/ai)
cmux browser --surface $SURFACE snapshot
# → @e3 switch "Auto Fallback" 이 존재하면 렌더링 성공
cmux browser --surface $SURFACE screenshot --out /tmp/ai-settings.png
패턴 2: 토글 동작 검증
bash
cmux browser --surface $SURFACE snapshot
cmux browser --surface $SURFACE click --selector "@e3" --snapshot-after
패턴 3: 인증 후 테스트
bash
SURFACE=$(cmux browser open https://example.com/login)
cmux browser --surface $SURFACE snapshot
cmux browser --surface $SURFACE fill --selector "@e2" --text "user@example.com"
cmux browser --surface $SURFACE fill --selector "@e3" --text "password"
cmux browser --surface $SURFACE click --selector "@e4"
cmux browser --surface $SURFACE wait --load-state complete
cmux browser --surface $SURFACE goto https://example.com/settings/ai
cmux browser --surface $SURFACE snapshot

판정 기준

판정기준
PASS기대 요소가 snapshot에 존재하고 올바른 상태
WARN요소는 존재하나 상태가 예상과 다름
FAIL기대 요소가 snapshot에 없거나 에러 발생

주의사항

  • 백엔드는 auto terminal detect로 자동 선택됨 — 수동 지정 금지
  • cmux 환경에서는 cmux browser가 최우선 — agent-browser를 사용하면 세션이 분리됨
  • cmux --surface 핸들은 open 명령이 반환 — 후속 명령에 반드시 전달
  • snapshot은 접근성 트리만 반환 — CSS 스타일은 포함 안 됨 (시각 확인은 screenshot 사용)
  • 운영환경 테스트 시 쓰기 작업(삭제, 설정 변경)은 신중하게 — 되돌릴 수 없을 수 있음

© autopus-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .omp/skills/browser-automation of autopus-ai/autopus-adk.

Open the folder on GitHubat commit a930e5f

Compare with similar skills

Browser Automation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Browser Automation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Browser Automation this skillautopus-ai/autopus-adk110—~2.1kAutomated safety check: PassMIT
Agent Browserquran/quran.com-frontend-next1.9k40 repos~3.3kAutomated safety check: PassNone
Dev-Browser CLI AutomationSawyerHood/dev-browser6.7k1 repos~455Automated safety check: PassMIT
Browser Automationopenclaw/openclaw392k—~2.9kAutomated safety check: PassMIT
Camoufox CLIBin-Huang/camoufox-cli3501 repos~4.5kAutomated safety check: PassMIT
BrowserVibiumDev/vibium2.9k—~4.8kAutomated safety check: PassApache-2.0

Similar skills

  • Agent Browser

    quran/quran.com-frontend-next

    Automates browser interactions for web testing, form filling, screenshots, and data extraction.

    1.9k GitHub starsUsed in 40 repos~3.3k tokens
    Productivity & AutomationAuto-check passed

  • Dev-Browser CLI Automation

    SawyerHood/dev-browser

    Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web…

    6.7k GitHub starsUsed in 1 repo~455 tokens
    Productivity & AutomationAuto-check passed

  • Browser Automation

    openclaw/openclaw

    A skill your agent uses when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.

    392k GitHub stars~2.9k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Camoufox CLI

    Bin-Huang/camoufox-cli

    Anti-detect browser automation CLI & Skills for AI agents. An agent skill from Bin-Huang/camoufox-cli.

    350 GitHub starsUsed in 1 repo~4.5k tokens
    Productivity & AutomationAuto-check passed

  • Browser

    VibiumDev/vibium

    Automate browsers with the Vibium CLI. An agent skill from VibiumDev/vibium.

    2.9k GitHub stars~4.8k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Use Agent Browser For Airi

    moeru-ai/airi

    Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts.

    50k GitHub stars~1.1k tokensUpdated today
    Productivity & AutomationAuto-check passed

More from autopus-ai/autopus-adk

All 11 skills in this repo

  • Auto Idea

    autopus-ai/autopus-adk

    아이디어 브레인스토밍 — 멀티 프로바이더 토론과 ICE 평가로 아이디어를 정리합니다. An agent skill from autopus-ai/autopus-adk.

    110 GitHub stars~2.4k tokensUpdated today
    Auto-check passed

  • Auto QA

    autopus-ai/autopus-adk

    QAMESH project QA mesh — plan, run, report, and publish deterministic QA evidence

    110 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Auto Setup

    autopus-ai/autopus-adk

    프로젝트 컨텍스트 생성 — 코드베이스를 분석하고 ARCHITECTURE.md 및 .autopus/project 문서를 생성합니다

    110 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Auto Sync

    autopus-ai/autopus-adk

    문서 동기화 — 구현 이후 SPEC, CHANGELOG, 문서를 반영합니다. An agent skill from autopus-ai/autopus-adk.

    110 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Ax Annotation

    autopus-ai/autopus-adk

    @AX code annotation workflow skill for agent-driven tag application

    110 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Codebase Design

    autopus-ai/autopus-adk

    작은 인터페이스 뒤에 많은 동작을 숨기는 deep module을 설계하기 위한 공용 어휘(module, interface, seam, adapter, depth)와 원칙

    110 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Categories

Questions about Browser Automation

What does Browser Automation do?

터미널 환경 자동 감지 브라우저 자동화 스킬 — AI 에이전트가 직접 웹 페이지를 조작하고 검증. An agent skill from autopus-ai/autopus-adk. Browser Automation is an agent skill from autopus-ai/autopus-adk.

When should I use Browser Automation?

Browser Automation fits situations like: tasks that involve Browser automation.

How do I install Browser Automation in Claude Code?

Run `npx skills add autopus-ai/autopus-adk --skill browser-automation -a claude-code`. Or copy the skill folder (.omp/skills/browser-automation in autopus-ai/autopus-adk) into .claude/skills/browser-automation in your project. Claude Code loads it when a task matches its description.

How do I install Browser Automation in Codex?

Run `npx skills add autopus-ai/autopus-adk --skill browser-automation -a codex`. Or copy the skill folder (.omp/skills/browser-automation in autopus-ai/autopus-adk) into .agents/skills/browser-automation in your project. Codex loads it when a task matches its description.

Can I use Browser Automation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autopus-ai/autopus-adk --skill browser-automation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/browser-automation, .gemini/skills/browser-automation, .github/skills/browser-automation and .opencode/skills/browser-automation in your project.

What does Browser Automation need to run?

Going by SKILL.md and its folder, Browser Automation needs the command-line tools its instructions call (npm). Our summary lists: Node.js. Compatibility (from SKILL.md): omp.

Does Browser Automation access the network?

SKILL.md names 1 domain. In commands or code: autopus.co; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Browser Automation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Browser Automation use?

Browser Automation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Browser Automation use?

About 2.1k tokens (SKILL.md is roughly 8.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Browser Automation?

Skills that share tags, products or a category with Browser Automation: Agent Browser (quran/quran.com-frontend-next, 1.9k stars), Dev-Browser CLI Automation (SawyerHood/dev-browser, 6.7k stars), Browser Automation (openclaw/openclaw, 392k stars) and Camoufox CLI (Bin-Huang/camoufox-cli, 350 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Browser Automation?

autopus-ai (a GitHub organization) maintains it in autopus-ai/autopus-adk, which has 110 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 10, 2026.

Source: autopus-ai/autopus-adk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.