chrome-devtools
Browser automation via Chrome extension and DevTools MCP. Use when controlling a logged-in Chrome browser, automating workflows, filling forms, extracting data, debugging web apps, reading console logs, or running scheduled browser tasks. Use for browser testing, form automation, data extraction, web scraping, authenticated browsing.
- Installs
- 136
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/oakoss/agent-skills --skill chrome-devtools- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads chrome-devtools automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Chrome DevTools Skill
Control a real Chrome browser with Claude. The Chrome extension runs inside an authenticated browser session, allowing interaction with sites the user is already logged into -- Gmail, Google Docs, Notion, CRMs, and more.
Overview
Two integration paths exist: Claude Code + Chrome Extension (terminal-based browser control via claude --chrome) and Chrome DevTools MCP (26 browser automation tools via Model Context Protocol). Both operate on a real Chrome instance with existing logins, requiring no re-authentication. The Chrome extension also supports workflow shortcuts, scheduled recurring tasks, and multi-tab coordination independently of Claude Code.
Quick Reference
| Integration | Setup | Best For |
|---|---|---|
| Claude Code + Extension | claude --chrome | Terminal-based browser control |
| Chrome DevTools MCP | claude mcp add chrome-devtools --scope user npx chrome-devtools-mcp@latest | Programmatic automation via MCP tools |
| Capability | Tools/Methods |
|---|---|
| Navigation | Navigate URLs, create/close/switch tabs, resize windows |
| Input | Click, type, fill forms, drag, hover, press keys, upload files |
| Extraction | Read page content, DOM state, console logs, network requests |
| Debugging | Screenshots, DOM snapshots, evaluate JavaScript, performance tracing |
| Emulation | Device emulation, viewport resizing |
| Recording | Record browser interactions as GIFs, save workflow shortcuts |
| Scheduling | Workflow shortcuts with daily/weekly/monthly/annual triggers |
| Requirement | Minimum |
|---|---|
| Google Chrome | Latest stable |
| Claude in Chrome Extension | 1.0.36+ |
| Claude Code CLI | 2.0.73+ |
| Claude Plan | Pro, Team, or Enterprise |
| Node.js (DevTools MCP) | 20.19+ |
Not supported: Other Chromium browsers (Brave, Arc, Edge), WSL, headless mode (extension path only; DevTools MCP supports headless), mobile devices.
Common Mistakes
| Mistake | Correct Pattern |
|---|---|
Running browser automation without --chrome flag | Start Claude Code with claude --chrome or enable Chrome by default via /chrome settings |
| Trying to take over existing tabs | Claude opens new tabs for tasks; it does not hijack tabs you already have open |
| Not handling CAPTCHAs and modal dialogs manually | Claude pauses at CAPTCHAs, login prompts, and modals; dismiss them yourself then tell Claude to continue |
| Using ambiguous instructions for form filling | Be specific about field names, values, and order; ambiguous prompts produce inconsistent results |
| Requesting all console logs without filtering | Specify log patterns or error types; requesting everything floods context with noise |
| Enabling Chrome by default without need | Increases context usage since browser tools are always loaded; use --chrome flag only when needed |
Using DevTools MCP without --scope user | Add --scope user to make the MCP server available across all projects |
Delegation
- Automate repetitive browser workflows across sites: Use
Taskagent with Chrome extension to fill forms, extract data, or navigate multi-step flows - Debug frontend issues with console and network inspection: Use
Exploreagent with DevTools MCP to capture console errors, network failures, and DOM state - Plan complex multi-tab data extraction pipelines: Use
Planagent to design the workflow steps before executing browser automation - Record and schedule recurring browser tasks: Use Chrome extension shortcuts with scheduling for daily/weekly automation
References
- Claude Code Chrome integration -- setup, capabilities, and how the extension communicates with Claude Code
- Chrome DevTools MCP tools -- all 26 MCP tools organized by category with configuration options
- Browser automation workflows -- common patterns for testing, data extraction, and content management
- Workflow shortcuts and scheduling -- creating reusable shortcuts and scheduled recurring tasks
- Troubleshooting and best practices -- fixing connection issues, handling dialogs, and security considerations
FAQ
What does the chrome-devtools skill do?
Browser automation via Chrome extension and DevTools MCP. Use when controlling a logged-in Chrome browser, automating workflows, filling forms, extracting data, debugging web apps, reading console logs, or running scheduled browser tasks. Use for browser testing, form automation, data extraction, web scraping, authenticated browsing.
How do I install chrome-devtools?
Run npx skills add https://github.com/oakoss/agent-skills --skill chrome-devtools in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/chrome-devtools/ (personal) or .claude/skills/chrome-devtools/ (project).
Which AI agents can use chrome-devtools?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is chrome-devtools safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains chrome-devtools?
It is published by oakoss in oakoss/agent-skills. It has 136 recorded installs.
More from oakoss/agent-skills
ui-ux-polish
oakoss/agent-skills
Iterative UI/UX polishing workflow for web applications. Use when improving visual polish, refining desktop and mobile UX separately, running iterative enhancement cycles, applying design patterns like glassmorphism or bento grids, or auditing accessibility and WCAG compliance. Use for Stripe-level visual quality, responsive optimization, and design system alignment.
playwright
oakoss/agent-skills
Open the skill to read its SKILL.md instructions.
coolify
oakoss/agent-skills
Coolify self-hosted PaaS for deploying applications, databases, and services via REST API and Git integration. Covers API authentication, deployment triggers, build packs (Nixpacks, Dockerfile, Compose), CI/CD with GitHub Actions webhooks, environment management, and Traefik proxy configuration. Use when deploying apps to Coolify, triggering deployments via API, configuring build packs, setting up GitHub Actions CI/CD pipelines, managing environment variables, or troubleshooting deployment failures.
application-security
oakoss/agent-skills
Application security covering threat modeling (STRIDE), OWASP Top 10 (2025), OWASP API Security Top 10 (2023), secure coding review, authentication/authorization patterns, input validation, encryption, security headers, supply chain security, compliance (GDPR/HIPAA/SOC2/PCI-DSS), and security monitoring. Use when reviewing code for vulnerabilities, implementing auth patterns, securing APIs, configuring security headers, hardening supply chain, preventing injection attacks, or preparing for compliance audits.
find-skills
oakoss/agent-skills
Discovers and installs agent skills from the open ecosystem. Enriches search results with descriptions fetched from skills.sh. Use when a user asks "how do I do X", "find a skill for X", "is there a skill that can...", or wants to extend agent capabilities. Use for skill discovery, skill search, skill install, finding tools.
drizzle-orm
oakoss/agent-skills
Drizzle ORM for type-safe SQL with PostgreSQL, MySQL, and SQLite. Use when defining schemas, writing queries, managing relations, running migrations, or using drizzle-kit. Use for drizzle, orm, schema, query, migration, pgTable, relations, drizzle-kit, drizzle-zod.
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. 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", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。