Web Search Skill — Development skill for Claude Code
Web search (Brave) and page reading (defuddle) for coding agents, through a real Chrome over CDP.
How to install Web Search Skill
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open alexwkleung/web-search-skill and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Web Search Skill does
Web search (Brave) and page reading (defuddle) for coding agents, through a real Chrome over CDP.
Alternatives in Development
- Chrome Devtools MCP — Chrome DevTools for coding agents 29504 108 1 31.7k ★
- Web Access — 给 Claude Code 装上完整联网能力的 skill:三层通道调度 + 浏览器 CDP + 并行分治 3140 4 1 3.3k ★
- Boss Zhipin Scraper — Boss直聘爬虫 / BOSS直聘职位数据抓取工具,基于 Chrome CDP 协议复用真实登录态,绕过字体反爬,输出明文薪资 JSON/CSV + 薪资技能分析 1.5k ★
README
web-search-skill
A web search and page-reading skill for coding agents. It drives a real Chrome over the DevTools protocol instead of a search API: there are no keys, and nothing to self-host.
node web.mjs search "vitest fake timers"
node web.mjs read https://vitest.dev/guide/mocking
Searches go through Brave, which links results directly where Google and Bing route every link through a tracking redirect. The browser runs minimized on a profile of its own, which is what keeps bot checks rare. When a check does appear, the window comes up for you to solve it once, and the same search then finishes. `read` loads the page in that browser and turns it into markdown with [defuddle](https://github.com/kepano/defuddle).
macOS first. Linux should work, but it's untested, and the Chrome window is visible there. Windows isn't supported yet.
Install
Clone it into a folder named `web-search` in a directory your agent loads skills from:
# pi and OpenCode both load ~/.agents/skills/
git clone https://github.com/alexwkleung/web-search-skill ~/.agents/skills/web-search
# Claude Code (OpenCode reads this one too)
git clone https://github.com/alexwkleung/web-search-skill ~/.claude/skills/web-search
Then run `npm install` in it once, which `read` needs. `search` has no dependencies. Requires Node 22 or newer.
It's most useful in agents with no web search of their own, which is most local-model setups. Where the agent has a built-in search tool (Claude Code does), the agent will usually use that instead, and this skill is still there for pages that block plain fetching, or when you ask for it.
See [`SKILL.md`](SKILL.md) for what the agent reads.
Status and bugs
This is new, and so far it's been tested on one machine: macOS with Chrome. It drives a real browser and reads a live search page, so it can break when Chrome, macOS or Brave change. If something doesn't work, [open an issue](https://github.com/alexwkleung/web-search-skill/issues) and
Related Skills
/chrome-cdp — Chrome Browser Automation
Control the user's live Chrome browser via Chrome DevTools Protocol. Connects to real tabs with existing cooki
Claude Skill Palmifer
Drive your real, logged-in Chrome from an agent CLI over raw CDP — zero deps, no extension, human-paced by def
Brave Search
Web search via the Brave: title, URL, snippet per result. Works headless, can serve as backup or when searchin
Browser Extension Connector
Agent Skill: build a Chrome MV3 connector for a web service with no public API: a MAIN-world tap on the page's
Forge Dash
Abre painel executor em localhost:4712 (Chrome/Arc/Edge/Brave)
Article Sweeper
Agent skill: summarize open article tabs in Thorium, Chromium, Chrome, Brave, Edge and Firefox, append to a da
Related Agents
Visual Tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structu
LinkedIn Operator
Executes LinkedIn writes that have no API, through a logged-in browser MCP (Claude in Chrome or Playwright): p
Browser Scout Sonnet
Default browser tier. Read-only work in the user's real Chrome — open a ticket, a chat channel, a dashboard or