Browser automation skills

4,404 tagged Browser automation, measured the same way as everything else here.

Browse within: agent 145agentic-ai 114cli 106skills 106LLM 105browser-automation 105chromium 84agents 62ai-tools 58agent-infrastructure 54playwright 51claude-code-skills 49agent-orchestration 47openclaw 40

web-scraping

217

yfe404/web-scraper

Skill Claude CodeCodex

This skill activates for web scraping and Actor development. It proactively discovers APIs via traffic interception, recommends optimal strategy (traffic interception/sitemap/API/DOM scraping/hybrid), and implements iteratively. For production, it guides TypeScript Actor creation via Apify CLI.

not rated 90 5mo ago A 57 tokens original MIT

justlovemaki/PrismFlowAgent

Skill Claude CodeCodex

Use when an AI agent needs to automate a real browser through Agent Browser Bridge CLI, including remote Chrome control, page extraction, clicking, typing, navigation, or screenshots.

not rated 88 today A 39 tokens GPL-3.0

chrome-agent

219

sderosiaux/chrome-agent

Skill Claude CodeCodex

Local browser automation with structured, verified outcomes. Use for web navigation, scraping and extraction, form interaction, screenshots and downloads, network or console checks, responsive testing, or page-scoped device emulation.

not rated 88 +1 changed 3d ago A SkillSpector: warn 44 tokens original MIT

zeke/faster-chrome-devtools-skill

Skill Claude CodeCodex

Inspect, debug, and automate Chrome directly through the Chrome DevTools Protocol (CDP). Use this skill whenever a task needs a real web browser: open a URL, navigate pages, take a screenshot of a web page, read the DOM or accessibility tree, click buttons, fill and submit forms, type text, wait for elements, scrape…

not rated 83 +1 1mo ago B 170 tokens

web-access

221

itwanger/PaiCLI-Python

Skill Claude CodeCodex

Use this skill for live web research, webpage fetching, login-state browsing, dynamic pages, social sites, and tasks that need current internet evidence.

not rated 84 +3 1mo ago A 32 tokens original MIT

agent-browser

222

zhu1090093659/CodeConductor

Skill Claude CodeCodex

Browser automation via the agent-browser CLI for navigation, interaction, snapshots, extraction, screenshots, network controls, storage, tabs, frames, and debugging. Use when tasks require automated web UI actions, form filling, scraping, state capture, or repeatable browser workflows.

not rated 80 7mo ago A 56 tokens original Apache-2.0

NatsuFox/ClaudeChrome

Skill Codex

Extract API endpoints from the active ClaudeChrome browser tab and save them as local artifacts. Use when the user asks to find, capture, reverse engineer, document, or generate Python scripts for endpoints used by the current tab, this page, a live website, or a user-specified browser interaction in ClaudeChrome.

not rated 79 10d ago A 70 tokens

tauri-pilot

224

mpiton/tauri-pilot

Skill Claude CodeCodex

Inspect, interact with, and test a running Tauri v2 app via CLI. Communicates over Unix socket using JSON-RPC 2.0. Use when testing UI, automating interactions, or debugging a Tauri app.

not rated 79 +2 8d ago B 52 tokens original MIT

lipas-e2e

225

lipas-liikuntapaikat/lipas

Skill Claude Code

Run end-to-end scenarios against a live LIPAS dev system. Use when verifying a user-visible flow works correctly across DB, Elasticsearch, app-db, and DOM. Covers municipality-user flows (create/update sports facility) and grows from there.

not rated 78 today A SkillSpector: pass 55 tokens original MIT

liyana31811/Codexless

Skill Claude CodeCodex

Diagnose and temporarily repair Codexless Browser compatibility after a Codex, Chrome Skill, or Browser runtime update when Codexless Browser stopped working. Use for current-version Codexless Browser compatibility drift, not ordinary website bugs, general Browser operation, Codexless install/update work, or long-term…

not rated 84 +9 2d ago A SkillSpector: warn 70 tokens original Apache-2.0

web-search

227

ogulcancelik/agent-skills

Skill Claude CodeCodex

Search the internet with Google or DuckDuckGo, inspect results, and extract selected pages as readable Markdown. Use when answers require current web sources, JavaScript-rendered pages, or browser access that can handle bot protection. Prefer dedicated tools such as GitHub CLI for GitHub data and curl for direct files…

not rated 76 +2 4d ago A SkillSpector: pass 68 tokens original MIT

tavily-search

228

framix-team/openclaw-tavily

Skill Claude CodeCodex

Web search, extraction, crawling, mapping, and deep research via Tavily API. Five tools for finding information, extracting content, exploring websites, and generating research reports.

not rated 75 6mo ago A Socket: passSnyk: warn 39 tokens original MIT

duckduckgo-search

229

Abruptive/Ankh.md

Skill Claude CodeCodex

Free web search via DuckDuckGo when Firecrawl is unavailable. No API key needed. Use ddgs CLI or Python library to find URLs, then webextract for content.

not rated 74 5mo ago A 40 tokens original MIT

claude-for-safari

230

SDLLL/claude-for-safari

Skill Claude CodeCodex

Control the user's real Safari browser on macOS through AppleScript, page JavaScript, screenshots, and carefully verified System Events input. Use when an agent needs to inspect or operate the user's existing Safari tabs and login sessions, including reading pages, navigating, clicking, filling non-sensitive forms…

not rated 73 1mo ago A 81 tokens original MIT

web-access

231

eze-is/eze-skills

Skill Claude CodeCodex

A guide for handling internet-based tasks such as searching, fetching pages, logging in, and interacting with websites.

not rated 73 4mo ago A 89 tokens

design-research

232

hamelsmu/design-research

Skill Claude CodeCodex

Conduct comprehensive design research on any website or web application using a team of browser-automation agents. Use when asked to analyze, audit, or document a website's design system, UX patterns, layout, typography, colors, components, accessibility, responsive behavior, and technical implementation.

not rated 72 6mo ago A 59 tokens

playwright-browser

233

91fapiao-cn/playwright-browser-skill

Skill Claude CodeCodex

A browser-automation skill for controlling web pages, including opening sites, clicking elements, filling forms, reading text, taking screenshots, and monitoring page behavior. The instructions are written in Chinese and describe 101 browser tools.

not rated 69 +1 6mo ago A 35 tokens original MIT

lwjjike/JSReverser-Strong-MCP

Skill Codex

A guide for investigating how web-page JavaScript works when its important requests or parameters are difficult to understand.

not rated 68 5mo ago A 60 tokens original Apache-2.0

site-audit

235

brennhill/Kaboom-Browser-AI-Devtools-MCP

Skill Claude CodeCodex

Use when user asks to audit a website, review all pages, check for broken links, capture full site state, or do a comprehensive product review.

not rated 65 2d ago A 34 tokens AGPL-3.0

windows-harness

236

browser-use/windows-harness

Skill Codex

Control a whole Windows desktop from one persistent Python session with foreground-first input (focus holding, SendInput with pen/message fallbacks), background screenshots, UI Automation, Browser Harness, clipboard paste, PowerShell, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app…

not rated 65 +3 12d ago A SkillSpector: pass 66 tokens original MIT

cheliped-browser

238

tykimos/cheliped-skills

Skill Claude CodeCodex

Agent Browser Runtime for browsing, observing, and interacting with web pages via Chrome DevTools Protocol (CDP). Use this skill when Claude needs to: (1) navigate to and browse websites, (2) extract page content, text, or links from any URL, (3) fill forms or type into input fields, (4) click buttons or links on a…

not rated 62 2mo ago A 162 tokens original MIT

browser-harness

240

matyasstoch/david-skills

Skill Claude CodeCodex

Direct browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connects to the user's already-running Chrome.

not rated 59 2mo ago A 38 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: