4,556 tagged Browser automation, measured the same way as everything else here.
Browse within: agent 146Multi-Agent 114skills 110cli 105agentic-ai 103browser-automation 102LLM 93dsh-plugin 90chromium 86knowledge-graph 84persistent memory 82agents 53ai-tools 53claude-code-skills 51
Skill Codex
Capture, archive, diff, and assess Boss/Zhipin frontend JavaScript for boss-cli safety gates and anti-debug guard updates. Use when Codex needs to re-analyze current Boss frontend scripts, compare online JS with docs/research/boss-online-js baselines, update bossavailability, or recommend code changes after Boss…
Skill Claude CodeCodex
Scrape Instagram reels + followers via a Playwright user session. MCP tools manage the full application — jobs, sessions, results, settings, proxies, and status — plus the core scraping tools scrapereels, getstatus, importcookies, stopscrape, exportresults. Use for reel metadata extraction, follower counts, music…
DavidCastilloAlvarado/dsh-google-chrome-search
Skill Claude CodeCodex
Use when the user asks to search Google, do a web search, look something up on Google, or find pages/news/links by running a real Google search. Drives the local Chrome browser over CDP. Falls back to asking the human to solve a CAPTCHA when Google serves a human-verification page.
Skill Claude CodeCodex needs its repo
A tool for extracting Figma Sites and design files into detailed design data and browser-rendered style information. Figma is a design and website-building application; the tool uses a logged-in Chrome browser and a target file.
Skill Claude CodeCodex
Operate desktop or browser UI through computer-use-mcp with minimal state-aware tool calls, structured-first targeting, mutually exclusive click locators, bounded vision fallback, and fresh completion evidence. Use when choosing or sequencing computer or browser tools; do not use for implementing the MCP server itself.
Skill Claude Code
Do things on live websites: look up current prices, check real availability or stock, search a site, get a quote or a fare, drive a configurator, start a booking, or pull anything that only exists behind a form, a filter, or a login. You write a short JavaScript script against typed functions and Bowmark runs it on…
Skill Claude CodeCodex
Runs an end-to-end test from a Jira ticket number. Reads the ticket, executes the browser test steps it contains with Playwright, optionally scores any AI or text output with the RetriEval MCP, and writes a pass/fail result back to the ticket. Use this WHENEVER the user gives a ticket key and asks to test, verify, QA…
Skill Claude CodeCodex
Build, test, monitor, and manage apps on Emergent.sh using browser automation.
6missedcalls/openclaw-webmcp-skill
Skill Claude CodeCodex
Lets OpenClaw agents discover and invoke WebMCP tools exposed by websites via Chrome's navigator.modelContext API. Instead of clicking buttons and scraping DOM, the agent calls structured tools directly.
Skill Claude CodeCodex
Scrape public Instagram data without logging in and without a Meta developer account — profiles, posts, reels, stories, comments, hashtags, locations, and mentions. Use when the user wants to fetch an Instagram profile's follower count, bio, or post count, pull a profile's recent posts or reels, read the comments on a…
Skill Claude CodeCodex
Scope coverage, build a testing strategy, test the feature with agent-browser, capture screenshots/video (always mandatory), upload to S3, and create a structured test report (never skip).
Skill Claude CodeCodex
A coding-agent add-on for controlling the WeChat desktop app on a Mac through its interface. WeChat is a messaging app used for private chats, group chats, and contacts; it can also connect through Wechaty, a separate messaging framework, with the required setup.
cookiemonster0921/vincent-vnc-mcp
Skill Claude CodeCodex
Structured, reviewable test/automation/demo runs against a remote Mac controlled via the vnc-mac-agent MCP tools (screen/mouse/keyboard/clipboard/apps). Records each step with a screenshot, purpose, feature tested, and a self-assessed evaluation with cited evidence, reviewable afterward at the viewer's /reports page.…