agent-repo-init
One-click initialization of a multi-agent repository from the Antigravity template. Use this skill when users want to scaffold a new project quickly (`quick` mode) or with runtime defaults (`full` mode) including LLM provider profile, MCP toggle, swarm preference context, sandbox type, and optional git init.
OpenClaw Killer Skill
name: openclaw-killer version: 1.1.0 description: One-click perfect uninstallation of OpenClaw. Say goodbye to the lobster gracefully ð¦ author: orange2ai license: MIT
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
Desktop control
`kaizen computer <verb>` reads the accessibility tree of a running app and acts on it. No screenshots, no pixel clicks, no keyboard shortcuts. Linux only (AT-SPI). It refuses every verb until the user turns this skill on.
vibe-check
Browser automation for AI agents. Use when the user needs to navigate websites, read page content, fill forms, click elements, take screenshots, or manage browser pages.
simulate-mouse-demo
Run the SimulateMouse demo scenario on SimulateMouseDemoScene. Clicks buttons, long-presses, drags boxes, split-drags through waypoints, and operates the virtual pad. Use when the user asks to run the simulate-mouse demo, test mouse simulation, or exercise the demo scene.
sidecar
Spawn conversations with other LLMs (Gemini, GPT, ChatGPT, Codex, o3, DeepSeek, Qwen, Grok, Mistral, etc.) and fold results back into your context. TRIGGER when: user asks to talk to, chat with, use, call, or spawn another LLM or model; user mentions Gemini, GPT, ChatGPT, Codex, o3, DeepSeek, Claude (as a sidecar target), Qwen, Grok, Mistral, or any non-current model by name; user asks to get a second opinion from another model; user wants parallel exploration with a different model; user says "sidecar", "fork", or "fold". CRITICAL RULES: (1) ALWAYS launch sidecar CLI commands with Bash tool's run_in_background: true. Never run sidecar start/resume/continue in the foreground. (2) The fold summary returns on stdout when the user clicks Fold in the GUI or the headless agent finishes. Use TaskOutput to read it when the background task completes. (3) Use --prompt for the start command (NOT --briefing). --briefing is only for subagent spawn. (4) NEVER use o3 or o3-pro unless the user explicitly asks for it by name. These models are extremely expensive ($10-60+ per request). If the user asks for o3, warn them about the cost before proceeding. Default to gemini for most tasks. (5) When the user asks to query MULTIPLE LLMs simultaneously (e.g., "ask Gemini AND ChatGPT", "compare Gemini vs GPT"), ALWAYS use --no-ui (headless) for all of them unless the user explicitly requests interactive. Opening multiple Electron windows at once is disruptive. Launch them all in parallel with run_in_background: true.
ab-test-generator
Generate A/B test variants for affiliate content. Triggers on: "create A/B test", "test my headline", "optimize my CTA", "generate variants", "split test ideas", "improve click-through rate", "test my landing page copy", "headline alternatives", "CTA variations", "which version is better", "optimize conversions", "test my email subject line", "compare approaches".
Picoli Mcp
MCP server for picoli.site - URL shortening and click analytics for AI agents
browser-automation
Local Python-based browser automation toolkit using Playwright. Provides command-line tools for navigating, interacting with, and testing web applications without using MCP protocols. Supports clicking, typing, hovering, screenshots, content extraction, and JavaScript execution.
PreClick — An MCP-native URL preflight scanning service for autonomous agents.
PreClick scans links for threats and confirms intent match with high accuracy before agents click.
gui
Cross-driver GUI actuation for CAE solvers running under sim-cli. Use to click buttons, fill fields, dismiss dialogs, and capture window screenshots against GUI-capable driver windows through `sim exec`.
Native DevTools
MCP server for desktop, browser (CDP), and Android automation. Screenshot, OCR, click, type.
Kane CLI â Browser Automation Skill
Use `kane-cli` for **any task that requires a real browser**: navigating websites, clicking elements, filling forms, searching, testing web UI, taking screenshots, or verifying deployments.
Claude Buddy
The user runs Claude on their Mac (Claude Desktop and/or Claude Code). A companion daemon on this device bridges them: it surfaces Claude's state and asks you to approve tool permission prompts out loud, so the user can say "yes" instead of clicking. The daemon listens on `127.0.0.1:5002`.
cloudflare-bypass
Finds and clicks Cloudflare checkbox
bilibili-hub
> **æ¹é æ¥æº**ï¼[jackwener/bilibili-cli](https://github.com/jackwener/bilibili-cli)ï¼Apache-2.0ï¼ > > æ¬æè½å¨åä»åºåºç¡ä¸åäºä»¥ä¸ç®åä¸æ¹é ï¼ > - ç§»é¤ `browser-cookie3` / `click` / `rich` / `PyYAML` / `qrcode` ä¾èµ > - Cookie 认è¯æ¹ä¸ºç´æ¥ä¼ å ¥ `dict` æä»ç¯å
click-target
Find and click a target object in XR. Use when testing UI interactions, clicking buttons, or verifying interactable elements work correctly.
DOMShell
Browse the web with filesystem commands. 38 MCP tools: ls, cd, grep, click, type via Chrome.
interactive-testing
Smoke-test the running Lightcode Electron app end-to-end via Chrome DevTools Protocol. Use when the user asks to "smoke test", "test the app", "verify the refactor in the UI", "open the app and click through", or otherwise wants Claude to drive the real running app instead of relying on unit tests. Boots dev server + Electron with CDP enabled, uses raw CDP or agent-browser as appropriate, walks the surfaces most relevant to the current diff (provider selector, ThreadDraftView, ChatPane, ThreadRuntimeRequestPanel, Browser panel), and reports findings with screenshots.
Durable UI
Durable UI is the practice of making client-side state and interactions resilient. State should survive page reloads, browser sessions, and â where appropriate â be shareable via URL. Interactive elements like dropdowns and modals should be dismissable in the ways users expect (click outside, Es
Cloudflare Connect â Subdomain + Hosting-Platform Wiring
Points a subdomain at a hosting platform (Railway, Vercel, more) by driving two browser dashboards: the platform's custom-domain form, and Cloudflare's DNS editor. End-to-end, click-by-click.
Io.Github.Pzep1/Mcp Meet
One-click Google Meet scheduling and Apple Calendar mirroring with smart availability detection
bgclick-rev
Reverse-engineer a macOS GUI automation app's background-click path and produce a Swift reproduction. Use only when the user provides a target .app and explicitly asks for IDA-backed background-click reverse engineering. Requires IDA Pro with IDA MCP attached.
agent-browser
Browser automation CLI for direct website interaction. Use when the user needs to open URLs, click buttons, fill forms, take screenshots, log in, or test web apps. NOT for web search.
cccontrol
Lightning-fast native macOS app control and testing via Accessibility APIs. 10-60x faster than screenshot-based computer use. Control any app â click, type, navigate menus, verify UI state â all without screenshots. Use when the user wants to test, control, or automate any macOS application.
Linkly
Create and manage short links, track clicks, and automate URL management
Skyvern
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
camoufox-cli
Anti-detect browser automation CLI for AI agents. Use when the user needs to interact with websites with bot detection, CAPTCHAs, or anti-bot blocks, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task that requires bypassing fingerprint checks.
pinchtab
Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, log into sites with a persistent profile, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API when the CLI is unavailable. Prefer this skill for token-efficient browser work driven by stable accessibility refs such as `e5` and `e12`.
higgsfield-apps
Use when the user asks about Higgsfield's one-click Apps, wants to know which app to use for a specific output, or needs guidance on the Apps workflow.
Openbrowser Ai
AI browser automation. Write async Python to navigate, click, type, and extract data.
Launch the Veld Feedback Loop
Veld shows the human an in-browser overlay to comment on elements, pages, and screenshots. Those comments land on a **linear queue**. Your job: drain it â pull the next item, fix it, reply, repeat â until the human clicks **Done**.
send-to-openclaw
Send web page content from Chrome to Clawdbot with one click. Chrome extension + local webhook server. Extracts clean text from any page, Google Docs (via export API, no auth needed), and X/Twitter threads (stripped of UI chrome). Use when setting up the Send to OpenClaw browser extension, troubleshooting the webhook server, or helping users send page content to their Clawdbot instance.
makepad-router
CRITICAL: Use for ALL Makepad/Robius questions including widgets, layout, events, and shaders. Triggers on: makepad, robius, live_design, app_main, Widget, View, Button, Label, Image, TextInput, ScrollView, RoundedView, SolidView, PortalList, Markdown, Html, TextFlow, layout, Flow, Walk, padding, margin, width, height, Fit, Fill, align, spacing, event, action, Hit, FingerDown, FingerUp, KeyDown, handle_event, click, tap, animator, animation, state, transition, hover, pressed, ease, shader, draw_bg, draw_text, Sdf2d, pixel, gradient, glow, shadow, font, text_style, font_size, glyph, typography, tokio, async, spawn, submit_async, SignalToUI, post_action, apply_over, TextOrImage, modal, collapsible, drag drop, AppState, persistence, theme, Scope, deploy, package, APK, IPA, WASM, cargo makepad, makepad widget, makepad ç»ä»¶, makepad æé®, makepad å¸å±, makepad äºä»¶, makepad å¨ç», makepad çè²å¨, å建ç»ä»¶, èªå®ä¹ç»ä»¶, å¼ååºç¨, å± ä¸, 对é½, ç¹å»äºä»¶, æ¬åææ, æ¸å, é´å½±, åä½å¤§å°
bilibili-cli Skill
A CLI tool for interacting with Bilibili (åå©åå©). Use it to fetch video info, search content, browse user profiles, and perform interactions like liking or triple-clicking.
compose-ui-control
Control a running Compose Desktop application via HTTP. Use when you need to interact with UI elements, click buttons, enter text, wait for elements to appear, or capture screenshots in a Compose Desktop app that has compose-ui-test-server enabled.