obsidian-cli

11.9k

kepano

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.

screenshot

10.4k

openai

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.

Cloudflare Browser

9.4k

cloudflare

Control headless Chrome via Cloudflare Browser Rendering CDP WebSocket. Use for screenshots, page navigation, scraping, and video capture when browser automation is needed in a Cloudflare Workers environment. Requires CDP_SECRET env var and cdpUrl configured in browser.profiles.

browser

2.4k

cexll

This skill should be used for browser automation tasks using Chrome DevTools Protocol (CDP). Triggers when users need to launch Chrome with remote debugging, navigate pages, execute JavaScript in browser context, capture screenshots, or interactively select DOM elements. No MCP server required.

tui-validate

2.0k

mikeyobrien

Validates Terminal User Interface (TUI) output using freeze for screenshot capture and LLM-as-judge for semantic validation. Supports both visual (PNG/SVG) and text-based validation modes.

ios-debugger-agent

2.0k

Dimillian

Use XcodeBuildMCP to build, run, launch, and debug the current iOS project on a booted simulator. Trigger when asked to run an iOS app, interact with the simulator UI, inspect on-screen state, capture logs/console output, or diagnose runtime behavior using XcodeBuildMCP tools.

zoom-meeting-assistance-rtms-unofficial-community

1.8k

openclaw

Zoom RTMS Meeting Assistant — start on-demand to capture meeting audio, video, transcript, screenshare, and chat via Zoom Real-Time Media Streams. Handles meeting.rtms_started and meeting.rtms_stopped webhook events. Provides AI-powered dialog suggestions, sentiment analysis, and live summaries with WhatsApp notifications. Use when a Zoom RTMS webhook fires or the user asks to record/analyze a meeting.

desktop-screenshot

913

openakita

Capture Windows desktop screenshot with automatic file saving. When you need to show desktop state, capture application windows, or record operation results. IMPORTANT - must actually call this tool, never say 'screenshot done' without calling. Returns file_path for send_to_chat.

agent-browser-skill

652

MGdaasLab

A browser automation tool built on the agent-browser CLI. Provides snapshot capture, element interaction, screenshots, and more. Recommended for scenarios that require page snapshot analysis and interacting with elements via ref references.

qt-testing

558

talmolab

Capture and visually inspect Qt GUI widgets using screenshots. Use when asked to verify GUI rendering, test widget appearance, check layouts, or visually inspect any PySide6/Qt component. Enables Claude to "see" Qt interfaces by capturing offscreen screenshots and analyzing them with vision.

browser

538

gmickel

Browser automation via agent-browser CLI. Use when you need to navigate websites, verify deployed UI, test web apps, read online documentation, scrape data, fill forms, capture baseline screenshots before design work, or inspect current page state. Triggers on "check the page", "verify UI", "test the site", "read docs at", "look up API", "visit URL", "browse", "screenshot", "scrape", "e2e test", "login flow", "capture baseline", "see how it looks", "inspect current", "before redesign".

browser-testing-with-screenshots

534

AgentWorkforce

Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality

screen-capture-api

376

a5c-ai

Cross-platform screen and window capture for screenshots and recording

screenshot-comparison

376

a5c-ai

Visual regression testing through screenshot capture and comparison. Pixel-diff analysis, responsive screenshot capture across viewports, and visual change reporting with highlighted differences.

obsidian-cli

353

guanyang

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.

browser-automation

212

ynulihao

Non-testing browser automation - web scraping, form filling, screenshot capture, PDF generation, workflow automation. For TESTING with Playwright, use e2e-playwright skill instead. Activates for web scraping, form automation, screenshot, PDF, headless browser, Puppeteer, Selenium, automation scripts, data extraction.

enact-playwright

188

aiskillstore

Browser automation tool using Playwright - captures screenshots and extracts content from web pages

unity-editor

188

aiskillstore

Remote control Unity Editor via CLI using unityctl. Use when working with Unity projects to launch/stop editor, enter/exit play mode, compile scripts, view logs, load scenes, run tests, capture screenshots, or execute C# code for debugging. Activate when user mentions Unity, play mode, compilation, or needs to interact with a running Unity Editor.

uloop-screenshot

177

hatayama

Take a screenshot of Unity Editor windows and save as PNG image. Use when you need to: (1) Screenshot the Game View, Scene View, Console, Inspector, or other windows, (2) Capture current visual state for debugging or documentation, (3) Save what the Editor looks like as an image file.

automating-browser

127

GGPrompts

Controls Chrome browser: takes screenshots, clicks buttons, fills forms, downloads images, inspects pages, captures network requests, checks console errors, debugs API issues. Use when: 'screenshot', 'click', 'fill form', 'download image', 'check browser', 'look at screen', 'capture page', 'check for errors', 'debug network', 'API failing', 'console errors'. Provides MCP tool discovery for 70 tabz_* browser automation tools.

screenshot-capture

72

AIDotNet

捕获屏幕、窗口或区域的截图，支持标注。

Screenshot Capture Testing

71

PramodDutta

Cross-platform desktop and application screenshot capture for visual testing, UI verification, and automated visual comparison across macOS, Linux, and Windows.

agent-browser

69

zhu1090093659

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.

seer

61

w00ing

Visual feedback capture for any running macOS app window via osascript + screencapture. Use when the user wants UI verification or a fresh screenshot.

microsim-generator

51

dmccreary

Creates interactive educational MicroSims using the best-matched JavaScript library (p5.js, Chart.js, Plotly, Mermaid, vis-network, vis-timeline, Leaflet, Venn.js). Analyzes user requirements to route to the appropriate visualization type and generates complete MicroSim packages with HTML, JavaScript, CSS, documentation, screen capture, and metadata.

microsim-utils

51

dmccreary

Utility tools for MicroSim management including quality validation, screenshot capture, icon management, and index page generation. Routes to the appropriate utility based on the task needed.

kild-peek

50

Wirasm

Capture screenshots and inspect native application windows for visual verification. TRIGGERS - Use this skill when user says: - "peek at X", "peek on X", "use kild-peek" - "take a screenshot of", "capture the window" - "look at the UI", "take a look at the window", "see what X looks like" - "visual check", "verify the UI shows", "check the window" - "compare screenshots", "diff the images" - "assert the window", "validate the UI" - "click on X", "interact with the UI", "press the button" - "list elements", "find element", "inspect the UI elements" kild-peek captures screenshots of native macOS applications, compares images, runs assertions on UI state, and interacts with UI elements. Use it to visually verify what applications look like, validate UI state, and automate UI interactions during development. IMPORTANT: Always list windows first to identify the correct target. Save screenshots to the scratchpad directory for easy cleanup.

browser-use-agentcore

46

tsaol

AWS AgentCore Browser skill for automated web testing and screenshot capture. Use this skill when the user asks to: - Test if a website works - Take a screenshot of a webpage - Check for JavaScript or console errors - Verify API health endpoints - Open a URL in a cloud browser - Debug website loading issues This skill uses AWS Bedrock AgentCore Browser (cloud-based; no local browser required).

hecras_explore_gui

43

gpt-cmdr

Explores the HEC-RAS GUI to document menus, dialogs, controls, and workflows using win32com automation with screenshot capture. Use when needing to discover menu structure, document dialog controls, capture screenshots for documentation, or explore unfamiliar GUI elements in HEC-RAS. Triggers: explore GUI, screenshot, capture dialog, document menu, HEC-RAS interface, discover controls, GUI automation, menu exploration, dialog documentation, visual documentation.

web-browser

42

tkersey

Use when tasks need real-browser web automation in Chrome/Chromium via CDP: open or navigate URLs, click/type/select in forms, run page JS, wait for selectors, scrape structured content, capture screenshots, or validate UI flows on live sites.

htmlcsstoimage

40

vm0-ai

HTMLCSStoImage API via curl. Use this skill to generate images from HTML/CSS or capture screenshots of web pages.

ios-device-screenshot

37

0xBigBoss

Take screenshots from physical iOS devices connected via USB using pymobiledevice3. Use when capturing screenshots from real iPhones/iPads (not simulators), debugging on-device, or needing high-fidelity device captures. Triggers on physical iOS device screenshots, pymobiledevice3 usage, or USB-connected device capture tasks.

makepad-screenshot

31

ZhangHanDong

CRITICAL: Use for Makepad GUI screenshot debugging and visual inspection. Triggers on: /screenshot, screenshot, look at UI, view interface, capture makepad, run and capture, run and screenshot, check the result, UI screenshot, interface screenshot, screenshot makepad, capture app, bring to front

DevTools

30

henkisdabro

This skill helps launch and configure the Chrome DevTools MCP server, giving Claude visual access to a live browser for debugging and automation. Use when the user asks to set up browser debugging, launch Chrome with DevTools, configure chrome-devtools-mcp, see what my app looks like, take screenshots of my web application, check the browser console, debug console errors, inspect network requests, analyse API responses, measure Core Web Vitals or page performance, run a Lighthouse audit, test button clicks or form submissions, automate browser interactions, fill out forms programmatically, simulate user actions, emulate mobile devices or slow networks, capture DOM snapshots, execute JavaScript in the browser, or troubleshoot Chrome DevTools MCP connection issues. Supports Windows, Linux, and WSL2 environments.

Web Application Testing

30

henkisdabro

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behaviour, capturing browser screenshots, and viewing browser logs. Use when a user asks to test a web app, verify UI, capture screenshots, check browser logs, or debug frontend issues.

tmux-debug

29

richardgill

This skill captures and analyzes tmux pane content for debugging. Triggers: "debug tmux", "capture tmux output", "check other session", "tmux pane content", "what's in that terminal", "inspect background process", "tmux scrollback". Captures screen content from tmux panes to debug sessions or monitor processes.

pr-screenshot-docs

27

majesticlabs-dev

Capture and document UI changes with before/after screenshots for pull requests. Use when creating PRs that include visual changes to ensure reviewers can assess design modifications.

guided-config

27

steveclarke

Guide through service/tool configuration step-by-step while maintaining clean documentation of the successful setup path. Captures screenshots, filters failed attempts, and produces a polished README. Use when setting up integrations, configuring services, or documenting setup processes. Triggers on "help me configure", "set up integration", "guided setup".

puppeteer-automation

23

Mindrally

Expert guidance for browser automation using Puppeteer with best practices for web scraping, testing, screenshot capture, and JavaScript execution in headless Chrome.

visual-testing

20

DNYoussef

Screenshot-based visual comparison and regression testing using claude-in-chrome MCP. Captures, compares, and validates UI states to detect layout shifts, visual bugs, and design regressions across viewports.

videodb

17

video-db

What you get A single API-first video stack for agents. Ingest anything, process server-side, and ship playable streams without FFmpeg glue. • Core capabilities Ingest + Transcode - Accept any format - Change codec, bitrate, FPS, resolution - Output a playable stream for your app (CDN + hosting) Scene-level Search Engine - Build a searchable index of your media, scene by scene - Find exact moments and auto-create clips - "Indexes as code": describe what you need, programmatically - Manage 1000s of hours of footage cleanly Generate + Compose - Generate assets: image, audio, video, text - Overlay text/images, branding, motion captions - Dub videos, translate captions, add animations Real-time RTSP - Connect live streams and create understanding in real time - Define events and set up alerts - Ideal for security cams and monitoring workflows Desktop Perception - Capture screen, mic, and system audio for real-time context - Stream your desktop live - Define alerts and triggers from what's happening on screen - Store episodic memory and semantic-search sessions - Record local sessions for QA and review • Try it now "Ingest this file and give me a playable web stream link" "Generate subtitles, burn them in, and add light background music" "Index this folder and find every scene with people" "Connect this RTSP URL and alert when a person enters the zone" "start recording and give me a actionable summary when it ends"

obershot

15

ryanthedev

Context-efficient screenshot capture and analysis. Use when needing to see, analyze, or interact with screen content. Dispatches haiku subagent to analyze full-res image, returns summary + thumbnail to preserve context. Triggers on "take a screenshot", "screenshot", "what's on my screen", "capture screen", "show me the screen", "analyze this window".

eyes

14

mintuz

WHEN users express dissatisfaction with visual appearance or behavior; use Playwright MCP to capture screenshots and collaborate on UI fixes with a structured feedback loop.

screenshot-analyzer

14

blacktop

Find and analyze screenshots from ~/Downloads/Screenshots/ for UI/UX review. Use when asked to look at screenshots, review UI designs, inspect interface errors, analyze layout issues, or examine visual problems. Triggers on "check my latest screenshot", "review my UI", "analyze this screen capture".

og-image

12

dirnbauer

Generate social media preview images (Open Graph) and configure meta tags. Creates a screenshot-optimized page using the project's existing design system, captures it at 1200x630, and sets up all social sharing meta tags.

screenshot

12

x-cmd

Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.

capture-screenshots

11

maxberko

Capture product screenshots using Claude's Computer Use API. Provides visual authentication (no session expiration!), intelligent content verification, and reliable screenshot capture. Screenshots are saved to configured directory for later upload to Pylon CDN.

create-release

11

maxberko

Orchestrate complete product release workflow for FINISHED, PRODUCTION-READY features. Executes comprehensive release preparation including screenshot capture, documentation creation/updates, knowledge base sync, and customer announcement generation. ONLY invoke when user explicitly requests a "release", "launch", "announcement", or "release materials" for a completed feature ready for customer communication. Do NOT use for bug fixes, incomplete features, documentation-only updates, or internal changes. This is a high-stakes workflow that runs start-to-finish without stopping.