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.
Controls Chrome browser to take screenshots, click buttons, fill forms, and debug network issues.
/plugin marketplace add ggprompts/tabzchrome/plugin install conductor@tabzchrome-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/workflows.mdControl Chrome browser programmatically via the Tabz MCP server. 70 tools for screenshots, interaction, network debugging, and more.
# List all tabz tools
mcp-cli tools tabz
# Search for specific tools
mcp-cli tools tabz | grep screenshot
mcp-cli grep "network"
# Get tool schema before calling (REQUIRED)
mcp-cli info tabz/tabz_screenshot
# Call tool
mcp-cli call tabz/tabz_screenshot '{}'
mcp-cli info tabz/tabz_get_console_logs
mcp-cli call tabz/tabz_get_console_logs '{"level": "error"}'
# 1. Enable capture BEFORE triggering the action
mcp-cli info tabz/tabz_enable_network_capture
mcp-cli call tabz/tabz_enable_network_capture '{}'
# 2. Trigger the action (click button, navigate, etc.)
# 3. Get failed requests (status >= 400)
mcp-cli info tabz/tabz_get_network_requests
mcp-cli call tabz/tabz_get_network_requests '{"statusMin": 400}'
# Or filter by URL pattern
mcp-cli call tabz/tabz_get_network_requests '{"urlPattern": "api/"}'
mcp-cli info tabz/tabz_screenshot
mcp-cli call tabz/tabz_screenshot '{}'
# Returns file path - use Read tool to view the image
mcp-cli info tabz/tabz_get_page_info
mcp-cli call tabz/tabz_get_page_info '{}'
# Returns URL, title, loading state
mcp-cli info tabz/tabz_get_element
mcp-cli call tabz/tabz_get_element '{"selector": "#error-message", "includeStyles": true}'
mcp-cli info tabz/tabz_profile_performance
mcp-cli call tabz/tabz_profile_performance '{}'
# Returns: DOM node count, JS heap size, event listeners, timing metrics
mcp-cli info tabz/tabz_get_dom_tree
mcp-cli call tabz/tabz_get_dom_tree '{"maxDepth": 3}'
# Or focus on specific element
mcp-cli call tabz/tabz_get_dom_tree '{"selector": "main", "maxDepth": 5}'
mcp-cli info tabz/tabz_get_coverage
mcp-cli call tabz/tabz_get_coverage '{"type": "js"}'
# Shows used vs unused bytes per file
| Category | Tools | Purpose |
|---|---|---|
| Tab Management | list_tabs, switch_tab, rename_tab, open_url | Navigate tabs |
| Tab Groups | create_group, add_to_group, ungroup_tabs | Organize tabs |
| Windows | list_windows, create_window, tile_windows | Window management |
| Audio | speak, list_voices, play_audio | TTS notifications |
| Page Info | get_page_info, get_element, get_dom_tree | Inspect content |
| Interaction | click, fill | Click/type |
| Screenshots | screenshot, screenshot_full | Capture visuals |
| Downloads | download_image, download_file | Save files |
| Network | enable_network_capture, get_network_requests | Debug APIs |
| Console | get_console_logs, execute_script | Debug JS |
| Performance | profile_performance, get_coverage | Diagnose slowness |
| Emulation | emulate_device, emulate_geolocation | Responsive testing |
When multiple Claude workers run in parallel, each MUST create their own named group:
# Create unique group for this worker
mcp-cli info tabz/tabz_create_group
mcp-cli call tabz/tabz_create_group '{"tabIds": [123, 456], "title": "ISSUE-ID: Research", "color": "blue"}'
# Add more tabs later
mcp-cli call tabz/tabz_add_to_group '{"groupId": 12345, "tabIds": [789]}'
# Cleanup when done
mcp-cli call tabz/tabz_ungroup_tabs '{"tabIds": [123, 456, 789]}'
Group colors: grey, blue, red, yellow, green, pink, purple, cyan
Screenshot:
mcp-cli call tabz/tabz_screenshot '{}'
Click:
mcp-cli call tabz/tabz_click '{"selector": "button.submit"}'
Fill form:
mcp-cli call tabz/tabz_fill '{"selector": "#email", "value": "test@example.com"}'
Switch tab:
mcp-cli call tabz/tabz_list_tabs '{}' # Get tab IDs (large integers like 1762556601)
mcp-cli call tabz/tabz_switch_tab '{"tabId": 1762556601}'
TTS notification:
mcp-cli call tabz/tabz_speak '{"text": "Done!", "priority": "high"}'
mcp-cli info tabz/<tool> before mcp-cli call1762556601), not 1, 2, 3#id, .class, button[type="submit"]For complex nested JSON, use heredoc to avoid escaping issues:
mcp-cli call tabz/tabz_execute_script - <<'EOF'
{"code": "document.querySelector('button').click()"}
EOF
See references/workflows.md for more patterns.
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.