// Operates the cdp CLI for browser navigation, element interaction, JavaScript evaluation, browser attachment, and interactive REPL workflows. Use when the task involves driving Chrome or Chromium with the repo's cdp command, exploring available commands, or choosing between interactive and scripted execution.
Writes and explains txtar-based cdp automation scripts, including txtar header comments, main.cdp, helper JavaScript files, sourced helper scripts, assertions, and artifact output. Use when the task involves authoring, debugging, or reviewing cdp run scripts.
Captures network activity with HAR, HARL, and cdp tagging workflows, including streaming capture, annotations, and WebRTC or gRPC-Web related recorder output. Use when the task involves recording, filtering, or explaining network traffic capture in this repository.
Captures screenshots, PDFs, and visual artifacts from pages driven by cdp scripts or the interactive CLI. Use when the task involves screenshot workflows, device emulation captures, PDF export, or embedding visual artifacts into recorded sessions.
Applies device and network emulation through the cdp MCP server. Use when the task involves viewport changes, mobile presets, throttling, offline mode, geolocation, or request header overrides.
Handles JavaScript dialogs through the cdp MCP server. Use when the task involves alert, confirm, prompt, or beforeunload flows that block page automation until the dialog is answered.
Captures and compares DOM snapshots through the cdp MCP server. Use when the task involves proving what changed after an interaction, navigation, or script execution.
| name | operating-cdp-cli |
| description | Operates the cdp CLI for browser navigation, element interaction, JavaScript evaluation, browser attachment, and interactive REPL workflows. Use when the task involves driving Chrome or Chromium with the repo's cdp command, exploring available commands, or choosing between interactive and scripted execution. |
Use this skill when the task is primarily about running or explaining the cdp command.
go build -o cdp ./cmd/cdpcdp run when the task should be reproducible as a scriptcdp commands and aliasesFor live browser work, prefer cdp --mcp and use a screenshot-first loop:
screenshot, usually with annotation enabled, and use page_snapshot when you need accessible element refs.click or type_text using @ref values first, CSS selectors when stable, and coord:x,y viewport clicks when the target is visible but not represented well in the accessibility tree.screenshot after every meaningful action; use get_page_content, get_console, and get_errors for text and failure context.page_snapshot after navigation or large DOM changes; stale refs should not be debugged manually first.list_frames/switch_frame, handle_dialog, upload_file, storage/cookie tools, network log tools, screenshots, and PDFs.raw_cdp only as an escape hatch for a missing tool or protocol-specific diagnosis.Treat screenshots as the source of truth for visible state. Text snapshots are complements, not replacements, because many browser failures are layout, focus, overlay, iframe, or dialog problems.
cdp run: ../writing-cdp-scripts/SKILL.md