Skip to content
Agentmart
Submit a tool

working-with-shadow-dom

Works with open and closed shadow DOM using cdp MCP tools, JavaScript, and viewport coordinate input.

Skill by tmc

IndexedMIT★ 5
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tmc-working-with-shadow-dom

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Works with open and closed shadow DOM using cdp MCP tools, JavaScript, and viewport coordinate input. Use when an element is visible but selectors, accessibility refs, or page snapshots do not expose the actual control.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/working-with-shadow-dom

What's inside

Skill name
working-with-shadow-dom
Description
Works with open and closed shadow DOM using cdp MCP tools, JavaScript, and viewport coordinate input. Use when an element is visible but selectors, accessibility refs, or page snapshots do not expose the actual control.
License
MIT
Instructions
26 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • shadow-dom.md · references/

SKILL.md (first lines)

# Working With Shadow DOM

Use this skill when page state or interaction depends on a web component or
shadow root.

## Quick start

- Use screenshots first to confirm the target is visible.
- For open shadow roots, use `evaluate` to inspect through `element.shadowRoot`.
- For closed shadow roots, use `click coord:x,y` or other viewport-coordinate
  input; JavaScript selectors cannot traverse the closed root.
- After coordinate input, verify with another screenshot or visible page state.

## Use this skill for

- visible controls hidden behind web components
- custom elements whose inner DOM is not in `page_snapshot`
- deciding between JavaScript inspection and compositor-level coordinate input

## Read next

- Tool details and limits: [references/shadow-dom.md](references/shadow-dom.md)
- Iframe and compositor notes: [../working-with-iframes/SKILL.md](../working-with-iframes/SKILL.md)
- General live loop: [../operating-cdp-cli/SKILL.md](../operating-cdp-cli/SKILL.md)

From tmc/cdp, MIT.

More from tmc/cdp

Signals

Stars
5
Forks
1
Open issues
0
Last commit (this folder)
Sep 22, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from tmc

Cite this page

working-with-shadow-dom skill. Agent Mart. https://agentmart.dev/skills/tmc-working-with-shadow-dom (last updated 2026-10-24)