different-ai/openwork-hub · Archived

openwork-chrome-mcp-testing

Use Chrome MCP to verify OpenWork UI flows, especially any feature that touches remote behavior. Triggers when user mentions: - "test with chrome mcp" - "ui verification" - "remote behavior test"

First seen Mar 13, 2026

Installation

$ npx skills add different-ai/openwork-hub --skill openwork-chrome-mcp-testing

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from different-ai/openwork-hub · top by installs.

npx skills add different-ai/openwork-hub

Browse all from different-ai/openwork-hub

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Declared

Repository health

Stars 26
Default branch main
Open issues 0
Status Archived

Skill metadata

Parsed from SKILL.md frontmatter.

Declared agents opencode

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,462 B
  • docs SUMMARY.md 229 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 2 installs

SKILL.md

Quick Usage (Already Configured)

1) Start headless + web UI

Start the OpenWork dev stack via Docker and open the UI:

  • Use skills/openwork-docker-chrome-mcp/SKILL.md step 1.
  • Confirm the Web UI loads and a session/chat view is accessible.

2) Test the feature in the UI

  • Navigate to the relevant screen.
  • Perform the feature flow end-to-end.
  • If the change touches remote behavior, verify the remote effect is visible in the UI.

3) Capture evidence

  • Take a Chrome MCP snapshot.
  • Pull console logs with Chrome MCP.
  • Attach logs if something fails:

- capture Chrome console output via Chrome MCP - optionally capture Docker logs for the dev stack

Required Gate (Non-Negotiable)

  • Any feature that changes remote behavior MUST be validated through Chrome MCP.
  • The feature is NOT done until the UI action succeeds in the browser via Chrome MCP.
  • If Chrome MCP validation is skipped, the change is considered incomplete and must not be merged.

Common Gotchas

  • If OpenCode Engine stays disconnected, ensure the OpenWork URL is clean and the client token is correct.
  • If you see CORS errors, check OpenWork server CORS headers for custom OpenCode headers.