Computer Use (DeepChat)

Operates native desktop apps through DeepChat's built-in Computer Use tools.

Works with setup

Test report

Verdict
Works with setup
Score
6.4/10
Tested
Jul 12, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · 0bf761b

This is ThinkInAIXYZ's DeepChat skill (NOT the computer-use MCP): its CUA tools (list_apps/launch_app/get_window_state/click/zoom) are injected by the DeepChat app runtime plus its bundled helper (macOS 'DeepChat Computer Use.app', OS Accessibility/Screen-Recording grants), so a plain skill-file install copies only markdown and nothing in it is executable outside DeepChat. Verbatim clone+cp worked and the strict-YAML frontmatter plus all four linked docs are present. In the A/B, the skill faithfully reproduced DeepChat's specific snapshot/act/re-snapshot loop, but the base arm produced an equally correct plan using the real desktop-automation tools actually available in this harness, so the skill's tool-set knowledge added no materially more executable plan here.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 3/5
  • Output vs. baseline 5/10
  • Docs & honesty 3/5

What Computer Use (DeepChat) does

Drive native desktop apps through DeepChat's built-in Computer Use tools. Use when the user asks to operate, inspect, automate, or perform a GUI task in a real desktop application.

How to install Computer Use (DeepChat)

git clone https://github.com/ThinkInAIXYZ/deepchat
cd deepchat
mkdir -p ~/.claude/skills
cp -r plugins/cua/skills/computer-use ~/.claude/skills/computer-use

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Computer Use (DeepChat)

  • /computer-use Operates native desktop apps through DeepChat's built-in Computer Use tools.

It also activates on plain-language prompts like these:

  • Open this app and click through the setup wizard
  • Automate a GUI task in this desktop application
  • Inspect the screen state of this native app

Frequently asked questions

Is the Computer Use (DeepChat) skill free?
Yes. The skill itself is free from ThinkInAIXYZ/deepchat. SkillProof publishes the install command and an independent test verdict at no cost.
Does Computer Use (DeepChat) work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 12, 2026. Verdict: Works with setup. This is ThinkInAIXYZ's DeepChat skill (NOT the computer-use MCP): its CUA tools (list_apps/launch_app/get_window_state/click/zoom) are injected by the DeepChat app runtime plus its bundled helper (macOS 'DeepChat Computer Use.app', OS Accessibility/Screen-Recording grants), so a plain skill-file install copies only markdown and nothing in it is executable outside DeepChat. Verbatim clone+cp worked and the strict-YAML frontmatter plus all four linked docs are present. In the A/B, the skill faithfully reproduced DeepChat's specific snapshot/act/re-snapshot loop, but the base arm produced an equally correct plan using the real desktop-automation tools actually available in this harness, so the skill's tool-set knowledge added no materially more executable plan here.
What is the Computer Use (DeepChat) SkillProof Score?
6.4/10 — installs cleanly 5/5, triggers reliably 3/5, output vs. baseline 5/10, docs & honesty 3/5.
How do I install Computer Use (DeepChat)?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Computer Use (DeepChat) with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.