Ops Desktop

What it does

When your agent uses it

• Asks to control the desktop

Example prompts

• “control the desktop”
• “/ops-desktop”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): Bash, Read, AskUserQuestion, ToolSearch, mcp__desktop-act__acquire_desktop, mcp__desktop-act__release_desktop, mcp__desktop-act__list_desktops, mcp__desktop-act__list_windows, mcp__desktop-act__launch_app, mcp__desktop-act__screenshot, mcp__desktop-act__observe, mcp__desktop-act__click, mcp__desktop-act__keypress, mcp__desktop-act__type_text, mcp__desktop-act__scroll, mcp__desktop-act__act, mcp__desktop-act__act_step, mcp__desktop-act__batch, mcp__desktop-act__status

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Acquire
2. 2Observe
3. 3Drive
4. 4Verify
5. 5Release

What it can do on your machine

Read from SKILL.md and the folder at commit 1aa0928. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • AskUserQuestion
  • ToolSearch
  • mcp__desktop-act__acquire_desktop
  • mcp__desktop-act__release_desktop
  • mcp__desktop-act__list_desktops
  • mcp__desktop-act__list_windows
  • mcp__desktop-act__launch_app
  • mcp__desktop-act__screenshot

  …and 9 more on the same allowed-tools line.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ops Desktop loads about 2.1k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 702 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~27

When it runs · the whole SKILL.md, loaded when a task matches

~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, AskUserQuestion, ToolSearch, mcp__desktop-act__acquire_desktop, mcp__desktop-act__releas

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Lifecycle-Innovations-Limited/claude-ops at commit 1aa0928, republished under its MIT licence (© Lifecycle-Innovations-Limited). 702 words, ~2,101 tokens.

name

ops-desktop

description

OPS on-demand: This skill should be used when the user asks to "control the desktop", "click on…

allowed-tools

Bash, Read, AskUserQuestion, ToolSearch, mcp__desktop-act__acquire_desktop, mcp__desktop-act__release_desktop, mcp__desktop-act__list_desktops, mcp__desktop-act__list_windows, mcp__desktop-act__launch_app, mcp__desktop-act__screenshot, mcp__desktop-act__observe, mcp__desktop-act__click, mcp__desktop-act__keypress, mcp__desktop-act__type_text, mcp__desktop-act__scroll, mcp__desktop-act__act, mcp__desktop-act__act_step, mcp__desktop-act__batch, mcp__desktop-act__status

argument-hint

[goal text | 'status' | 'list' | 'release [session_id]']

effort

medium

maxTurns

40

ToolSearch select:mcp__desktop-act__acquire_desktop,mcp__desktop-act__screenshot,mcp__desktop-act__click,mcp__desktop-act__type_text,mcp__desktop-act__release_desktop

ToolSearch select:mcp__desktop-act__list_desktops

AskUserQuestion: Release session abcd1234?
  [Release]  [Skip]

# Load schemas
ToolSearch select:mcp__desktop-act__acquire_desktop,mcp__desktop-act__screenshot,...

session = mcp__desktop-act__acquire_desktop()
session_id = session["session_id"]
display    = session["display"]      # e.g. ":51"
novnc_url  = session["novnc_url"]    # e.g. http://host:6082

shot = mcp__desktop-act__screenshot(session_id=session_id)
Read(file_path=shot["path"])   # let Claude see the screen

windows = mcp__desktop-act__list_windows(session_id=session_id)

mcp__desktop-act__launch_app(session_id, app="firefox")
mcp__desktop-act__click(session_id, x=640, y=400)
mcp__desktop-act__type_text(session_id, text="ECS clusters")
mcp__desktop-act__keypress(session_id, key="Return")
mcp__desktop-act__scroll(session_id, direction="down", amount=3)
mcp__desktop-act__screenshot(session_id)   # verify

result = mcp__desktop-act__act(
    session_id=session_id,
    goal="$ARGUMENTS",
    max_iterations=20,
)

mcp__desktop-act__release_desktop(session_id=session_id)

Keep session abcd1234 alive for follow-up?
  [Keep]  [Release]

/ops:desktop                                    # status
/ops:desktop list                               # pool state
/ops:desktop release abcd1234                   # free session
/ops:desktop open the AWS ECS console and screenshot the my-project-api cluster
/ops:desktop launch Firefox and navigate to https://example.com

© Lifecycle-Innovations-Limited, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in claude-ops/skills/ops-desktop of Lifecycle-Innovations-Limited/claude-ops.

Open the folder on GitHubat commit 1aa0928