SKILLEMALL.ai
GitHub ↗ RU Sign in

BC peekaboo-linux-gnome-wayland-computer-use

See and control GNOME Wayland desktops using gnome-screenshot, ydotool, Window Calls, AT-SPI hybrid element coordinates, and optional GNOME Remote Desktop. The Linux/Wayland counterpart to macOS computer-use ("peekaboo") — a native agent on the box can screenshot, reason over the image, locate UI elements by role/name, and click/type them, with no human, no RDP, and no global-coordinate accessibility. Covers the native single-actor loop, the remote-over-SSH path, and an optional RDP fallback for hands-on human access.

ClawHub Agent Skills author: Kyzcreig v1.0.2 MIT-0 9 files · 1 script body ≈ 4 420 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

See and control GNOME Wayland desktops using gnome-screenshot, ydotool, Window Calls, AT-SPI hybrid element coordinates, and optional GNOME Remote Desktop.

As a process C 55/100 · Has gaps — weak spots: result and completion, inputs and preconditions

ProcedureGitHubAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
84
Quality 40%
85
Run on models
none yet
Process rating
C
55/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
50
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 4

    ✓ No critical or high findings

    Medium and low: 4
    • medium Dangerous commands cmd-privilege references/peekaboo-and-rdp-setup-ubuntu-gnome-wayland.md:81
      Privilege escalation / world-writable permissions
      #     | sudo tee /etc/udev/rules.d/99-u…les
    • medium Dangerous commands cmd-privilege references/peekaboo-and-rdp-setup-ubuntu-gnome-wayland.md:163
      Privilege escalation / world-writable permissions
      sudo chown gnome-remote-desktop:gnome-remote-desktop "$SYS/rdp-tls".{key,crt}
    • medium Dangerous commands cmd-privilege references/peekaboo-and-rdp-setup-ubuntu-gnome-wayland.md:164
      Privilege escalation / world-writable permissions
      sudo chmod 600 "$SYS/rdp-tls.key"; sudo chmod 644 "$SYS/rdp-tls.crt"
    • low Dangerous commands cmd-background-process references/peekaboo-and-rdp-setup-ubuntu-gnome-wayland.md:166
      Starts a background / autostarted process
      sudo systemctl enable --now gnome-remote-desktop.service

    Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 55/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 50When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 70Execution cost. Instruction body is 4420 tokens
    • 100Steps. 31 steps
    • 100Consistency. Name and required fields are in place
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 10 top-level sections: this looks like several domains in one skill

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -31 of 3 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 523: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 31 items
    • +4Has examples (10 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

    External checks

    ClawHub: suspicious
    This skill openly enables unattended screenshotting and control of a GNOME desktop, but the persistent remote-control setup is broad enough that users should review it carefully before installing.
    LLM: suspicious (medium) · VirusTotal: · 3 Jun 2026