SKILLEMALL.ai

BC cua-driver

Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, click/type/scroll by element_index or pixel coordinates, and verify via re-snapshot without bringing the target to the foreground. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real application on the host.

ClawHub Agent Skills author: Cua v0.11.0 MIT-0 9 files body ≈ 12 592 tokens Open the sourceclawhub.ai analyzed 2 d ago

Drive a native GUI app (macOS, Windows, Linux) via the cua-driver CLI (default) or MCP server; snapshot its accessibility tree, click/type/scroll by…

As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

IntegrationAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
99
Quality 40%
70
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Consistency w 8
40
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 1

✓ No critical or high findings

Medium and low: 1
  • low Exfiltration intent-browser-credential-store BROWSER.md:122
    Accesses a browser credential / cookie store (negated — the text forbids it)
    - edit Chromium `Preferences`, `Local State`, or profile files;
    negated

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 12592 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 57/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Consistency. Frontmatter name (cua-driver) differs from the folder (driver)
  • 40Execution cost. Instruction body is 12592 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 85Steps. 53 steps, 3 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 2 branches, has a failure section
  • 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 18 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (5 tags): a typed call is more reliable

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
  • -2localhost URLs: will not work for another user
  • -221 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 371: enough signal without eating the budget
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 53 items
  • +4Has examples (7 code blocks)

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

External checks

ClawHub: suspicious
The skill is coherent desktop automation, but it deserves Review because it grants high-impact screen/control authority and includes risky install and bypass modes that are not strongly user-gated.
LLM: suspicious (high) · 22 Jul 2026