BD cherry-computer
Drive native apps via Computer Use: open, inspect, type, click, screenshot. Needs OS permissions; respect user stop.
This skill wraps Computer Use in Cherry Studio, letting your AI click, type, and read window states of native applications. Claims to work across nine platforms from Claude to DeepSeek.
Files check out: grade A, no critical issues, quality score 88. Real constraints exist—requires explicit user permission for desktop access and respects application ownership. Process score of 47 suggests either incomplete implementation or narrow use case.
Install if you're in Cherry Studio and need to automate clicks on windows. For other platforms on the list, verify compatibility separately—claimed support doesn't guarantee uniform behavior everywhere.
Drive native apps via Computer Use: open, inspect, type, click, screenshot.
As a process D 47/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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 · 0
✓ No critical or high findings
Files scanned: 2. 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 47/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 100Steps. 5 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 951 tokens
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)
- +3Description length 116: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 3 headings
- +3Step-by-step instructions: 5 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.