AC windows-automation
This skill should be used when the user needs to automate Windows desktop operations through PowerShell and Python scripts. Trigger phrases include: "打开应用" (open app), "截图" (screenshot), "移动鼠标" (move mouse), "点击" (click), "键盘输入" (keyboard input), "自动操作" (automate), "RPA" (robotic process automation), "模拟鼠标" (simulate mouse), "模拟键盘" (simulate keyboard), "控制应用" (control app), "窗口操作" (window operation). Use this skill for any Windows automation tasks involving application control, screen capture, mouse/keyboard simulation, or desktop interaction.
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: This skill should be used when the user needs to automate Windows … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (windows-automation) differs from the folder (windows-automation-claw)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 69 steps
- 100Execution cost. Instruction body is 1867 tokens
- 100Running it twice. Mutating operations check current state
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +3Description length 549: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 69 items
- +4Has examples (16 code blocks)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.