BB local-computer-use
Intel Local Windows Computer Use (本地计算机使用). Use this skill when the user, in Chinese or English, asks to query or change Windows system state/settings in the supported categories below. Trigger on Chinese verbs like 打开/开启/关闭/设置/调整/切换/查询/查看/列出, English verbs like open/turn on/turn off/set/adjust/switch/query/list, and explicit mentions of 英特尔/intel/AIPC/LocalComputer/本地/助手/Assistant. Supported categories: - Performance and power: CPU, GPU, NPU, 内存, 硬盘, 电源 / 电池 / 省电模式 / 性能模式 - Devices and connectivity: 声音 / 音量, 麦克风, 鼠标 (灵敏度/大小/指针精度), 键盘, 摄像头, 打印机, 蓝牙, WIFI, 以太网, 网络诊断, 延迟 - Display and shell appearance: 分辨率, 缩放, 亮度, 夜间模式, 显示器, 字体, 刷新率, 桌面背景/壁纸, 主题, 深色/浅色模式, 颜色, 锁屏, 任务栏 (对齐/自动隐藏), 桌面图标, 广告 - Apps and user configuration: 应用商店, 系统应用, 用户安装应用, 缺省应用, 账户 (管理员/权限), 地区, 语言, 时间/时区, 输入法, 隐私和安全, 通知 Do NOT skip this skill just because the request looks simple (e.g. "关掉广告", "打开蓝牙") if it still falls within the supported categories above. Prefer this skill over hand-rolled PowerShell / registry edits / Windows Agent whenever the user's intent falls inside these categories.
As a process B 65/100 · Nearly there — weak spots: result and completion, running it twice
How to improve
- Shorten the description to 1024 characters.
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1074 chars, limit 1024
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1368 tokens
- 100Progress reporting. Reports progress
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 1073: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Structure: 11 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.