BD windows-health
Windows 文件管家与系统健康诊断（mac-health 的 Windows 原生版，供 WorkBuddy 等 Windows 端工具调用）。Always use when the user says「电脑管家」「文件整理」「C盘满了」「Windows清理」「磁盘整理」「电脑诊断」「清理一下」「哪些可以删」「系统整理」「电脑卡」「运行慢」「内存不足」「Windows 卡」「开机慢」。涉及删除或迁移时先诊断和校验，执行时保留清单与回滚线索。
Windows 文件管家与系统健康诊断（mac-health 的 Windows 原生版，供 WorkBuddy 等 Windows 端工具调用）。Always use when the user…
As a process D 45/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 5
✓ No critical or high findings
Medium and low: 5
-
medium Dangerous commands
cmd-execpolicy-bypassSKILL.md:106Runs PowerShell with execution policy bypassedPowerShell -ExecutionPolicy Bypass -File scripts/scan.ps1
-
medium Dangerous commands
cmd-execpolicy-bypassSKILL.md:107Runs PowerShell with execution policy bypassedPowerShell -ExecutionPolicy Bypass -File scripts/scan.ps1 -Deep
-
low Dangerous commands
cmd-execpolicy-bypassscripts/scan.ps1:2Runs PowerShell with execution policy bypassed (code comment; documentation of a security skill)# 用法：powershell -ExecutionPolicy Bypass -File scan.ps1 快速扫描
commentsecurity skill -
low Dangerous commands
cmd-execpolicy-bypassscripts/scan.ps1:3Runs PowerShell with execution policy bypassed (code comment; documentation of a security skill)# powershell -ExecutionPolicy Bypass -File scan.ps1 -Deep 深度诊断（大文件 + node_modules）
commentsecurity skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 8. 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 45/100
- 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. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (windows-health) differs from the folder (windowshealth)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 59 steps
- 100Execution cost. Instruction body is 1703 tokens
- low 19 top-level sections: this looks like several domains in one skill
- medium 4 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +1No license
- +2Single-language instructions
- +3Description length 224: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 59 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.