AB alibabacloud-cms-manage
Entry skill for the aliyun CLI distribution of CloudMonitor (CMS). Use when the user mentions aliyun cms2, CloudMonitor, CMS commands, or any CMS module operation such as Integration Policy/Center, APM, RUM, Prometheus Service, Recording rule, alert rule, alert template, alert history, event hub, SLS event, PromQL, cloud resource, service observability, monitoring onboarding, metric query, etc.
Entry skill for the aliyun CLI distribution of CloudMonitor (CMS).
As a process B 79/100 · Nearly there — weak spots: running it twice
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
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
medium Dangerous commands
cmd-pipe-to-shellreferences/ai.md:207Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- 各有专用 installer 脚本（`curl -fsSL ... | bash`），脚本自动安装对应可观测插件
quoted
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7119 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 79/100
- 30Running it twice. 27 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Steps. 36 steps, 4 vague phrases
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7119 tokens
- 100Result and completion. Output format and completion criterion are stated
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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)
- +2Single-language instructions
- +3Description length 397: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 36 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (16 of 18)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.