AC qwencloud-observe
Report the health, performance, resource status, and actual billed cost of an application deployed by qwencloud-deploy to Alibaba Cloud International (alibabacloud.com), in plain language and without opening the console. Reads the local .qwencloud-deploy state file to identify the app and its ECS (and optional RDS MySQL) resources, then queries read-only cloud APIs to summarize application availability, ECS/RDS performance, and USD cost. Use when: the user asks how their deployed app is doing, wants a health/performance/cost overview, asks about CPU/memory/connections/slow SQL risk, or asks the monthly cost of a qwencloud-deployed app. Do not use when: no .qwencloud-deploy state file exists, the target is Aliyun China (use qianwenai-observe), or the user wants to change/recover resources (use qwencloud-operate).
Report the health, performance, resource status, and actual billed cost of an application deployed by qwencloud-deploy to Alibaba Cloud International…
As a process C 62/100 · Has gaps — weak spots: result and completion, 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
- 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-privilegereferences/cli_installation_guide.md:12Privilege escalation / world-writable permissionstar -xzf aliy…tgz && sudo mv aliyun /usr/local/bin/
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "prerequisites" - note
frontmatter-keyunknown frontmatter key "input" - note
frontmatter-keyunknown frontmatter key "output"
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 9 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 21 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2739 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
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
- +3Description length 823: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 14 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.