AB qwencloud-operate
Diagnose why an application deployed by qwencloud-deploy to Alibaba Cloud International (alibabacloud.com) is unavailable or slow, and — only after explicit user confirmation — perform a safe recovery and verify the result. Reads the local .qwencloud-deploy state file to identify ECS (and optional RDS MySQL) resources, runs minimal read-only diagnostics, then proposes one recovery action at a time (start ECS, restart the app service, reload Nginx), each gated by a confirmation that states impact. Use when: the user says the app is down / returns 502 / cannot connect to the database, or asks to restart and verify the app. Do not use when: no .qwencloud-deploy state file exists, the target is Aliyun China (use qianwenai-operate), or the user only wants a status/cost overview (use qwencloud-observe).
Diagnose why an application deployed by qwencloud-deploy to Alibaba Cloud International (alibabacloud.com) is unavailable or slow, and — only after explicit…
As a process B 74/100 · Nearly there — 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: 16. 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 74/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 6 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 25 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1438 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
- +3Description length 808: 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: 10 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (14 of 14)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.