CB huawei-cloud-devkit-application-check-cli
Use Kunpeng DevKit CLI to collect installed software information (packages, middleware, databases) from application systems, analyze Maven POM file dependency compatibility, and generate migration assessment reports.Automatically creates a Kunpeng ECS server, uploads DevKit scripts, and on user request installs DevKit and executes scans. Trigger words: "system migration", "information collection", "maven migration", "container migration", "system migration assessment", "系统迁移", "信息收集", "maven迁移", "容器迁移", "系统迁移评估"
Use Kunpeng DevKit CLI to collect installed software information (packages, middleware, databases) from application systems, analyze Maven POM file dependency…
As a process B 76/100 · Nearly there — no weak spots found
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
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
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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
-
high Dangerous commands
cmd-install-from-urlreferences/cli-installation-guide.md:271Installs a package from an untrusted URL / archivepip install -i https://repo.huaweicloud.com/repository/pypi/simple paramiko
Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7266 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 76/100
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 60Steps. 85 steps, 8 vague phrases
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7266 tokens
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 17 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
- low The response is described with custom markup (9 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
- +4Description does not say when NOT to use the skill (false activations)
- -229 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 517: enough signal without eating the budget
- +4Structure: 34 headings
- +3Step-by-step instructions: 85 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (10 of 10)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.