BB alibabacloud-pai-resource-group-management
End-to-end Alibaba Cloud PAI ResourceGroup (resource pool) lifecycle management via `aliyun paistudio`. Covers list / get / create / update / delete of ResourceGroups (general computing ECS or Lingjun GPU), read-only inspection of MachineGroups, and bind/unbind UserVpc. Use when the user asks to list / get / create / update / delete PAI resource groups, inspect machine groups, bind/unbind UserVpc, or audit resource-group capacity. Trigger phrases: "PAI resource group", "PAI resource pool", "Lingjun resource group", "create PAI resource group", "list PAI resource groups", "PAI machine group", "Lingjun resource group (灵骏资源组)", "PAI resource pool (PAI 资源池)", "PAI 资源组".
End-to-end Alibaba Cloud PAI ResourceGroup (resource pool) lifecycle management via aliyun paistudio.
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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
-
low Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:22Privilege escalation / world-writable permissions (documentation of a security skill)sudo mv aliyun /usr/local/bin/aliyun
security skill
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5915 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "domain" - note
frontmatter-keyunknown frontmatter key "required_permissions" - note
edit-residuethe text marks something as outdated (lines 30, 279, 281, 370): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 44 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 5915 tokens
- 85Steps. 10 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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 (10 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)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -224 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 674: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (12 of 12)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.