BB alibabacloud-pai-node-management
Manage Alibaba Cloud PAI compute Nodes — list nodes within a ResourceGroup or Quota, inspect a node's status, hardware spec (GPU / CPU / memory) and resource usage, and perform safety-gated maintenance operations (cordon, uncordon, drain) with explicit two-step confirmation. Use when the user asks to list / get / inspect PAI nodes, check node status, find a node's MachineGroup or ResourceGroup, or cordon / uncordon / drain a node. Out of scope: node power changes (start / stop / reboot), node replacement / migration, per-node GPU metrics, and per-node pod listing — these are platform-managed and require escalation to the platform Ops team / Lingjun ops ticket / account manager. Trigger phrases: "PAI node", "list nodes", "node status", "GPU node", "Lingjun node", "cordon node", "uncordon node", "drain node", "isolate node for maintenance", "PAI 节点", "查看节点", "隔离节点", "恢复节点".
Manage Alibaba Cloud PAI compute Nodes — list nodes within a ResourceGroup or Quota, inspect a node's status, hardware spec (GPU / CPU / memory) and resource…
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, 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-privilegereferences/cli-installation-guide.md:22Privilege escalation / world-writable permissionssudo mv aliyun /usr/local/bin/aliyun
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7213 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 186): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 14 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 7213 tokens
- 85Steps. 29 steps, 3 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 9 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 (18 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
- +3Description length 884: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -212 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 15 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (11 of 11)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.