AB alibabacloud-compute-provision
Alibaba Cloud Compute Provision - Automatically selects an Alibaba Cloud compute resource (ECS, FC, ACK, PAI) based on user intent, then creates instances and executes scripts. Use this skill when the user needs to run compute jobs, execute scripts, train models, or deploy containerized applications on Alibaba Cloud, or mentions keywords such as cpu_bound, gpu, vCPU, budget, training, A100, or qwen. Provides a full loop of resource selection, pricing, budget control, instance creation, and script execution.
As a process B 69/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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
-
low Secrets in code
secret-high-entropy-tokenreferences/ecs.md:291High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)image_id="aliy…xxx", # Required
quoted
Files scanned: 17. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 69/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 30 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, git, python, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4179 tokens
- 100Steps. 39 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 12 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
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
- +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
- -4Absolute local paths (C:\Users, /home/…): not portable
- -36 of 8 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 512: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.