AF huawei-cloud-cce-autoscaling-diagnoser
Huawei Cloud CCE autoscaling failure diagnosis skill using Python SDK dispatcher. Use this skill when the user wants to: (1) diagnose CCE autoscaling failures across HPA not increasing Pod replicas, CCE elastic engine or Cluster Autoscaler not adding/removing nodes, missing metrics, missing CPU/memory requests, maxReplicas or max_nodes limits, Pending Pods, scheduling constraints, subnet IP exhaustion, ECS quota, or IAM agency permission issues, (2) perform HPA-to-CA cascade diagnosis linking workload-level and node-level scaling failures, (3) analyze CA Pod logs for Cluster Autoscaler signals (NoExpansionOptions, MaxNodeGroupSizeReached, QuotaExceeded, SubnetIPExhausted, IAM denied), (4) generate a complete Markdown diagnosis report with process, evidence, conclusion, confidence, and recommendations. Trigger: user mentions "autoscaling diagnosis", "弹性伸缩诊断", "HPA diagnosis", "HPA 诊断", "scaling failure", "伸缩失败", "HPA not scaling", "HPA 不伸缩", "replica scaling", "副本伸缩", "autoscaling issue", "伸缩问题"
Huawei Cloud CCE autoscaling failure diagnosis skill using Python SDK dispatcher.
As a process F 66/100 · Will not run — References files that are not bundled: references/verification-method.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/verification-method.md - note
frontmatter-keyunknown frontmatter key "id"
Process rating: all ten parameters 66/100
- 0Tools and files. 1 referenced file(s) missing: references/verification-method.md
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4492 tokens
- 100Steps. 53 steps
- 100When it triggers. States when to use and when not to
- 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 10 top-level sections: this looks like several domains in one skill
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)
- +3Description length 1009: 120–800 characters recommended
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 20 headings
- +3Step-by-step instructions: 53 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.