AD huawei-cloud-ces-aom-capacity-assessment
Huawei Cloud capacity assessment. Assesses capacity for instances across 21 services (NAT/RDS/ECS/ELB/EIP/CSS/DDS/DWS/DCS/DMS/TaurusDB/GeminiDB/DC/ER/EVS/EFS Turbo/APIG/DRS/VPCEP/Bandwidth/CCE) by comparing peak/valley fluctuations of monitoring data between entry instances and target instances, calculating pressure coefficients to predict festival traffic ceilings, and giving scale-out recommendations. Data collection uses hcloud (KooCLI) CES commands (CCE and other cloud-native metrics go through AOM). Supports four modes: single-instance historical, full historical, single-instance T-24, full T-24. Trigger words: 容量评估、扩容建议、节日保障、压力系数、峰谷值倍数、预计节日上限、容量预测、capacity assessment、要不要扩容、ECS/RDS/CCE 够不够用.
Huawei Cloud capacity assessment.
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 · 0
✓ No critical or high findings
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 49/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4116 tokens
- 85Steps. 60 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (11 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
- +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
- +1No license
- +2Single-language instructions
- +3Description length 705: enough signal without eating the budget
- +4Structure: 17 headings
- +3Step-by-step instructions: 60 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.