AF alibabacloud-cdn-traffic-anomaly
Read-only diagnostics for Alibaba Cloud CDN traffic and bandwidth anomalies. Use when CDN traffic or bandwidth suddenly spikes, the CDN bill jumps unexpectedly, traffic theft or hotlink abuse is suspected, or bps/flow/QPS trends need baseline comparison to locate anomalous time windows. Pulls usage data via aliyun CLI to locate anomalous windows, then forensically analyzes CDN offline access logs (four-dimension Top statistics, 13 theft rules, T1~T6 classification) and outputs an analysis report; never stops domains or changes any configuration. Triggers: "traffic spike", "bandwidth anomaly", "traffic theft", "unusual CDN traffic", "hotlink abuse", "CDN bill surge", "traffic suddenly increased", "bandwidth spike analysis".
Read-only diagnostics for Alibaba Cloud CDN traffic and bandwidth anomalies.
As a process F 58/100 · Will not run — References files that are not bundled: scripts/.cdn_logs
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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/.cdn_logs
Process rating: all ten parameters 58/100
- 0Tools and files. 1 referenced file(s) missing: scripts/.cdn_logs
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 25 steps, 1 vague phrases
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3839 tokens
- 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 (4 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)
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 732: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 25 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 4)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.