AB alibabacloud-live-assistant
Read-only diagnostics for Alibaba Cloud Live: stream quality checks (codecs, bitrate, GOP, B-frames, A/V sync), CDN edge-node probing, local recording/snapshot, traffic-theft analysis on abused live domains, and signed push/pull test URL generation; never changes any configuration. Use when the user reports live stream stuttering, pixelation or latency, push/pull stream failures, audio-video out of sync, wants to probe live CDN nodes or record a stream, suspects live traffic theft or anomalous billing, needs a URL authentication check, or asks for push/pull test URLs. Triggers: "live stream stuttering", "live stream pixelation", "live stream latency", "push stream failed", "pull stream failed", "audio video out of sync", "live CDN node check", "live traffic theft", "anomalous live billing", "live URL authentication check", "live stream recording", "generate push stream URL", "generate pull stream URL".
Read-only diagnostics for Alibaba Cloud Live: stream quality checks (codecs, bitrate, GOP, B-frames, A/V sync), CDN edge-node probing, local…
As a process B 71/100 · Nearly there — weak spots: result and completion, running it twice
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: 11. 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 71/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 13 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4373 tokens
- 100Steps. 38 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 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 11 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 915: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +4Structure: 17 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 5 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.