AF smyx-child-nightmare-rollover-detection-analysis
Using a fixed camera in the child's bedroom (infrared night vision), the system continuously captures video and audio at night to analyze the child's sleep behavior. It detects rollover frequency (rollovers per minute), cries (recognizing specific cry-sound features), and sleep talk (speech during sleep), and generates a sleep-quality report. When rollovers occur too often (e.g., > 3 per hour), strong crying is detected, or sleep talk is observed, the system pushes 'possible nightmare' or 'restless sleep' alerts to the parents. Application scenarios: child bedrooms, infant rooms. The system relays night-time monitoring to help parents understand the child's sleep quality and provide timely comfort. Skill features: improve sleep. | 通过儿童床或卧室的固定摄像头（红外夜视），在夜间连续采集视频及音频，分析儿童的睡眠行为。检测翻身次数（每分钟翻身频率）、哭声（识别特定的哭声音频特征）以及梦话（检测睡眠中的语音），生成睡眠质量报告。当翻身过于频繁（如>3次/小时）、出现强烈哭声或梦话时，推送给父母'可能做噩梦'或'睡眠不安'的预警。应用场景：儿童卧室、婴儿房。系统夜间接力监测，帮助家长了解儿童睡眠质量，及时安抚。技能特点：改善睡眠。
As a process F 32/100 · Will not run — weak spots: steps, result and completion, when it triggers
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: 30. 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 32/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 25Steps. 1 steps
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1480 tokens
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)
- +3Description length 942: 120–800 characters recommended
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- -256 emoji in the instructions: noise for the model
- -32 of 4 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Structure: 19 headings
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.