AC sleep-routine-coach
Provide privacy-first, non-diagnostic sleep habit coaching with a short setup, consent-gated wind-down reminders, and gradual sleep-time adjustment that does not require a fixed sleep duration. Build deterministic 15- or 30-minute reminder stages and require user confirmation before advancing. Use goodnight and morning messages as low-friction data collection for descriptive trend analysis, with local records, corrections, reminder controls, and weekly summaries. Use when a user wants gentler bedtime cues, wants to move a late or early sleep time gradually, says goodnight or good morning in an established coaching context, manages sleep data, or requests explicitly authorized OpenClaw Cron reminders.
Provide privacy-first, non-diagnostic sleep habit coaching with a short setup, consent-gated wind-down reminders, and gradual sleep-time adjustment that does…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 0. 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 54/100
- 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
- 30Running it twice. 5 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1704 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4No input/output examples
- +2Single-language instructions
- +3Description length 709: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 27 items
- +4Reference files are cited in the instructions (4 of 4)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.