AC steward-ops
World-class autonomous admin, personal ops, chief-of-staff skill system. Use ANY time user asks to triage email, manage inbox, track deadlines, monitor renewals, set reminders, capture tasks, build daily briefings, manage calendars, track expiring sessions, monitor subscriptions, handle billing, create SOPs, build checklists, track invoices, handle admin, build dashboards, manage vendors, track compliance, handle personal-business crossover, build escalation protocols, organize files, track domain/SSL/insurance renewals, monitor platform restrictions, audit accounts, or ANY admin, ops, inbox, deadline, reminder, task, briefing, or chief-of-staff task. If it involves organizing, tracking, triaging, reminding, monitoring, surfacing, filtering, scheduling, or back-office work — USE THIS SKILL. Also trigger for "what do I need to do", "anything urgent", "check my email", "what's coming up", "remind me", "don't let me forget", "track this", "when does X expire", "morning briefing". Trigger aggressively.
World-class autonomous admin, personal ops, chief-of-staff skill system.
As a process C 57/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, 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: 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 57/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 30Running it twice. 8 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Steps. 97 steps, 4 vague phrases
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4725 tokens
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
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 1013: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Structure: 21 headings
- +3Step-by-step instructions: 97 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (14 of 14)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.