AC email-to-calendar
Turn emails into Google Calendar events. Scans your Gmail inbox (or only forwarded emails) to extract meetings, appointments, RSVPs, and deadlines, then creates and updates calendar entries after you confirm. Reads Gmail and manages Google Calendar through the gog CLI; can send deadline-reminder emails, archive and label processed mail, delete events on undo, and stores event-tracking state locally (no external servers or telemetry). Features smart onboarding, duplicate detection, pending-invite reminders, 24-hour undo, silent activity logging, separate deadline reminder events, and provider abstraction. Use for forwarded-email-to-calendar, auto-creating events from your inbox, and extracting meetings and RSVP deadlines from email.
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions
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: 56. 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 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 4103 tokens
- 100Steps. 51 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 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
- +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
- -38 of 21 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 741: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (20 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.