AC meeting-prep
The moment an external meeting is booked on anyone's Google Calendar, one card lands in Slack: who is joining, the open deal, the line that mattered last time, one recent public event, and an opener grounded in your positioning, with reschedules and cancellations threaded under it. Triggers: "tell me in slack whenever someone books", "a card for every external meeting", "briefer on our google calendar", "watch our calendars for new meetings with prospects", "post who is joining before each booked meeting". Cargo CDK, defineAgent, Google Calendar agent trigger, domain-wide delegation, getEvent, Slack postMessage, gtm_ native models, workspace context, webSearch. Skip when: you want one company looked into now, in this chat, which is research-account; or you want the call scribed after it happened, which is call-capture.
The moment an external meeting is booked on anyone's Google Calendar, one card lands in Slack: who is joining, the open deal, the line that mattered last…
As a process C 56/100 · 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: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 56/100
- 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
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (web, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4228 tokens
- 100Steps. 31 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 tags): a typed call is more reliable
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 830: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 31 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.