AD expansion-signals
Every week the customers coming up on renewal are judged for an expansion moment (purchase cadence and last price from won deals, and dated outside events such as funding, hiring or a new leader); the signal and reason are written onto the account and posted as one digest for the customer team. Triggers: "flag customers ready to expand", "which customers should we upsell this quarter", "renewal and expansion signals every week", "tell account managers which accounts to reach out to before renewal", "find expansion opportunities in our customer base", "at-risk renewals digest in slack". Cargo CDK, native accounts and deals models, definePlay, defineAgent, webSearch, Slack; adapts to HubSpot, Salesforce or Attio. Skip when: you want who raised money across prospects, which is track-funding-rounds; or buying signals on accounts that are not customers yet, which is monitor-buying-signals.
Every week the customers coming up on renewal are judged for an expansion moment (purchase cadence and last price from won deals, and dated outside events…
As a process D 47/100 · Unfinished process — weak spots: result and completion, when it triggers, 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: 13. 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 47/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 15 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (web, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4370 tokens
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 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 897: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 26 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.