AC stalled-deal-nudge
Every Monday each rep gets one Slack digest of their open deals that went quiet: how long since the last logged activity, the line that activity left off on, why the deal is worth a touch now, and a follow-up drafted for them to send. Triggers: "flag deals that went quiet", "weekly stalled deal report in slack", "nudge reps on deals with no activity", "which open deals have gone cold", "remind reps to follow up on stuck opportunities", "draft follow-ups for stalled deals weekly". Cargo CDK, defineAgent, native deal, account and activity models, SQL, Slack postMessage, workspace context, ledger model; adapts to HubSpot, Salesforce or Attio. Skip when: you want the week's GTM work ranked against initiatives, which is weekly-planning; or you want one account researched now, which is research-account.
Every Monday each rep gets one Slack digest of their open deals that went quiet: how long since the last logged activity, the line that activity left off on…
As a process C 52/100 · Has gaps — 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 52/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 17 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4322 tokens
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 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 (4 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 808: 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: 30 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.