AC agentic-engagement
Deploy an agent that holds email conversations with leads: a sending domain, a mailbox, a native email trigger on reply and unsubscribe, and a heartbeat that checks thread status when nothing inbound happened. Triggers: "handle email conversations with leads", "agentic engagement", "an agent that replies to inbound email", "stand up a conversation agent on a Cargo mailbox", "native email trigger for lead replies", "keep talking to leads over email". Cargo CDK, defineDomain, defineMailbox, defineAgent, agentNativeTrigger, heartbeat, sendEmail. Skip when: you want to send one email right now, which is a native sendEmail from the CLI and needs nothing deployed; or you want a play that blasts a list rather than holding a thread.
Deploy an agent that holds email conversations with leads: a sending domain, a mailbox, a native email trigger on reply and unsubscribe, and a heartbeat that…
As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
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: 11. 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 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Result and completion. Does not say what the result is
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 28 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3225 tokens
- 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
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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 734: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 28 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.