AD new-hire-detection
Watch your whole market for people who just took a role you sell to, qualify the company each one joined against your ICP, and post the ones that fit to Slack with the verdict and the links. A deployed pipeline on a Sales Navigator job-change search; checking or writing the CRM is an optional variation. Triggers: "watch our market for new hires", "put new VPs of Sales in our market into HubSpot", "post in Slack when a new VP Sales joins a company in our ICP", "a decision-maker just joined a company in our market", "new KDM detection", "route new hires into the CRM", "tell the deal owner when a new decision-maker lands mid-deal", "run our new-hire play on a schedule". Cargo CDK, Sales Navigator, Slack, HubSpot, Salesforce, Attio. Skip when: your own CRM contacts may have moved jobs, which is track-job-changes; or you want a list of people once, which is find-b2b-leads.
Watch your whole market for people who just took a role you sell to, qualify the company each one joined against your ICP, and post the ones that fit to Slack…
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: 15. 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. 23 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 4718 tokens
- 100Steps. 24 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
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 880: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +4Structure: 10 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.