AC inbound-qualification
Turn the website's demo form into qualified inbound: each submission runs a Cargo tool that identifies the company by work email, qualifies it against the ICP, lands account and contact in the shared GTM models, posts it to Slack, and answers on the page with a booking link or a thank-you; an optional play then tiers and summarises each qualified contact. Triggers: "add a demo form to our website", "handle inbound leads", "route website form submissions", "qualify inbound demo requests", "contact form that books meetings", "inbound lead flow", "Cargo public form", "tier each demo request and summarise it". Cargo CDK, defineTool, publicForm, @cargo-ai/form-sdk, definePlay, gtm_accounts, gtm_contacts. Skip when: you want visiting companies that fill nothing in, which is visitor-identification; no site yet, which is website-building first; or leads from a list, which is find-b2b-leads.
Turn the website's demo form into qualified inbound: each submission runs a Cargo tool that identifies the company by work email, qualifies it against the…
As a process C 54/100 · 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: 17. 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 54/100
- 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. 11 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 (bash, web, node) that frontmatter does not declare
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3945 tokens
- 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 895: 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: 33 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.