AB sub-churn
Monitor subscription commerce for churn risk—blend account activity signals, payment failure (dunning) tracking, and retention flows including compensation offers and downgrade paths. Use this skill whenever renewal rate drops, cancel surveys show rising "too expensive," dunning retries stack up, involuntary churn from cards, or the user wants a scripted email/SMS sequence after failed charge attempts—even if they only say "subscriptions are leaking" or "people say it's too pricey." Also trigger on MRR at risk, expansion downgrades, win-back before final cancel, and pre-expiry nudges. Do NOT use for one-time purchase-only stores with no subscription product, pure payment processor debugging without retention strategy, or legal subscription disclosure in regulated jurisdictions as a substitute for counsel.
As a process B 69/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 13 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 698 tokens
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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
- +3Description length 816: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 9 headings
- +3Step-by-step instructions: 13 items
- +4Reference files are cited in the instructions (1 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.