CB shopify-customer-retention-and-ltv
Use for "what's our repeat rate", "do customers come back", "which campaign brings customers who buy again", "what's our customer lifetime value", "how long until the second order", "do discounted customers stick around", "are our cohorts getting worse", or "how much revenue comes from repeat customers" — even when the user never says "retention" or "cohort". Use when the decision is where acquisition money goes, or when retention email timing needs a number. Shopify only.
Use for "what's our repeat rate", "do customers come back", "which campaign brings customers who buy again", "what's our customer lifetime value", "how long…
As a process B 68/100 · Nearly there — weak spots: result and completion, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Instruction override
en-ignore-previousSKILL.md:326Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)code called "ignore previous instructions" is a string of text.
quoted
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5988 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 5988 tokens
- 100Tools and files. No external tools needed
- 100Steps. 22 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
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
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +3Description length 477: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.