AB kol-roi
Decode KOL and creator "black box" performance—strip refunds, suspicious traffic, and vanity clicks to estimate each creator's true profit contribution and produce a renewal-style P&L view. Use this skill whenever the user runs multiple affiliate links or discount codes per creator, must decide whether to renew or renegotiate with a blogger or influencer, suspects inflated traffic, needs net-of-refund revenue by creator, or wants true ROI (not platform-reported ROAS)—even if they only say "which KOL is worth keeping" or paste a messy commission export. Also trigger on UTM vs code attribution conflicts, chargebacks clawing commission, and cohort windows for repeat purchases from creator traffic. Do NOT use for pure follower growth or content calendars with no order linkage, single-post vanity metrics only, or legal contract review without performance numbers.
As a process B 68/100 · 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 68/100
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 14 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
- 65Failures and branches. 3 branches
- 100Steps. 16 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 977 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 870: 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 2 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 8 headings
- +3Step-by-step instructions: 16 items
- +4Reference files are cited in the instructions (1 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.