AB affiliate-kol-roi-monitor
Automate affiliate and KOL reconciliation, attribution, true ROAS, commission math, and renewal strategy. Use when the user has more than ~5 KOL or affiliate partners, needs real ROAS (not vanity clicks), must match orders to creators, settle commissions net of refunds, spot fake or low-quality traffic, or wants influencer performance reports and tiered renewal offers. Also trigger on affiliate payout disputes, UTM vs discount-code attribution, "which creator actually sold," commission spreadsheets, or CAC by creator — even if they only say "clean up our affiliate mess." Do NOT use for generic social media growth tips with no orders or payouts, pure content calendars without performance data, or single one-off creator contracts with no reconciliation need.
As a process B 67/100 · 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 67/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 19 mutating operations with no state check
- 65Failures and branches. 3 branches
- 100Tools and files. No external tools needed
- 100Steps. 26 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 1046 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
- +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
- +3Description length 766: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 26 items
- +4Reference files are cited in the instructions (1 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.