BB omnichannel-roi-monitor
Build omnichannel marketing ROI views across TikTok, Meta (Facebook/Instagram), Google (Ads/Shopping/YouTube as applicable), and Email—connect traffic and spend to conversion outcomes, compare channel contribution with honest attribution limits, and produce budget reallocation and next-focus recommendations. Use this skill whenever the user mentions multi-channel ROAS, marketing mix, budget split, which platform "actually makes money," TikTok vs Meta vs Google vs email performance, incrementality or assisted conversions, attribution windows, MMM-lite views, or asks where to shift spend next quarter—even if they only paste a messy spreadsheet or say "we're bleeding on ads but don't know who wins." Also trigger on CMO-style "heat maps" of channels, MER/ACOS blended views, or reconciling platform-reported numbers with Shopify/GA4. Do NOT use for pure creative script requests with no metrics, single-channel deep dives with no cross-channel comparison unless the user asks for that channel in a mix context, or certified financial audit sign-off.
As a process B 78/100 · Nearly there — weak spots: result and completion, inputs and preconditions, progress reporting
How to improve
- Shorten the description to 1024 characters.
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1055 chars, limit 1024
Process rating: all ten parameters 78/100
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 40Result and completion. Does not say what the result is
- 65Failures and branches. 3 branches
- 100Tools and files. No external tools needed
- 100Steps. 13 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 1007 tokens
- 100Running it twice. No mutating operations
- 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 1055: 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 (2 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.