BD marketing-analytics
Analyze marketing performance data using Coupler.io MCP tools (list-dataflows, get-schema, get-data). Use when the user asks to pull or analyze data from Coupler.io dataflows/data sets, generate marketing performance reports, understand campaign ROI, or investigate changes in business metrics. Make sure to use this skill whenever the user mentions Coupler.io data, marketing dashboards, channel comparisons, campaign analysis, or asks questions like "why did conversions drop", "which channel has best ROI", "where should I spend more", "what's working", "show me my marketing numbers", "pull my latest data", even if they don't explicitly say "marketing analytics". For deep paid-ads-only analysis (per-platform ad efficiency, budget pacing, brand vs non-brand, ad fatigue), use the ppc-analytics skill instead — this skill owns the cross-channel view.
Analyze marketing performance data using Coupler.io MCP tools (list-dataflows, get-schema, get-data). Use when the user asks to pull or analyze data from…
As a process D 42/100 · Unfinished process — References files that are not bundled: references/examples/
How to improve
- The text references files that are not there: add them or drop the references.
- 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
- warning
missing-refreference to a missing file: references/examples/
Process rating: all ten parameters 42/100
- 0Tools and files. 1 referenced file(s) missing: references/examples/
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 9 mutating operations with no state check
- 60Steps. 29 steps, 5 vague phrases
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 4 branches
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3660 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- medium 4 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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)
- +3Description length 855: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Structure: 21 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.