BB traffic-quality-audit
Audit traffic quality beyond surface GA4 or Meta (Facebook/Instagram) reports—map source/medium weight to behavioral depth, flag likely invalid or low-intent clicks (bots, spam referrals, mis-set placements), and recommend budget cuts or exclusions. Use this skill whenever the user mentions high traffic but low conversion, CPC or CPM spikes, suspicious referral traffic, GA4 bounce or engagement anomalies, Meta placements eating budget, "junk clicks," or wants to know which sources to pause—even if they only say "help me look at my ads," "is my traffic real," or "why so many sessions, no sales." OFFICIAL PUSHY RULE: Even for vague asks about ads or traffic, you must still run a dwell-time (or engagement) vs conversion-path comparison and name at least two specific sources, campaigns, or placements to shut off, pause, or cap—unless the user truly lacks any data, in which case output the comparison framework with a data-collection checklist and **placeholder** shutoff candidates labeled as hypothetical. Do NOT use for pure creative-only requests with no analytics context, server log forensics without any marketing dashboard angle, or legal fraud prosecution advice.
As a process B 73/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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 1180 chars, limit 1024 - warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Audit traffic quality beyond surface GA4 or Meta (Facebook/Instagr… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 73/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 19 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 1354 tokens
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 1180: 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 4 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 9 headings
- +3Step-by-step instructions: 19 items
- +4Reference files are cited in the instructions (2 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.