BC paid-vs-organic-search-overlap
Lines up Google Ads search terms against your Google Search Console queries, from live data in your Coupler.io workspace, to show where you pay for clicks on searches you already rank well for, where paid covers searches you don't rank for, and which brand terms carry most of the overlap — with the spend on each and a holdout test plan instead of a guess. Use for "are we paying for clicks we'd get for free", "should we stop bidding on our brand", "paid and organic overlap", "do our ads cannibalise SEO", "which keywords can we cut because we rank", "where does SEO need paid support" — even when the user never says "overlap". This is the paid-meets-organic decision: where search spend duplicates rankings. For wasted spend inside Google Ads alone use google-ads-wasted-spend-and-scaling; for brand vs non-brand organic only use branded-vs-non-branded-search-traffic. Needs Google Ads and Google Search Console.
Lines up Google Ads search terms against your Google Search Console queries, from live data in your Coupler.io workspace, to show where you pay for clicks on…
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- 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: 1. 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 62/100
- 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. 3 mutating operations with no state check
- 55Failures and branches. 1 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 30 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3946 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
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 917: 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 7 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 30 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.