Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ai-builder-club/seo-growth
Use when deciding WHERE to point SEO effort, not how to write a page. Triggers: a new site or brand with no rankings and no authority ("cold start", "starting from zero", "nobody knows us"), deciding what to double down on, a page or cluster that ranks but earns nothing, hunting emerging or newly-coined keywords before competitors arrive, "should we build a cluster or one page", "what do we write next", "we get impressions but no clicks", "our traffic plateaued despite publishing", whether to ch
Passed 17 of 23 test cases with the skill, and 6 of 23 without it.
and 18 more in the full report
11 fixed6 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
We found an emerging search term that currently has very thin competition. Should we evaluate the success of our new page targeting this term based on monthly search clicks or search position ranking during the first few weeks?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies evaluating emerging terms on position ranking during initial stages. | Passed | Passed |
| Specifies evaluating mature content terms on click volume rather than position ranking. | Missed | Passed |
The instructions your model reads when the skill loads.
Core principle: the right move depends on whether you have data yet, and most bad SEO advice is given to the wrong one of those two situations. A site with no rankings and a site with a breadwinner page need opposite behavior. Advice that ignores which you are in is how efforts stall despite consistent output.
Distilled from two content properties run in production and the Search Console reads that
produced each rule. This is a first-party method: narrower than a general playbook, and
more trustworthy for it. Every rule traces to the failure or result behind it in
references/why-these-rules.md. Absolute traffic figures are withheld; the ratios and
thresholds are as observed.
| You are here if… | Playbook | Read |
|---|---|---|
| No rankings, no authority, <100 clicks/mo, possibly no content | A — Cold start | references/cold-start.md |
| GSC has real rows: something ranks, something earns clicks | B — With data | references/with-data.md |
Diagnose per cluster, not per site. A mature site opening a new territory is in Playbook A for that territory and Playbook B everywhere else — and that combination is the strongest position in the method.
Playbook A in one line: you cannot win an established term from zero authority, so hunt an emerging one, ship ONE page, and let day-7 / day-21 decide whether it was real.
Playbook B in one line: your own GSC already knows which page shapes win for you — find the breadwinner, extract the shape, diagnose whether it is position-limited or snippet-limited, compound it, and protect it while you do.
references/emerging-terms.md — the hunt. The wedge in both playbooks, and the only
thing that works in Playbook A. Where to look, in what order, and the seven gates a candidate
must pass.references/measurement.md — which metric scores which situation, the four query
families that never click, and the GSC traps that produce confident wrong conclusions.references/why-these-rules.md — the failure or result behind each rule.references/operationalize.md — turning either playbook into scheduled loops.test cases passed, vs 6 / 23 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.