One page template on Wise ranks for 151,315 organic searches. Not a blog post. Not a landing page.
One template, filled thousands of times with currency pairs and country codes, pulling in six figures of monthly search volume while looking like nothing at all.
The team at OpenSEO ran a teardown of Wise and put a number on it: the whole analysis cost under thirty cents.
i read that and felt a specific kind of irritation. People pay agencies five figures a year for a version of this answer. And here it is, a slash command in Claude Code, a paperclip's worth of credits, and a markdown table telling you which page types carry the traffic.
So i installed it. And then i read the actual SKILL.md, which is where things got more interesting than the announcement thread suggested.
/reverse-engineer-seo is a free, MIT-licensed skill. It was built by Every App, the company behind OpenSEO, and it lives on seo.party, their community skill marketplace.
A skill is a folder with a SKILL.md file. Claude Code, Codex, or Cursor loads it when your request matches its description. No extension, no plugin API, just instructions plus a tool connection.
The tool connection is the whole trick. The skill does not crawl anything. It calls OpenSEO's MCP server, which serves keyword, ranking, and backlink data bought from DataForSEO.
That distinction matters more than the marketing implies. The skill is a procedure. The data is rented.
Install is one line:
gh skill install every-app/seo-party-skills reverse-engineer-seo --agent claude-code
Pinned to commit ce87df4, if you care about that sort of thing. You should.
The steps are specific in a way i didn't expect. It's not "analyze the site and give me insights." It's a numbered procedure with actual parameters.
get_domain_overview and get_backlinks_overview
totalCount against the site total
That last instruction is the one that made me trust the skill. Sorting backlinks by newest is what most tools do by default, and it's useless for this question. Somebody thought about that.
A run is about 12 OpenSEO calls and 250 to 300 credits.
The skill says this itself. Which is honest, and also the first place the free story starts to wobble.
The output is a set of tables, not an essay. Playbook, scorecard, traffic engines, top pages, search patterns, link magnets, moves to copy, what won't copy.
The "what won't copy" section is the thing i keep coming back to. It's a skill that tells you what not to steal from a competitor.
Wise's currency converter pages work because Wise has a brand, a decade of links, and a product people search for by name. You can copy the template. You cannot copy the trust.
The skill says so, in the output, without being asked.
For developers and agents the appeal is different from the SEO consultant appeal. A consultant sells judgment. This sells a repeatable procedure that produces a file.
You can run it on five competitors, diff the outputs, and hand the result to a coding agent that builds the pages.
That's the real shift. Not analysis. Analysis that ends in a build spec.
The launch numbers are real. OpenSEO's post pulled 450+ likes.
Julian Goldie, who covers SEO tools to a large audience, posted about it and got 400+ likes and a YouTube video with 7,400 views in two days. There were LinkedIn reposts, Thai-language explainers, Facebook posts from marketing academies.
Then i looked at the GitHub stars. 42.
Forty-two stars on the skills repo. 259 installs on seo.party. For a thing that got a video, five social posts, and a news writeup in the same week.
i don't think that's a scandal. i think it's the gap between watching a demo and connecting a paid MCP server and running twelve billed API calls. The funnel is wide at the top and narrow at the bottom, and the bottom requires the free skill's data source to not be free.
The other thing the threads skipped: seo.party labels it plainly. Community skill, passed automated checks.
No person reviewed it.
Here's the arithmetic nobody put in the thread.
At Base plan pricing, $10 buys $10 of usage. A run is 250 to 300 credits.
So roughly thirty to forty runs per ten dollars, if nothing else touches the balance. That's cheap. Genuinely cheap.
But the skill's own notes warn you about studying more than three sites in one go. And teardowns are the kind of thing where you start with one and end with a spreadsheet.
The free part is the instructions. The meter is the data.
i want to be clear that i don't think this is deceptive. OpenSEO publishes the 28% data fee in public comparison copy. The skill tells you the cost before you start.
That's more honesty than most tools in this category manage.
It just isn't the story that got passed around.
Which reminds me of something unrelated. i have a folder of install commands i've never run. Bookmarked skills, half-read repos, a gh skill install line for something i saw in September and forgot about.
i keep the folder because deleting it feels like giving up on a version of myself who has time for all of it. That version does not exist. The folder is now a museum of ambition.
Every skill marketplace is going to become one of these folders for most people. Not because the skills are bad. Because installing is easy and setting up the connection is not.
Most sites don't need this.
If you run a five-page site and you already know why you rank, a teardown of a competitor's 40,000-page programmatic playbook tells you nothing you can use. You will read the tables, feel informed, and build none of it.
This is also not a replacement for an SEO who has opinions about your specific situation. The skill estimates. It cannot tell you whether your audience searches in your market, whether your brand can survive the content, or whether the section you're about to copy is actually holding traffic or just inheriting it.
And there's a quieter risk. Copying a competitor's structure is the fastest way to look like every other site in your category.
The skill is good at telling you what works. It's not going to tell you when the thing that works has already been done to death by eleven other companies.
If you're under 10k monthly visits and thinking about a programmatic section, use the free-tool skill first. One good page beats a thousand thin ones, and it costs less to find out you were wrong.
i opened the Wise report expecting to feel behind. Instead i felt like someone had handed me a map of a city i'd been driving around blind for years.
The thirty cent part is what stuck. Not because it's cheap, but because it puts a price on something that used to be a retainer. Somebody looked at all of it, the keyword splits and the link magnets and the template archaeology, and said: this is a script, and the script is free, and the data costs what the data costs.
There will be a hundred of these by spring. Most will be worse. A few will be better.
The ones that matter will be the ones that tell you what not to copy.