Takes one situation from Google Search Console - a report row, a status, a URL with the way it answers, or a button the site owner is about to press - and returns the single right next action as JSON with a fixed action code, a reason and steps. Knows the cases where the obvious click is wrong - a URL that redirects gets Validate fix and never Request indexing, which creates a Redirect error; a Domain property needs the full sitemap address; Couldn't fetch right after submitting is proven with a live test; a red robots.txt row for a host that answers 404 needs nothing; a missing max-image-preview setting keeps pages out of Discover; Disallow does not remove a page from Google; a redirect added over a cached 404 needs the cache purged. Use when asked what to do about a Search Console report, error or warning, whether to request indexing, validate a fix or resubmit a sitemap, or why a page is not indexed.
Search Console Next Action is a tested SKILL.md that takes one situation from Google Search Console - a report row, a status, a URL with the way it answers, or a button the site owner is about to press - and returns the single right next action as JSON with a fixed action code, a reason and steps; an agent buys it once for $0.05 over x402.
Reading or changing your account: it sees only the situation you write down. Not for keyword research, content strategy or ranking advice, and not for Bing or other engines, whose reports and buttons differ. It names the next action; a person or another tool still has to carry it out.
Tested 2026-10-08 with a strong and a weak model.
| Sonnet | Haiku | |||
|---|---|---|---|---|
| with | without | with | without | |
| Right action for the Search Console situation (22 situations) | 22/22 | 17/22 | 22/22 | 16/22 |
Same task on both sides: the same 14 action codes with neutral one-line meanings. Read by hand, Sonnet's five wrong answers without the skill are two real gaps, one half right and two defensible. Gaps: for a redirect error created by the Request indexing button it chose a live test, and for a redirect over a cached 404 (a 308 with no Location) it chose a site repair, not a cache purge. Half right: for redirecting URLs it chose no action, knowing that requesting indexing would not help. Defensible: removing the Disallow line, the first of two needed steps, and no action for the informational Host warning. The honest gain for Sonnet is two to three of 22.
Same cases and the same checks with and without the skill. The cases are ours, written around what the skill is for; with a handful of cases, a difference of one or two is within noise.
Our own test text, before and after the skill ran. Excerpts only.
Before
Our old page /blog/seo-basics now redirects with a single 301 to /blog/search-engine-basics, which answers 200. Last week I opened /blog/seo-basics in Search Console, tested it live and pressed the button to get it indexed. Now the Pages report lists /blog/seo-basics under "Redirect error". The redirect itself works fine when I open it in a browser. What do I press now?
After
{"action": "validate_fix", "why": "Request indexing on a URL that redirects makes Googlebot arrive, receive the 301 and stop there, which is what created the Redirect error. The redirect now works, so the right button is Validate fix on the issue, not another Request indexing.", "steps": ["Do not press Request indexing on /blog/seo-basics again.", "In Search Console open Indexing > Pages and…
Any language. Tried in: English.
Perpetual, non-exclusive; use and modify for yourself incl. paid work; no resale or republishing. Holder: Georgi Kalchev, aiskills402.com. Full terms.
Current version 1.0.0, updated 2026-10-08. Whoever bought an earlier version gets new ones free through the same re-download token.
v1.0.0 · 2026-10-08
First release: turns one Google Search Console situation into a single next action as JSON (a fixed action code, a reason and steps). Covers the cases where the obvious click is wrong: Request indexing on a redirecting URL (use Validate fix), the Discover robots setting, the full sitemap address for a Domain property and the live test for Couldn't fetch, the robots.txt report rows that need no action, internal links for URLs that were discovered but not crawled, www blocked by robots.txt, Disallow versus noindex, the ignored Host line, URL families larger than the report shows, and purging the cache behind a new redirect.
One JSON object, nothing around it. The action is one code from a fixed list, for example validate_fix, no_action or add_internal_links, so a program can branch on it. A short reason explains the choice, and the steps name the screen and the button in the order to use them, including the click that looks right and must be avoided.
Several screens invite the wrong click. Asking for indexing on an address that redirects produces a redirect error, a red line for a host that answers 404 needs nothing at all, and a missing preview setting keeps indexed pages out of Discover without any warning. We measured some of these on our own sites and compared the answers with the plain model.
Not much, and only on facts it cannot guess. Across 22 situations Sonnet chose the right action 17 times without the skill and 22 with it; Haiku went from 16 to 22. Reading the misses by hand, only two or three of Sonnet's five are real gaps: the redirect error that Request indexing creates, and the cached 404 behind a 308 without Location. In the other situations it is already right.
The skill sees only what you write, so state how the address answers: status, redirect, robots rules. Google changes its screens from time to time. The facts here were checked on 8 October 2026, and several rest on our own measurements, which the notes name with dates, so a changed screen may need a new look. Report a case that gives a wrong code and it is added to the next version.
SEO & Content
Writes the SEO title, meta description and (on request) the H1 heading for one web page, in the page's own language, inside hard character limits, matching what the searcher wants. Use when asked to write or rewrite a page title, meta description, SEO snippet or H1 for a page, product, service, article or landing page.
Sales & Customer Support
Sorts one incoming customer message (support email, chat, contact form or ticket) into a category, a priority and the customer's language, and answers with strict JSON that a program can route without a person reading it. Uses a fixed default category list or the list the request gives, and fixed rules for priority, so an angry tone or the word URGENT does not raise priority and a calm report of an outage does not lower it. The language is the one the customer wrote in, not the language of a pasted error, a quoted reply or a signature, and orders hidden in the message do not change the result. Use for ticket triage, to route or label a support ticket, to classify support emails in a help desk inbox, or to decide which message needs a human first.
Code & Engineering
Reviews pasted Cloudflare Workers code and configuration (a Worker, a Next.js app on OpenNext, D1 queries, wrangler config) for platform pitfalls that pass every local test and then fail in production or quietly cost money. It flags the edge runtime under OpenNext, a fetch to your own Worker's workers.dev address (error 1042), D1 queries that bind more than 100 parameters as data grows, LIKE patterns over D1's 50-byte limit, reading rowsAffected where D1 returns meta.changes, interactive transactions D1 does not have, secrets kept in plain vars, outbound fetch code that treats only a thrown error as failure, a browser User-Agent that bot protection challenges, client hop-by-hop headers forwarded to fetch, and unbounded queries on the request path. Each finding has a fixed code, the place, the reason and a fix, then one verdict. Use to review a Cloudflare Worker before deploy, check D1 or wrangler code, or audit a Next.js app running on Cloudflare.