CF hreflang-international
International / multilingual SEO audit focused on hreflang correctness: missing or broken return tags, wrong language/region codes, missing x-default, self-referencing errors, hreflang vs canonical conflicts, and inconsistent signals across HTML head, HTTP headers and XML sitemap. Also reviews URL structure (ccTLD vs subdirectory vs subdomain), language targeting and geo signals. Use whenever the user runs a multi-language or multi-region site and asks about hreflang, international or multilingual SEO, the wrong-language page showing in search, or duplicate content across country versions. Trigger on: "hreflang", "international SEO", "multilingual SEO", "multi-region", "wrong language in Google", "x-default", "ccTLD vs subdirectory", "geo targeting", "language targeting", "my English page shows for Thai users", "th/en page ranking in the wrong country", or any cross-language/cross-country ranking question. For full-site audits use /seo-analysis; for a single URL use /seo-page.
International / multilingual SEO audit focused on hreflang correctness: missing or broken return tags, wrong language/region codes, missing x-default…
As a process F 26/100 · No process to follow — References files that are not bundled: ../../seo/hreflang-international/WORKFLOW.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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
- warning
missing-refreference to a missing file: ../../seo/hreflang-international/WORKFLOW.md
Process rating: all ten parameters 26/100
- 0Tools and files. 1 referenced file(s) missing: ../../seo/hreflang-international/WORKFLOW.md
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 69 tokens
- 100Running it twice. No mutating operations
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 991: 120–800 characters recommended
- +4Structure: 1 headings, hard to scan
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -15SKILL.md body under 300 characters: nearly empty
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
Quality base 70; lint remarks subtract, signals add up to 100. Result: 54.