AI search measurement for ai-seo, adapted with credit from Profound's MIT-licensed AEO skills and labeled as vendor research.
- ai-seo (2.8.0 → 2.9.0): four new references.
answer-accuracy.mdis a claim ledger for what AI says about you, with seven verdicts, source tracing, severity, and a fix-the-source workflow.prompt-portfolio.mdcovers intent families, stable/exploratory/control cohorts, versioning, run cadence by portfolio size, and multi-turn buying journeys.ai-attribution.mdmeasures exposure, immediate, delayed, and business layers with 1-hour, 24-hour, and 7-day windows and names the evaluation design behind each claim.multilingual-and-commerce.mdadds a per-language AEO checklist and a fit check for AI shopping surfaces. Citations-vs-recommendations gains a citation-mix taxonomy with channel rules; agent-defaults gains a docs audit for coding agents (task-to-page map, technical fact ledger); content-patterns gains a fact-family fan-out matrix. SKILL.md adds an evidence-order rule and replaces the "third-party sources matter more than your own site" claim with the measured citation mix. Stat cleanup: SE Ranking, Profound, and BrightEdge figures now carry sources and dates; the ZipTie attribution is corrected to Sellm.io; the 40/35/25 split, the 3.2x freshness multiplier, and the 30–40% schema lift are cut as unverifiable.
Skill ZIP assets
Complete source catalog: 50 skills.
Claude web target: 50 skills with reviewed short descriptions.
Choose <name>-claude-web.zip for the documented single-folder web upload format.
Source ZIPs retain original metadata; they are not substitutes for omitted web ZIPs.
Live client upload, account limits, and invocation behavior have not been verified.
Web omissions (also recorded in claude-web-manifest.json):
- None.