Just dropped a demo of our new Product Page Kit. A ChatGPT voice agent audits a real product page live in Chrome, points at every fix with the cursor, and builds a PDF action plan. Watch it here: https://www.youtube.com/watch?v=A6dL7PpoeqI The kit is Pro-first for now, same as always. It will reach you here at the right time, bit by bit, like every skill before it. Pro members have it today.🆕

We shipped the update live: moving the release-ready improvements from our private development repository into the public open-source edition, reviewing the changes, running the checks, and publishing the release. What changed: ✅ Fresher Google Search and AI Search guidance ✅ More accurate commands, documentation, and recommendations ✅ Stronger consistency, portability, security, and privacy checks ✅ Cleaner prompts and fewer outdated false positives ✅ No breaking changes — the existing workflow remains the same Final validation included 328 passing tests, clean consistency and portability checks, and successful credential, PII, and private-reference scans. Useful links: 🎥 Watch the livestream replay: https://www.youtube.com/live/aHJwrswC3ko ⭐ Claude SEO on GitHub: https://github.com/AgriciDaniel/claude-seo 📦 Claude SEO v2.2.3 release: https://github.com/AgriciDaniel/claude-seo/releases/tag/v2.2.3 📎 I’ve also attached the presentation covering the latest Google updates, what they mean for Claude SEO, and the release workflow we used during the livestream. If you use Claude SEO, grab v2.2.3 and let me know what you build with it! 🙌

New video is live. First time I've run both agents in parallel on the same deliverable, and it got interesting fast. The setup: Claude SEO skill in both Claude Code (Fable 5, max) and Codex (GPT 5.6 Sol, extra high), same 42-page site, one timer. What happened: - Codex won the race: 21:58, site scored 82/100, PDF report included without me asking - Claude finished ~3 min later with a deeper 18-page report, but made 2 factual mistakes Codex caught - Each agent audited the other's audit (steal this workflow, it's the best QA I've found) - Gemini Antigravity judged both blind and picked Codex - My verdict: use them together. One orchestrates, one executes. Your turn: install claude-seo (github.com/AgriciDaniel/claude-seo) and run /seo-audit on your own site with whichever agent you use. Post your health score and the one finding that surprised you most below.

Was live...taking Claude Ads v2 public: updating the website and pushing the open-source skill from 8 ad platforms to 12. All in Claude Code, in real time. Repo: github.com/AgriciDaniel/claude-ads Site: claude-ads.md ▶️ Watch: https://www.youtube.com/live/rz3dpN9wZB0

I take a website from an empty folder to live and indexed on Google with Claude Code. No code, no designer, no agency. What is inside: - Pick the niche and audience - Grab a v0 template, let Claude build it - Run SEO and GEO audits - Deploy on Railway - Connect a custom domain - Index on Google, Bing and Yandex The result is claude-ads.md, live and indexed. Same process that took claude-seo.md to 11,000 clicks in 3 months off one backlink. Free prompt pack with every command I ran: https://agricidaniel.github.io/claude-seo-prompt-pack/#c0 Watch it here: https://www.youtube.com/watch?v=UywcPcSOKsA Then go build yours and drop the link in the comments. I will check them out.