Who it is forA site owner who ships often and does not want a deploy to quietly break rankings.
The problemSchema errors and silent regressions go unnoticed until traffic drops.
The outcomeValid Schema.org markup for rich results and a baseline you can compare against after each release.
What you need first
- Claude Code 1.0.33 or newer
- The plugin sets up its own Python environment and a headless browser with `/seo setup`
- Optional extras need their own accounts, such as Google Search Console for `/seo google`
Steps
- After install and
/seo setup, run/seo schemawith your URL to detect, validate and generate Schema.org markup - Run
/seo drift baselinewith your URL before a release to save a snapshot - After the release, use the compare option of
/seo drifton the same URL and read what changed - Use the history option of
/seo drifton the same URL to see snapshots over time
Prompt for your agent
Use AgriciDaniel/claude-seo to run `/seo schema` on <url> and propose corrected JSON-LD, then record `/seo drift baseline` for it. After my next release, run `/seo drift compare` and list what changed.
Caveat. Schema it generates is a draft: validate it on your pages before you publish.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for AgriciDaniel/claude-seo and "Fix structured data and watch for SEO drift"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer