template · core tier
SEO, AI & Syndication Kit
Rank on Google. Get cited by ChatGPT. Same pipeline.
Seven chained agent skills that build programmatic sites engineered for BOTH search rankings AND AI citation (ChatGPT, Perplexity, AI Overviews). Keyword intake → topical maps → briefs → page generation → internal linking → schema → indexing — plus a dedicated AI-search module that structures every page so LLMs cite you by name. Built for operators who want compounding traffic from every direction without a content team.
seo-autopilot/ ├── README.md · LICENSE ├── pipeline/ ← 7 chained stage-skills │ ├── seo-keyword-intake/ → 01-clusters.json │ ├── seo-topical-architecture/ → 02-topical-map.md │ ├── seo-brief-factory/ → 03-briefs/* │ └── … 4 more stages ├── ai-search/ ← AEO citability engine (6 skills) │ ├── seo-citation-hook/SKILL.md ← "Cite Me First" pattern │ ├── seo-ai-handshake/SKILL.md ← agent-discoverable schema │ ├── seo-paa-megaguide/SKILL.md ← PAA cascade ownership │ ├── seo-content-shredder/SKILL.md ← 1 page → 5 platform assets │ ├── seo-citation-tracker/SKILL.md ← weekly AI citation audit │ └── seo-launch-syndication/SKILL.md ← launch distribution checklist ├── templates/ ← Next.js page factories (production code) └── mesh-generator/ ← runnable link-plan script
Why it's different
- ▸ Every page engineered for two readers: human browsers and AI extractors
- ▸ Includes E-E-A-T quality gates so pages read human, not generated
- ▸ Schema, llms.txt, and citation-hook generation built into every stage
Runs unattended
The recurring skills in this kit ship with a scheduling procedure — not a guide for you to follow, but a file your agent reads and executes. Paste one line; it installs to the right directory for your platform, creates the schedule, and proves the first run actually wrote something.
Read RUN-UNATTENDED.md in this folder and put this kit's recurring skills on a schedule for my platform, verifying each step.
| Platform | Runs with your laptop closed | How |
|---|---|---|
| Claude Code | Yes — Anthropic's cloud | Routines, hourly or slower |
| Hermes | Only while its host stays up | cron, any interval |
| Codex | Needs a scheduler you own | codex exec + launchd or CI |
Every scheduled run has to name the file it must write, and records a result either way. A run that finishes cleanly having produced nothing is recorded as a failure — which is the difference between automation you can leave alone and automation that has quietly stopped working.
Questions, answered
Does programmatic SEO still work after AI Overviews?+
The traffic moved, it didn't die. The kit's AI-search module targets citability in AI answers alongside classic rankings — pages are engineered to be quoted, not just indexed.
Do I need to know SEO already?+
No. The pipeline encodes the strategy; the docs explain each decision. Knowing your niche matters more than knowing SEO.
Add tool connectors
Workflow kits teach the job. Integration kits handle the tools. They stack.
Zyte Scraper Kit
Scraping that notices when it silently failed — JS rendering, pagination, and the 200-with-zero-rows trap.
$39$29
VIEW
Xata Database Kit
Database work your agent won't get wrong — schema design, full-text search, and the queries that quietly return nothing.
$34$24
VIEW
Wachete Monitor Kit
Change detection that doesn't cry wolf — real diffs, not layout noise. Works with no API key.
$29$19
VIEW