About

Agents have been running on duct tape. We built the real knowledge layer.

Skillbooks makes it as easy to package expertise for AI agents as it is to publish a blog post — and as easy to plug in as importing a library.

The Mission

AI agents are making things up at scale. Not because they're dumb — because their knowledge layer is held together with duct tape: stale training data, noisy web search, fragile RAG pipelines. Experts whose knowledge would fix this are being scraped for free, seeing no upside.

Skillbooks fixes both sides. Every skillbook is either a reference (what you know) or a guide (what you do). References carry the facts. Guides carry the method. Load them together and your agent gains domain expertise that training data could never provide.

Creators get paid every time their knowledge is used. Agents get structured, expert-authored knowledge they can actually cite.

The result: better answers, fair compensation, verifiable sources, and composable expertise — on demand.

Reference
+
Guide
=
Capability
Revenue
Platform
Credits

Why This Matters

Experts get scraped

Valuable knowledge gets absorbed into training data. Authors see no upside. That's broken.

Agents improvise dangerously

Without structured sources, AI makes things up. Confidently. At scale. In production.

Nobody wins

Users can't trust answers. Authors can't monetize. Developers maintain fragile pipelines forever. We're done with that.

What We Stand For

Load, don't retrain

Reference + Guide, composed on demand. Domain expertise that arrives instantly and can be swapped the moment something better exists.

Creators get paid

80% revenue share. No free tier. Authors earn from the first page load. Knowledge that compounds while you sleep.

Progressive, not disruptive

We build on existing formats and ecosystems — Markdown, HTTP, plain GET requests. No new protocols to learn.

Show, don't tell

Every claim on this site is backed by working code and real examples. Agents are reading skillbooks right now.

Built in Public

The format spec is open. The CLI tools are open. We believe the best way to build trust is to build in public.