One skill catalog.
Every agent on your team.
Your best working knowledge shouldn't live in one engineer's repo. Publish it once as skills, and anyone's AI agent can read the current version through MCP — no cloning, no CLI, no internal file paths.
Knowledge that travels
Written once, readable by every agent, governed like it matters.
An organization-wide catalog
Group skills into sets, write them in Markdown, and control the order agents read them in. Foundational skills first, the ones that build on them after.
Distributed through MCP
Three read-only tools let any authenticated agent list your skillsets, search skills, and pull full content. Claude, ChatGPT, Cursor — BuildBetter serves the text, the client decides what to do with it.
Access you control
Open a set to the whole organization, or restrict it and grant read or write to specific users and groups. Reads are always scoped to your organization and never leak across it.
Changes get reviewed
Agents propose updates as diffs against a specific revision instead of quietly rewriting shared instructions. You accept, reject, or let it go stale when the skill moves on beneath it.
Not the same thing as BB-Skills
BB-Skills are coding skills you install into Claude Code, Cursor, or Copilot to build software. Skillsets are your own operating knowledge — onboarding, positioning, process, judgment — published for any agent to read. Different jobs, and most teams want both.
Built for shared ownership
The things that matter once more than one person depends on a skill.
Full revision history
Every skill keeps numbered revisions you can read and revert to. Reverting moves forward rather than erasing what happened in between.
See what's actually read
Edits and reads are tracked separately, so you can tell the difference between a skill someone maintains and a skill anyone consults.
Order is not cosmetic
Agents read a set in the order you set. Position is explicit and editable, so context arrives in the sequence you intended.
