Layer 01
Skill hosting and execution
The contract other layers and agents build against.
Agents, MCP & capabilities · Concept
SkillServers, specified end to end.
Infrastructure for hosting, discovering, executing and governing reusable agent skills as network-accessible capabilities.
01
Positioning
One sentence, then the boundaries that make it credible.
Infrastructure for hosting, discovering, executing and governing reusable agent skills as network-accessible capabilities.
Status: Concept. The product is documented as a specification; production behaviour is not claimed.
02
Scope
What the brief commits to, and what it explicitly does not.
- Who it is for
- AI developers, enterprises, skill publishers, agent platform operators
- What it replaces
- embedded agent scripts, manual skill sharing and ungoverned capability endpoints
- What it produces
- A queryable record of what was known, decided and done.
- What it refuses
- Bypassing the authority model for convenience.
03
Shape
Three layers, ordered from boundary to contract.
Layer 02
Manifest and dependency management
Where the product meets the operator and the evidence is shaped.
Layer 03
Skill discovery and versioning
The outer boundary that makes the rest reviewable.
04
Status of this site
The same disclosure appears on every page.
SkillServers is classified Concept in the inventory. A complete architecture exists; runtime enforcement has not been verified. This site describes the intended product, its interfaces and the evidence a release would have to produce.
No customers, benchmarks, certifications or production deployments are claimed anywhere on this site.