Skill manifests in the agential semioverse

Skill manifests describe how agents in the agential semioverse advertise executable capabilities. Each manifest entry names a skill, its runtime (human, inference, or script), and its inputs/outputs, giving other agents a basis to plan, schedule, and verify interactions.

Role in the semioverse

• Discovery: Agents enumerate available interactions and their preconditions.
• Planning: Inputs/outputs form the interface for composing skill pipelines.
• Safety: Runtime declarations constrain what executions are allowed and how to validate them.
• Auditability: Manifest ids make it possible to log and replay skill invocations consistently.

Structure

• Frontmatter fields follow Skill Spec v1 (skill_spec_version, id, name, kind, runtime, inputs, outputs).
• Runtime covers both executable skills and non-executable guidance (invocation: manual|none|inference|documentation).
• Inputs/outputs are typed to support machine routing and validation.

Relationship to other objects

• Manifest entries are Things in the agential semioverse with footprints in logs and audits.
• MCP/OpenAPI adapters expose manifest entries as tools/endpoints for authorized agents.
• Petri-net/Lean models can treat each manifest entry as a transition for reachability/liveness checks.