Governed skills

Skills are registry-driven workflow selectors over typed public actions. They do not duplicate execution logic and there is no separate command layer.

Current counts are derived release facts, not permanent ceilings.

A first-class action requires a first-class skill/workflow binding. Counts can change with the registry. Missing actions fail closed; no command alias or prompt example creates an executable route.

Source-bound workflow map

This page is projected from the same current executable snapshot as the rest of the documentation set. The map is deliberately two-directional: each horizontal district shows peer stages while vertical edges show ownership and state progression.

flowchart TB
    subgraph InputDistrict["Input and classification"]
      direction LR
      A["User-selected intent"] --> B["Skill routing classification"] --> C["One of 26 governed skills"]
    end
    subgraph ExecutionDistrict["Selection and execution"]
      direction TB
      D["Ordered MCP workflow groups"] --> E["Typed action owner"] --> F["Tool existence and result validation"]
    end
    subgraph EvidenceDistrict["Evidence and outcome"]
      direction LR
      G["Skill routing receipt"] --> H["Bounded reusable workflow"]
      G -. mismatch .-> I["Fail closed on missing or ambiguous route"]
    end
    C --> D
    F --> G

Contract and readback

Canonical source owners

• skills/skill-surface-registry.v1.json
• skills/evi/references/mcp-tool-routing.v1.json
• sdk/workflows/skill-workflow-registry.v1.json

Exact backend readback

Cross-surface invariants

• The current snapshot contains 91 public actions, 26 skills, 11 hook events / 44 handlers, 119 tool requirements, 18 sector lanes, and 11 named authorities. These are derived counts, not fixed ceilings.
• Executable ownership stays one-way: skills select, MCP exposes, the outer SDK routes, the internal SDK executes, ENV selects, UOP governs, tools perform bounded work, hooks emit receipts, and the owning authority validates effects.
• Any missing identity, schema, grant, capability, dependency, receipt, or authority proof must fail closed at its owning phase; a later green check cannot retroactively authorize the skipped boundary.
• A changed route refreshes every dependent schema, manifest, generator, test, diagram, and documentation reference; the superseded executable route is directly purged in the same Delta.
• Tests, Git, CI, installation, restart, deployment, discussion, or a rendered page never imply Project HIL, Learning HIL, Goal completion, or pointer movement.

This page is a Git-tracked documentation projection. Executable source, SQLite authorities, installed-runtime receipts, and explicit human gates remain the governing evidence.