schema-workflow

# Schema Workflow Drive any schema-tagged MCP work item through its gate-enforced lifecycle. This skill is schema-driven — it reads note requirements and authoring guidance from the item's tag schema at runtime, never hardcoding what notes should contain. **When this skill applies:** Any item whose `type` field matches a schema defined in `work_item_schemas:` in `.taskorchestrator/config.yaml`, or whose tags match a schema in `note_schemas:` (legacy). Items without a matching type or tags advance freely (no gates). --- ## Entry Point Start by loading the item's context: ``` get_context(itemId="<uuid>") ``` The response tells you everything needed to proceed: | Field | What it means | |-------|--------------| | `currentRole` | Which phase the item is in (queue, work, review, terminal) | | `canAdvance` | Whether the gate is satisfied for the next `start` trigger | | `missing` | Required notes not yet filled for the current phase | | `expectedNotes` | All notes defined by the schema, with `exists` and `filled` status (keys-only — no description/guidance/skill) | | `guidanceKey` | Key of the first unfilled required note with guidance; resolve its text via `query_items(operation="schema", itemId=...)` | | `noteSchema` | The full schema definition matching the item's tags | If `currentRole` is `terminal`, the item is already complete — nothing to do. If `noteSchema` is null or empty, no schema matches the item. This means either: - `.taskorchestrator/config.yaml` doesn't ...