orchestration-envelopelisted
Install: claude install-skill gtrabanco/agentic-workflow
# Machine result contract (internal)
Interactive skills remain text-first. A headless driver obtains a compact,
validated result at the boundary; it does not add a repeated JSON section to
every user-facing skill.
The canonical [Turn contract](references/TURN_CONTRACT.md) remains here for
the executor and review skills that load it.
The executable source of truth is
[`@gtrabanco/agentic-workflow-schema`](../../packages/agentic-workflow-schema/):
types, JSON Schemas, `renderOutputInstruction(skill)`, `parseTurn(input)`, and
`compileWorkflowSnapshot(input)`. This document states the policy only; do not
copy a second schema here.
## Output profiles
`WORKFLOW_SKILL_PROFILES` is the authoritative inventory.
- `workflow-status` always returns the strict **Envelope v2** sensor result.
Its envelope includes the detailed project view under `detail`.
- The other driver-invoked skills return **SkillOutcome v1** only when the
driver appends `renderOutputInstruction(skill)` to that invocation. It has
the small model-owned fields: outcome, next intent/targets, blockers,
questions, discoveries, and evidence references.
- `ship-roadmap` is the conductor, not a worker profile: it keeps its native
terminal `SHIP:` banner and is parsed by its own fixed turn contract.
- Interactive invocations emit their normal human-readable reports; no driver
result is required.
Both results are one final fenced `json` block. The package rejects unknown
keys at the routing boundary. Reposito