| name | neo-architecture |
| description | Resolve system boundaries, contracts, data and control flow, quality scenarios, failure behavior, and architectural tradeoffs for an active Neo task. Use only with an architecture-stage handoff generated by $neo. Do not use directly, reduce architecture to technology selection, or implement code. |
Resolve Architecture
Work only on the active Neo architecture stage.
Use the <neo-cli> already resolved by the active $neo router. If it is not
present in the handoff context, resolve
scripts/neo.py from the installed neo skill's
source location.
- Validate the handoff with
neo.py handoff <slug> --expect architecture.
- Load only approved upstream artifacts and relevant repository evidence.
- Read
interaction.md and
architecture.md.
- Identify the system of interest, stakeholders, concerns, responsibilities,
trust boundaries, contracts, data ownership, control flow, deployment,
failure recovery, observability, compatibility, and expensive reversals.
- Turn important quality claims into measurable scenarios.
- Compare at least two viable approaches for every consequential boundary.
Show costs, risks, migration, reversibility, and repository fit before
recommending one.
- Present decisions through compact cards and record only explicit approvals.
- Write
.neo/tasks/<slug>/architecture.md and gate it with
neo.py gate <slug> --stage architecture --artifact <path>.
If no user input is required, return control to $neo to continue the next
handoff in this context. Do not produce file-by-file implementation steps.
