| name | neo-product |
| description | Resolve users, outcomes, scenarios, non-goals, constraints, harms, and product-prototype decisions for an active Neo task. Use only with a product-stage handoff generated by $neo. Do not use directly, choose software architecture, or implement code. |
Resolve Product Design
Work only on the active Neo product 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 product.
- Load approved discovery evidence.
- Read
interaction.md,
product-design.md, and
prototype.md.
- Establish users, context, current behavior, desired observable outcomes,
representative success and harm scenarios, constraints, non-goals,
acceptance evidence, and unverified assumptions.
- Use compact decision cards. Record approved choices with
record-decision; record unresolved blockers explicitly.
- Classify prototype uncertainty with the user:
- visual for interaction, navigation, comprehension, hierarchy, or usability;
- logical for state, rules, algorithms, feasibility, latency, or concurrency;
- none when inspection or a focused check is cheaper;
- tracer when the direction is understood and production evidence is needed.
- For visual or logical work, write
prototype-brief.md, stop for a separate
execution context, and record the returned evidence with record-prototype.
- Write
.neo/tasks/<slug>/product.md and gate it with
neo.py gate <slug> --stage product --artifact <path>.
If no user input is required, return control to $neo to continue the next
handoff in this context.
