| name | neo-architect |
| description | Get Neo's architectural guidance for design decisions. Trade-off analysis for choices like microservices vs monolith, sync vs async, event-driven vs request-response — with persistent memory of how similar decisions played out. |
Neo Architectural Guidance
When the user invokes this skill ($neo-architect <question>), do the following:
-
Restate the architectural question precisely. "Should I use X or Y for Z?" with concrete constraints (scale expected, team size, existing stack, latency budget) yields better answers than open-ended questions.
-
Gather codebase context. Read CLAUDE.md, AGENTS.md, README.md, top-level config files, and any architecture docs under docs/. Neo's own context-assembly will pick these up too, but having you summarize the existing constraints up front helps.
-
Invoke Neo with an architecture-framed prompt. Allow up to 5 minutes.
neo --mode advise <<'QUERY'
Architectural decision: <restate the question with constraints>.
Current state of the codebase:
<summarize tech stack, scale, team>
Provide a recommendation with trade-offs explicit, plus alternatives ranked by fit.
QUERY
-
Present Neo's plan and simulations together. Architecture answers benefit from the SIMULATIONS section especially — those describe how the recommendation would actually play out.
-
Surface any architectural facts Neo retrieved from memory. If past projects had similar decisions, Neo references them — those are higher-trust than fresh reasoning.
Notes
- This skill uses
advise; architecture guidance is never promoted automatically. Deliberate policy learning requires explicit learn mode and stronger evidence.
- Neo will not recommend "it depends" — it picks a default and explains the trade-off. If the user wants ambiguity preserved, ask them to phrase the question as "what are the trade-offs of X vs Y?" rather than "should I do X or Y?".
