Menu
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.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Ask Neo to help debug intermittent, complex, or hard-to-reproduce issues. Particularly useful for race conditions, memory issues, distributed-systems bugs, and cases where the symptom is not the root cause.
Ask Neo for optimization suggestions on a function, file, or hot path. Targets algorithmic improvements, redundant work, allocation/hot-loop issues — not micro-style.
Ask Neo to extract a reusable pattern from a piece of code, or to find existing patterns in the codebase that match a description. Useful for codifying conventions and finding duplicated logic.
Get Neo's code review with semantic pattern matching. Focuses on security vulnerabilities, edge cases, error handling, and performance issues across the target file or module.
Ask Neo for semantic reasoning and code suggestions over the current codebase. Use for general questions, code suggestions, or architectural guidance backed by Neo's persistent memory.
Sync current branch with base branch. Codex (you) resolves conflicts intelligently, not automated scripts.
Based on SOC occupation classification
| 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. |
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.
advise; architecture guidance is never promoted automatically. Deliberate policy learning requires explicit learn mode and stronger evidence.