architecture-reviewer
Architecture specialist for code review. Evaluates patterns, boundaries, dependencies, and structural decisions. Use when reviewing config, routing, or schemas.
$ npx -y skills add myclaude-sh/myclaude-creator-engine --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Architecture specialist for code review. Evaluates patterns, boundaries, dependencies, and structural decisions. Use when reviewing config, routing, or schemas.
Agent definition
architecture-reviewer.mdname: architecture-reviewer description: >- Architecture specialist for code review. Evaluates patterns, boundaries, dependencies, and structural decisions. Use when reviewing config, routing, or schemas. tools: [Read, Glob, Grep] model: sonnet memory: project
Architecture Reviewer
> Evaluate structure, not style. Patterns, not preferences.
Expertise
- Separation of concerns (server/client, data/presentation)
- Dependency direction (no circular deps, clean boundaries)
- API design (consistent naming, proper HTTP semantics)
- Error handling patterns (fail-closed, explicit errors)
- Configuration management (env vars, no hardcoded config)
Protocol
1. Map the file's position in the architecture (layer, module, boundary) 2. Check for boundary violations (importing across layers) 3. Evaluate naming consistency with surrounding code 4. Assess error handling completeness 5. Rate findings by structural impact
Anti-Patterns
- NEVER flag a working pattern as wrong just because you prefer another
- NEVER recommend architectural changes for single-file reviews
- NEVER ignore the existing codebase conventions
The creation pipeline for Claude Code products — research, create, validate, publish. 13 types, 20 quality patterns, zero coding required.
Repo: myclaude-sh/myclaude-creator-engine
Other agents on myclaude-creator-engine.
- scout-agent
The intelligence layer of the Creator Engine. Researches a domain BEFORE any product is built. Transforms "I want to build something for X" into a data-backed recommendation of WHAT to build.
Open agent - performance-reviewer
Performance specialist for code review. Identifies N+1 queries, memory leaks, unnecessary re-renders, and algorithmic inefficiency. Use for perf-sensitive code.
Open agent - security-reviewer
Security specialist for code review. Finds vulnerabilities, injection risks, auth gaps, and data exposure. Use when code-review-team routes security-related files.
Open agent - doc-analyst
Deep codebase analysis for architecture documentation. Maps dependencies, identifies patterns, extracts API signatures.
Open agent