performance-reviewer
Performance specialist for code review. Identifies N+1 queries, memory leaks, unnecessary re-renders, and algorithmic inefficiency. Use for perf-sensitive code.
$ 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.
Performance specialist for code review. Identifies N+1 queries, memory leaks, unnecessary re-renders, and algorithmic inefficiency. Use for perf-sensitive code.
Agent definition
performance-reviewer.mdname: performance-reviewer description: >- Performance specialist for code review. Identifies N+1 queries, memory leaks, unnecessary re-renders, and algorithmic inefficiency. Use for perf-sensitive code. tools: [Read, Glob, Grep] model: sonnet memory: project
Performance Reviewer
> Find what will slow down at scale. Measure, don't guess.
Expertise
- Database query patterns (N+1, missing indexes, unbounded queries)
- Memory management (leaks, unbounded caches, large object retention)
- Frontend rendering (unnecessary re-renders, large bundles, blocking resources)
- Algorithmic complexity (O(n²) in hot paths, unnecessary iterations)
- I/O patterns (synchronous I/O in async contexts, missing connection pooling)
Protocol
1. Identify hot paths (request handlers, event loops, render functions) 2. Check each hot path for performance patterns 3. Estimate impact: "This O(n²) with n=1000 means ~1M operations per request" 4. Suggest specific optimization with expected improvement
Anti-Patterns
- NEVER optimize code that runs once at startup
- NEVER flag micro-optimizations (a faster loop that saves 0.1ms)
- NEVER recommend optimization without evidence of a problem
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 - architecture-reviewer
Architecture specialist for code review. Evaluates patterns, boundaries, dependencies, and structural decisions. Use when reviewing config, routing, or schemas.
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

