Complexity Optimizer

Agent skill for analyzing a software codebase, finding algorithmic complexity and performance hotspots, and producing safe optimization reports.

Works with Claude Code, Codex, Cursor, and 50+ other AI coding agents.

Install

npx skills add nickleefly/complexity-optimizer

Options

# Install to specific agents
npx skills add nickleefly/complexity-optimizer -a claude-code -a codex

# Install globally (available across all projects)
npx skills add nickleefly/complexity-optimizer -g

# List available skills before installing
npx skills add nickleefly/complexity-optimizer --list

# Install a specific skill
npx skills add nickleefly/complexity-optimizer -s complexity-optimizer

For more installation options, see the skills CLI documentation.

Verification

# Verify the skill is available in the repository
npx skills add nickleefly/complexity-optimizer --list

# List installed skills
npx skills list

Use

In your AI coding agent:

Use $complexity-optimizer to analyze this codebase and give me a report.

By default, report-only prompts do not modify files. The skill reports:

• File and line for each finding
• Current pattern and why it may be costly
• Estimated current complexity
• Recommended change
• Estimated complexity after the change
• Risk level
• Tests, benchmarks, or manual checks needed
• Clear statement that no files were modified

To apply a change, ask explicitly:

Use $complexity-optimizer to implement the lowest-risk optimization from the report and run the relevant tests.

Features

• Multi-language support: Python, JavaScript, TypeScript, JSX/TSX, Java, Go, C, C++, C#, Ruby, PHP, and Swift
• Safe optimization: Preserves behavior, tests, APIs, outputs, and maintainability
• Risk assessment: Each optimization includes risk level and verification requirements
• First-pass scanner: Bundled analyze_complexity.py script for initial hotspot detection

How It Works

1. Establish baseline: Identifies language, framework, test commands, and performance-sensitive paths
2. Rank opportunities: Prioritizes hot paths, large input paths, rendering loops, and database/API loops
3. Prove behavior: Locates or adds focused tests before changing code
4. Optimize conservatively: Applies proven improvements over broad rewrites
5. Verify: Runs tests and benchmarks to confirm correctness

License

MIT