Performance Optimizer

Performance Optimizer is a Quality skill for Claude Code, published by levnikolaevich in claude-code-skills.

549 stars82 forkson levnikolaevich/claude-code-skillsAdded 2026/08/25+2% in starsRepository updated 2026/08/07

agent-skillsai-agentsanthropicclaude-codeclaude-code-skillscode-reviewcodebase-auditcodexdeveloper-productivitydeveloper-toolsgithub-actionsopenaiperformance-optimizationplugin-marketplaceproduct-discoverysoftware-architecturetesting

Install in seconds

Install Performance Optimizer

Copy Performance Optimizer into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/levnikolaevich/claude-code-skills/tree/master/plugins/optimization-suite/skills/ln-31-performance-optimizer ~/.claude/skills/ln-31-performance-optimizer

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/levnikolaevich/claude-code-skills.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: plugins/optimization-suite/skills/ln-31-performance-optimizer/SKILL.md in levnikolaevich/claude-code-skills
Installs to: ~/.claude/skills/ln-31-performance-optimizer
Collection: One of 25 skills cataloged from this repository
Category: Quality — 1354 skills

What Performance Optimizer does

Performance Optimizer improves a measured latency, throughput, memory, CPU, or I/O problem by profiling and testing keep-or-discard changes. Use it for a known bottleneck, not for unbiased A/B comparisons.

Performance Optimizer is cataloged under Quality on DirSkills. Performance Optimizer comes from a repository tagged agent-skills, ai-agents, anthropic, claude-code and claude-code-skills.

Documentation

README

Excerpt

Performance Optimizer

Goal: Optimize only measured problems. Preserve correctness, isolate experiments, and retain a change only when comparable evidence shows that it improves the agreed metric without unacceptable regressions.

Execution contract: Treat the ordered checkbox workflow below as this skill's Definition of Done. Work through every item in order, and mark it complete only when its action and required evidence are complete. N/A, skipped, unavailable, or delegated items remain incomplete. Before returning, apply this skill's verdict, decision, and approval rules to every incomplete item and prepend Checklist: X/Y completeIncomplete: None | section/item — reason; outcome impact; exact next action; list every incomplete item.

Tool Routing

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Performance Optimizer

What else does levnikolaevich publish alongside Performance Optimizer?
Performance Optimizer is one of 25 skills that DirSkills catalogs from levnikolaevich/claude-code-skills, the repository it ships in. Its siblings there include Acceptance Test Builder, Architecture Auditor and Architecture Decision Recorder. Each one is a separate skill with its own page in this directory, installs the same way Performance Optimizer does, and is maintained by levnikolaevich in that same repository. The rest of the collection is listed on the levnikolaevich/claude-code-skills page.
How does Performance Optimizer compare to other Quality skills?
Performance Optimizer ranks #1162 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Performance Optimizer against them. Open each page to compare what they document and how they install.