Perf Profiler
Identify performance bottlenecks and generate optimization suggestions for code, databases, and networks.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/perf-profiler-laolaoshiren/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Use when something is slow — profiles code, database, and network hot spots and suggests concrete optimizations.
What this skill does
This skill identifies performance bottlenecks across code, databases, and networks, then delivers concrete optimization strategies. Whether your application is slow due to algorithm inefficiency, database queries, or network latency, Perf Profiler analyzes the root causes and suggests practical fixes. It examines code-level patterns like algorithm complexity and memory usage, database issues such as N+1 queries and missing indexes, and network concerns including request batching and caching. The output highlights critical bottlenecks with the biggest impact first, explains each problem clearly, and quantifies expected improvements.
What it does
- Code analysis: detects algorithmic inefficiencies (O(n²) vs O(n)), unnecessary object creation, and synchronous blocking calls
- Database diagnostics: identifies N+1 queries, missing indexes, slow queries, and connection pool misconfiguration
- Network optimization: recommends request merging, caching strategies, CDN setup, and compression techniques
- Impact prioritization: flags critical bottlenecks (>50% impact) separately from minor issues
- Quantified improvements: shows estimated performance before and after optimization, with percentage gains
How to use it
Share your code, database queries, or network traces—or describe what's slow. Include file names and line numbers where possible. The skill will systematically analyze all three layers, pinpoint the biggest performance drains, propose specific fixes (like swapping nested loops for hash tables), and estimate the speed improvement you'll gain.
Note: this skill's internal instructions are written in Chinese. Claude reads them natively and will work with you in English.
Related skills
Generative Code Art
anthropics
Create algorithmic art with p5.js using randomness and interactive parameters.
Poster & Visual Design
anthropics
Create original posters and visual art in PNG and PDF formats.
Claude API Helper
anthropics
Build, debug, and optimize Claude API applications with caching and model migration support.
MCP Server Builder
anthropics
Build protocol servers that connect language models to external APIs and services.