Python Performance — Claude Code skill: what it does, how to install
Python Performance guides AI assistants in profiling bottlenecks, reducing memory footprints, and speeding up Python workloads.
LicenseRef-Proprietary 192 installs ★ 7 updated 2026-01-05
npx skills add pluginagentmarketplace/custom-plugin-python --skill python-performance -a claude-codeWhat Python Performance does
The skill feeds concrete optimization patterns directly to your coding assistant. It covers four major pillars: execution profiling via cProfile, timeit, and memory_profiler, smart collection selection like deque and bisect, memory footprint reduction using __slots__, and accelerated computing with NumPy and Numba.
Instead of generic advice, your agent applies verified patterns. It converts memory-heavy list iterations into lightweight generators and replaces slow linear lookups with O(1) set operations.
Line-by-line metrics and RAM tracking depend directly on extra third-party tools like line_profiler and memory_profiler. You must install these dependencies into your virtual environment before running the profiling benchmarks.
What it helps with
- identify execution bottlenecks using cProfile and timeit
- shrink instance memory usage with __slots__
- accelerate mathematical loops via NumPy vectorization and Numba
- avoid cache memory leaks with WeakValueDictionary
Example prompts for the agent
- Profile this data processing pipeline with cProfile and list top bottlenecks
- Convert this class hierarchy to use __slots__ to save memory
- Vectorize these nested loops using NumPy array operations
How to install Python Performance
1Skills CLI (Vercel)
npx skills add pluginagentmarketplace/custom-plugin-python --skill python-performance -a claude-code2Manually: put the files in place
~/.claude/skills/python-performance/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/python-performance/
1Skills CLI (Vercel)
npx skills add pluginagentmarketplace/custom-plugin-python --skill python-performance -a codex2Manually: put the files in place
.agents/skills/python-performance/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add pluginagentmarketplace/custom-plugin-python --skill python-performance -a cursor2Manually: put the files in place
.cursor/skills/python-performance/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install pluginagentmarketplace/custom-plugin-python skills/python-performance2Manually: put the files in place
.github/skills/python-performance/SKILL.md1Skills CLI (Vercel)
npx skills add pluginagentmarketplace/custom-plugin-python --skill python-performance -a gemini-cli2Platform CLI
gemini skills install https://github.com/pluginagentmarketplace/custom-plugin-python --path skills/python-performanceManually: put the files in place
.devin/skills/python-performance/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add pluginagentmarketplace/custom-plugin-python --skill python-performance -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about Python Performance
How to install Python Performance in Claude Code?
Run npx skills add pluginagentmarketplace/custom-plugin-python --skill python-performance -a claude-code in your terminal. The configuration is written to ~/.claude/skills/python-performance/SKILL.md.
What does Python Performance do?
It equips the agent with guidelines for benchmarking, selecting efficient data structures, tuning garbage collection, and speeding up CPU-bound code.
Which external packages are needed to use these profiling techniques?
The suggested workflows rely on external packages such as line_profiler, memory_profiler, numpy, and numba installed in your Python environment.