Python Performance Optimization
Profile slow Python code and suggest targeted speed and memory fixes
- Repository
- wshobson/agents
- Stars
- 42,095
- Licence
- MIT
- Files
- 3 files
What it does
When installed, the agent gets a guide for finding why Python code is slow or memory-hungry. It knows to measure first with profiling tools such as cProfile and memory profilers, then suggests fixes like better data structures, caching, batching I/O, or NumPy. It is mainly a set of instructions and examples the agent follows while helping you, not a tool that changes your code on its own.
Great for
- Python developers debugging slow scripts or web services
- Engineers investigating memory growth or latency bottlenecks
- Teams wanting a checklist of common Python performance pitfalls
Skip it if
- Non-programmers, since the advice assumes working Python code and profiler output
- Projects in other languages, because the guidance is Python-specific
- Production systems to be profiled without care, since profiling live code can add overhead and the skill's own advice to profile production code (e.g. with py-spy) should be done deliberately
Try asking
- “My Python data pipeline takes 20 minutes. Help me find the bottleneck with cProfile.”
- “This Flask endpoint is slow under load, what should I check first?”
- “Our Python worker's memory keeps growing. Help me track down the leak.”
- “Suggest ways to speed up this loop that processes a million rows.”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 3 original files, the MIT licence and an attribution note.
python-performance-optimization.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip python-performance-optimization.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip python-performance-optimization.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Give the agent real profiler output or a reproducible slow case so it can measure rather than guess.
- Ask for one change at a time and re-measure to confirm each optimization helps.
- Review any suggested code before running it against production data or systems.
What's inside
- references/advanced-patterns.md
- references/details.md
- SKILL.md
Redistributed unmodified from wshobson/agents under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.