A sandboxed execution environment for when you actually need to run code, not just show it. Supports Python (200+ preinstalled libraries including pandas, matplotlib, scikit-learn), JavaScript, and TypeScript. Use it to debug snippets, test package installations, prototype algorithms, or verify calculations. The key distinction: this is for testing and experimentation, not production output. If you're making a chart for a presentation or a formatted Excel report, reach for the specialized visual-design or excel-spreadsheets skills instead. Files persist within your session and can be saved to the shared workspace. Think of it as a Python REPL with teeth, not a document generator.
npx -y skills add aws-samples/sample-strands-agent-with-agentcore --skill code-interpreter --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot