aiskillstore/marketplace / skills/2025emma/claude-cookbooks
claude-cookbooks
FlaggedClaude AI cookbooks - code examples, tutorials, and best practices for using Claude API. Use when learning Claude API integration, building Claude-powered applications, or exploring Claude capabilities.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.5 KB |
| references/CONTRIBUTING.md | markdown | 6.1 KB |
| references/README.md | markdown | 5.7 KB |
| references/capabilities.md | markdown | 2.9 KB |
| references/index.md | markdown | 981 B |
| references/main_readme.md | markdown | 5.7 KB |
| references/multimodal.md | markdown | 1.8 KB |
| references/patterns.md | markdown | 708 B |
| references/third_party.md | markdown | 1.3 KB |
| references/tool_use.md | markdown | 1.7 KB |
| scripts/memory_tool.py | script | 12.9 KB |
| skill-report.json | config | 25.9 KB |
references/tool_use.md
View on GitHubTRANSLATED CONTENT:
# Tool Use with Claude
Source: anthropics/claude-cookbooks/tool_use
## Overview
Learn how to integrate Claude with external tools and functions to extend its capabilities.
## Key Examples
### Customer Service Agent
- **Location**: `tool_use/customer_service_agent.ipynb`
- **Description**: Build an intelligent customer service agent using Claude with tool integration
- **Key Concepts**: Function calling, state management, conversation flow
### Calculator Integration
- **Location**: `tool_use/calculator_tool.ipynb`
- **Description**: Integrate external calculation tools with Claude
- **Key Concepts**: Tool definitions, parameter passing, result handling
### Memory Demo
- **Location**: `tool_use/memory_demo/`
- **Description**: Implement persistent memory for Claude conversations
- **Key Concepts**: Context management, state persistence
## Best Practices
1. **Tool Definition**: Define clear, specific tool schemas
2. **Error Handling**: Implement robust error handling for tool calls
3. **Validation**: Validate tool inputs and outputs
4. **Context**: Maintain context across tool interactions
## Common Patterns
```python
# Tool definition example
tools = [{
"name": "calculator",
"description": "Performs basic arithmetic operations",
"input_schema": {
"type": "object",
"properties": {
"operation": {"type": "string"},
"a": {"type": "number"},
"b": {"type": "number"}
},
"required": ["operation", "a", "b"]
}
}]
```
## Related Resources
- [Anthropic Tool Use Documentation](https://docs.claude.com/claude/docs/tool-use)
- [API Reference](https://docs.claude.com/claude/reference)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |