---
name: "crewai-custom-tools-memory"
description: "Equip CrewAI agents with custom Python tools and short/long-term memory systems."
metadata:
  author: "CrewAI"
  version: "1.0.0"
  runtime_compatibility:
    - "codex"
    - "claude-code"
    - "cursor"
    - "windsurf"
triggers:
  - "create custom tool crewai"
  - "enable memory in crewai"
  - "bind pydantic tool crewai"
permissions:
  fs_read: true
  fs_write: "workspace"
  shell_exec: false
  net_access: false
---

# CrewAI Custom Tools & Embeddings Memory

Integrates custom tools with CrewAI @tool decorator, Pydantic input schemas, ChromaDB embeddings memory, and entity memory tracking across execution sessions.

## When to Invoke
Invoke this skill whenever you need to:
- create custom tool crewai
- enable memory in crewai
- bind pydantic tool crewai

## Execution SOP & Rules
1. Define custom tools with the @tool decorator and clear docstring descriptions.
2. Use Pydantic models for tool input arguments to ensure strict validation.
3. Enable memory=True on Crew initialization to activate ChromaDB memory vectors.
4. Handle tool execution errors gracefully by returning descriptive error strings to the agent.

## Verification Checklist
- Run local linting, syntax validation, and type-checks before reporting completion.
- Ensure all created or modified files adhere to workspace boundaries and avoid uncommitted secrets.
- Verify tests or build commands exit cleanly with return code 0.