todo-manager

jawwad-ali's avatarfrom jawwad-ali

Manage Todo operations (Create, Read, Update, Delete) using SQLModel and Postgres. Use when the user wants to organize tasks.

⭐1stars🔀0forks📁View on GitHub🕐Updated Jan 2, 2026
[Project Management]

When & Why to Use This Skill

The Todo Management Skill is a high-performance AI agent tool designed to streamline task organization through robust CRUD (Create, Read, Update, Delete) operations. Built with SQLModel and PostgreSQL, it provides a persistent, asynchronous backend for managing task lifecycles within AI-driven workflows. It ensures data integrity and operational efficiency by utilizing modern Python standards like FastAPI and the uv package manager, making it an essential component for developers building sophisticated productivity applications.

Use Cases

  • Natural Language Task Creation: Seamlessly convert user prompts like 'Add a meeting with the design team tomorrow at 10 AM' into structured database entries.
  • Persistent Task Lifecycle Management: Track the progress of various projects by updating task statuses, descriptions, and deadlines with full database persistence.
  • Asynchronous Task Retrieval: Efficiently query and list pending or completed tasks to provide users with real-time updates on their productivity.
  • Automated Task Cleanup: Identify and remove obsolete or completed tasks to maintain a clean and focused workspace.
nametodo-manager
descriptionManage Todo operations (Create, Read, Update, Delete) using SQLModel and Postgres. Use when the user wants to organize tasks.

Todo Management Skill

Executive Summary

This skill governs the lifecycle of Todos in the "Advanced AI-Todo" application. It ensures all operations are persistent, async-ready, and compliant with the project's technical mandates.

Operational Mandates

  1. Environment First: ALWAYS run source .venv/bin/activate before any backend execution or uv command.
  2. Dependency Management: Use uv for all package operations. Never use raw pip.
  3. Connectivity: Connect to Gemini 2.5 Flash using the AsyncOpenAI class.
  4. Docs Validation: Before proposing code changes to SQLModel or FastAPI, call the context-7 MCP server to verify the latest async patterns.

Execution Workflow

  • Step 1: Planning: Check SKILLS/SKILL.md for current project state.
  • Step 2: Documentation: Query MCP context-7 for "FastAPI SQLModel Postgres async best practices".
  • Step 3: Implementation:
    • Use AsyncOpenAI for the chatbot logic.
    • Ensure Postgres connection strings are pulled from environment variables.
    • Implement CRUD operations as async functions.
  • Step 4: Verification: Run tests using uv run pytest.

Examples

  • Input: "Create a task to buy milk."
  • Action: Invoke todo-manager → Search MCP for SQLModel patterns → Generate async code to insert into Postgres → Confirm with Gemini 2.5 Flash.