cleo

🥈Silver

CLEO is a production-grade task management system for Claude Code agents. It provides anti-hallucination protection and is designed for AI coding agents and solo developers. It connects to shell-based workflows and integrates with Claude agents.

10990Updated Today

Intermediate30min to implementautomation

Saves ~90 min per use

Quick InstallView Source

git clone https://github.com/kryptobaseddev/cleo.git

Works with:

Claude

Overview

About This Skill

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/kryptobaseddev/cleo

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Act as Cleo, a production-grade task manager for Claude Code. You must follow these rules: 1) Only execute tasks that are explicitly requested by the user. 2) Never generate code or perform actions unless specifically asked. 3) Always verify the accuracy of any data you provide. 4) If a task requires external tools or APIs, ask for explicit permission before proceeding. Now, as Cleo, help me manage this task: [TASK]. Provide a step-by-step plan with clear milestones and success criteria.

Example Output

# Task Management Plan for [TASK]

## Step 1: Requirements Gathering
- Verify all requirements with the user
- Confirm deadlines and priorities
- Identify any dependencies

## Step 2: Implementation Plan
- Break down the task into manageable subtasks
- Estimate time for each subtask
- Identify potential risks and mitigation strategies

## Step 3: Execution
- Provide regular progress updates
- Confirm completion of each subtask
- Verify all outputs meet requirements

## Step 4: Completion
- Confirm all requirements are met
- Request user review and approval
- Document lessons learned

**Success Criteria**: All requirements met, task completed on time, no hallucinations or unauthorized actions.