A robust, dependency-free Python library for orchestrating and validating multi-step AI agent tasks with built-in safety checks.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install task-panner-validator
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install task-panner-validator using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Task Planner and Validator?
Task Planner and Validator provides a structured framework for AI agents to plan, validate, and execute complex sequences of actions. Built with a focus on safety and reliability, this tool ensures that every step an agent takes is verified against potential risks before execution.
By integrating this library into your Openclaw Skills, you can create highly dependable autonomous systems that handle errors gracefully and provide full transparency. It features a lightweight design using only the Python standard library, making it an ideal choice for developers who need to implement secure task orchestration without the overhead of heavy dependencies.
Task Planner and Validator Use Cases
- Orchestrating multi-step API interactions and sequential data fetching.
- Building secure data pipelines that require extraction, transformation, and loading (ETL).
- Automating system maintenance tasks like database backups and schema migrations with rollback support.
- Developing autonomous agents that require human-in-the-loop approval for sensitive operations.
How Task Planner and Validator Works
- Initialize the TaskPlanner and define a custom executor function to handle the specific logic for different actions.
- Define a structured plan consisting of multiple steps, including descriptions, action IDs, parameters, and expected outputs.
- Run the validation engine to detect dangerous operations, sensitive paths, or integrity issues within the proposed plan.
- Obtain manual or automatic approval for the plan to transition it from a draft to an executable state.
- Execute the plan step-by-step, with options for dry runs, configurable retry logic, and error handling.
- Review the execution summary and checkpoint history to verify success or diagnose failures.
Task Planner and Validator Setup
# Clone the repository
git clone https://github.com/cerbug45/task-planner-validator.git
cd task-planner-validator
# Run tests to verify installation
python test_basic.py
# Explore the example implementation
python examples.py
Task Planner and Validator Data Schema & Taxonomy
The skill organizes tasks into JSON-compatible plan objects. Each step within a plan follows a specific metadata taxonomy:
| Field | Requirement | Description |
|---|---|---|
description |
Required | Human-readable explanation of the step |
action |
Required | Identifier used by the executor to route logic |
parameters |
Required | Dictionary of inputs for the action |
expected_output |
Required | String describing the target result |
safety_check |
Optional | Boolean to enable/disable safety warnings (default: True) |
rollback_possible |
Optional | Boolean defining if the step supports undos (default: True) |
max_retries |
Optional | Number of retry attempts on failure (default: 3) |
Task Planner and Validator Advanced Features
- Automated safety validation that identifies dangerous operations and sensitive file paths.
- Dry run mode to simulate complex execution lifecycles without side effects.
- Checkpoint system that automatically manages state for rollback-capable steps.
- Persistence layer for saving, loading, and verifying the integrity of plans via JSON.
- Execution history tracking with timestamps and status logs for every step.
- Customizable validation rules to extend safety checks for specific Openclaw Skills environments.
SKILL.md
Loading
Related Openclaw Skills
Email Formatter
A professional enhancement tool that transforms rough email drafts into polished, secure, and well-formatted business communication.
ClawHub
ClawHub is a secure communication protocol that enables AI agents to exchange messages via end-to-end encryption and verified identities.
AI Wallet Payment System
A secure Python-based skill for AI agents to manage Ethereum wallets and perform blockchain transactions with multi-factor authentication.
AI Agent Tools
A lightweight Python utility library providing essential tools for AI agents to manage files, process text, and handle session memory.
WhatsApp Intelligent Context Manager
An AI-powered context management system that provides WhatsApp agents with instant customer history, sentiment analysis, and priority-based response suggestions.
Capital Equipment Platform
A comprehensive AI-driven tool for discovering, booking, and managing scientific research equipment across global core facilities.
Featured*
