task-decomposer

Name: task-decomposer
Availability: InStock
Author: whichguy

Generate validated plan.json task plans from intentions and execution context.

1|Updated Jun 23, 2026

Search Tags:#state management #task execution #task planning #intent decomposition #plan.json schema

Ready to run

npx skills add https://github.com/whichguy/hermes-skills-marketplace --skill task-decomposer-whichguy

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: task-decomposer
Source: https://github.com/whichguy/hermes-skills-marketplace/tree/main/skills/task-decomposer
Command: npx skills add https://github.com/whichguy/hermes-skills-marketplace --skill task-decomposer-whichguy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of creating detailed task plans for complex intentions, providing a clear path towards achieving goals with traceable requirements and verifiable outcomes.

Core Features & Use Cases

Task Planning: Generate a validated task plan.json from an immutable intent and accumulated state.
State Management: Keep track of established facts, known gaps, and dead ends in the state.
Task Execution: Use a driver to execute each task and record results.
Use Case: When an AI agent needs to decompose a high-level intention (like replacing a live system without downtime) into actionable steps, this skill can create a detailed plan with a defined set of tasks that can be executed sequentially.

Quick Start

Plan tasks for an intention: 'hermes -z /opt/hermes/.venv/bin/python scripts/envelope.py plan_prompt'

Frequently Asked Questions about task-decomposer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate a task plan from a complex intent for automated execution?▼

To generate a task plan, you provide an immutable intent and accumulated state to the system, which then outputs a validated plan.json file containing sequential, actionable steps for automated systems or manual agent operations.

How does intent decomposition handle state management during task planning?▼

Intent decomposition handles state management by tracking established facts, known gaps, and dead ends within the state, ensuring that the generated task plan remains traceable and accounts for missing evidence during execution.

What is the best way to break down a high-level intention into verifiable tasks?▼

The best way to break down a high-level intention is to use an automated task planner that creates a validated plan.json schema, ensuring every step has traceable requirements and verifiable outcomes for your specific workflow.

Do I need Python and file operation permissions to execute generated task plans?▼

Yes, you need Python support and file operation permissions to save and execute tasks, because the system requires an execution context to run the driver that processes each task and records the results.

Can I use this task planning approach for replacing a live system without downtime?▼

Yes, you can use this task planning approach for replacing a live system without downtime by decomposing the high-level intention into a detailed, sequential plan.json that an AI agent can execute step by step.

What are the limitations of using a plan.json schema for task execution?▼

A limitation of using a plan.json schema is that it requires an explicit execution context and a dedicated driver to execute each task and record results, making it less suitable for environments without file operation permissions.