Does it provide criteria for task completion?

Every generated task includes specific acceptance criteria, test scenarios, and edge cases derived directly from the source specification document.

What is 'Context Grouping' in this context?

Context Grouping is a feature that organizes tasks based on token estimation, ensuring the AI agent doesn't lose track of information due to context window limits during implementation.

What document types are supported for analysis?

It is optimized for Product Requirement Documents (PRDs), Technical Specifications, and Design Documents, specifically in Markdown format.

How does this skill handle large specification documents?

The skill parses documents for explicit and implicit requirements, then uses a specialized algorithm to group tasks into context windows that fit within AI model token limits.

Can it identify dependencies between tasks automatically?

Yes, it maps hard dependencies (blockers), soft dependencies, and resource dependencies to create a logical execution graph.

Spec Task Management

Name: Spec Task Management
Author: sequenzia

bysequenzia

•

生産性とワークフロー

Transforms complex specification documents into structured, atomic task lists optimized for AI coding agents.

概要

Spec Task Management bridges the gap between high-level documentation and executable code by automatically parsing PRDs, technical specs, and design documents. It intelligently decomposes requirements into independent, testable tasks while mapping complex hard and soft dependencies. Unique to this skill is its AI-optimized context grouping, which organizes tasks into manageable token-sized buckets to prevent context overflow during long development sessions. By calculating priorities and execution phases, it enables AI agents to work autonomously or in parallel with high precision.

主な機能

Atomic Requirement Decomposition: Breaks down large documents into single-responsibility tasks with unique IDs.
Priority & Phase Calculation: Determines optimal execution order based on risk, complexity, and dependency depth.
AI-Optimized Context Grouping: Bin-packs tasks into groups that fit within AI model token limits to ensure efficient processing.
Automated Testing Criteria: Generates specific acceptance criteria and edge cases for every task derived from the spec.
Intelligent Dependency Mapping: Automatically identifies hard, soft, and resource-based task dependencies.
1 GitHub stars

ユースケース

Organizing large-scale feature development into context-aware phases for multi-session AI handoffs.
Converting a lengthy Product Requirement Document (PRD) into a structured backlog for an AI coding agent.
Managing complex system migrations by identifying the critical path and hard dependencies across multiple modules.

概要

主な機能

Atomic Requirement Decomposition: Breaks down large documents into single-responsibility tasks with unique IDs.
Priority & Phase Calculation: Determines optimal execution order based on risk, complexity, and dependency depth.
AI-Optimized Context Grouping: Bin-packs tasks into groups that fit within AI model token limits to ensure efficient processing.
Automated Testing Criteria: Generates specific acceptance criteria and edge cases for every task derived from the spec.
Intelligent Dependency Mapping: Automatically identifies hard, soft, and resource-based task dependencies.
1 GitHub stars

ユースケース

Organizing large-scale feature development into context-aware phases for multi-session AI handoffs.
Converting a lengthy Product Requirement Document (PRD) into a structured backlog for an AI coding agent.
Managing complex system migrations by identifying the critical path and hard dependencies across multiple modules.