nanospec

Coordinate AI task documentation and alignment across plan, research, and execute stages.

1|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/xxih/ai-harness-zh --skill nanospec
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nanospec
Source: https://github.com/xxih/ai-harness-zh/tree/main/packages/nanospec/targets/codex/skills/nanospec
Command: npx skills add https://github.com/xxih/ai-harness-zh --skill nanospec

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

NanoSpec standardizes the intermediate-document directory and alignment workflow for AI tasks, enabling coherent spec-driven processes across planning, research, and execution.

Core Features & Use Cases

  • Standardizes task containers and alignment across tasks.
  • Enables a predictable path: init / clarify / spec / plan / execute / align / accept / summary.
  • Supports on-demand references and assets to keep work traceable and reusable.

Quick Start

Create a new task skeleton with the provided script and begin the workflow by generating the spec and plan.

Frequently Asked Questions about nanospec

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

FAQPage Schema
How do I maintain alignment across AI planning and execution workflows?

To maintain alignment across AI task workflows, you need a spec-driven process that propagates updates to outputs consistently. NanoSpec standardizes this by applying clarify, plan, and execute stages to keep documentation coherent.

What is a spec-driven workflow for AI task documentation?

A spec-driven workflow for AI tasks standardizes intermediate documents to coordinate planning, research, and execution. It establishes a predictable path through init, clarify, spec, plan, execute, align, accept, and summary stages.

How do I standardize task containers and intermediate documents for AI projects?

You standardize AI task containers by creating a task skeleton with a provided script, then generating the spec and plan. This ensures intermediate documents remain traceable and reusable across the workflow.

Can I use NanoSpec to trace research and execution stages in AI development?

Yes, NanoSpec supports tracing research and execution stages by routing through dedicated commands. It provides on-demand references and assets to keep work traceable throughout the entire process.

Does spec-driven alignment work without external dependencies?

Yes, spec-driven alignment works independently as NanoSpec requires no external dependencies. It uses internal scripts and references to orchestrate task documentation and ensure alignment updates are propagated.