spec-writing

Create structured specs with goals, constraints, and acceptance criteria.

8|Updated Feb 8, 2026
One-click install
npx skills add https://github.com/kensaurus/cursor-kenji --skill spec-writing-kensaurus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: spec-writing
Source: https://github.com/kensaurus/cursor-kenji/tree/main/skills/spec-writing
Command: npx skills add https://github.com/kensaurus/cursor-kenji --skill spec-writing-kensaurus

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Spec writing for AI agents provides a clear, reusable structure to capture goals, context, constraints, success criteria, and implementation notes, reducing ambiguity and rework when planning features or agent interactions.

Core Features & Use Cases

  • Clear templates: A standard spec template to outline goals, background, requirements, acceptance criteria, and technical notes.
  • Structured planning: Guides for feature planning, PRD-style briefs, and agent session preparation.
  • Quality guardrails: Explicit edge cases, out-of-scope items, and acceptance criteria to ensure testable outputs.

Quick Start

Provide a complete spec using the template in this Skill for your feature idea.

Frequently Asked Questions about spec-writing

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

FAQPage Schema
How do I write a spec for AI agents that reduces ambiguity and rework?

Spec writing for AI agents requires a structured template capturing goals, context, constraints, and acceptance criteria. This ensures observable behavior and clear success criteria, reducing ambiguity and rework when planning features or agent interactions.

What should be included in acceptance criteria for AI feature planning?

Acceptance criteria for AI feature planning must document observable behavior, include must and should-not requirements, define edge cases, and establish clear success criteria with explicit out-of-scope items to ensure testable outputs.

Can I use a standard spec template for PRD-style briefs and agent session preparation?

A standard spec template applies to PRD-style briefs and agent session preparation by outlining goals, background, requirements, acceptance criteria, and technical notes in a reusable structure for structured planning.

How do I handle edge cases and out-of-scope items in technical documentation briefs?

Technical documentation briefs handle edge cases and out-of-scope items by applying quality guardrails that explicitly define these boundaries alongside acceptance criteria, ensuring the spec documents observable behavior and testable outputs.

Why does my feature planning fail without clear constraints and technical notes?

Feature planning fails without clear constraints and technical notes because missing context and success criteria create ambiguity. Structured spec writing captures goals and implementation notes to prevent rework in AI agent interactions.

What is the best way to structure goals and context for agent session preparation?

The best way to structure goals and context for agent session preparation is using a standard spec template that outlines goals, background, requirements, acceptance criteria, and technical notes in a precise, reusable format.