specification-writing

Write technical specifications with context, rationale, and open questions for implementation.

4.7k|374|Updated Mar 16, 2023
One-click install
npx skills add https://github.com/EpicenterHQ/epicenter --skill specification-writing
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: specification-writing
Source: https://github.com/EpicenterHQ/epicenter/tree/main/.agents/skills/specification-writing
Command: npx skills add https://github.com/EpicenterHQ/epicenter --skill specification-writing

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Write technical specifications that give agents enough context to implement features while leaving room for autonomous research and decision-making.

Core Features & Use Cases

  • Provide context and rationale to explain why a feature is needed and what it should achieve.
  • Document research, decisions, and assumptions to enable informed implementation and future iterations.
  • Leave open questions and design gaps to empower agents to spawn sub-tasks and continue autonomous work.

Quick Start

Draft a concise specification for a feature, including purpose, constraints, surrounding assumptions, and a plan for validating success.

Frequently Asked Questions about specification-writing

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

FAQPage Schema
How do I write technical specifications that autonomous agents can understand for feature implementation?

To write technical specifications for autonomous agents, document the feature purpose, constraints, assumptions, and validation plans while leaving open questions to enable autonomous research and iterative implementation decisions.

What should be included in planning docs for autonomous agents to implement complex features?

Planning docs for autonomous agents should include context and rationale for the feature, documented research and architectural decisions, assumptions, and identified design gaps to empower agents to spawn sub-tasks during implementation.

How do I document architecture decisions to guide autonomous agents during development?

Document architecture decisions by recording the research, rationale, and assumptions that inform the choice, ensuring autonomous agents have enough context to execute implementation plans and make informed design decisions.

Can I leave open questions in feature specs for agents to resolve autonomously?

Yes, feature specs can leave open questions and design gaps intentionally to empower autonomous agents to spawn sub-tasks, conduct research, and continue iterative work without requiring constant manual input.

What is the best way to structure research notes for autonomous agent feature planning?

Structure research notes by drafting a concise specification that covers the feature purpose, constraints, surrounding assumptions, and a clear plan for validating success to guide autonomous agents effectively.

When do I need to write detailed implementation guides for autonomous agents?

Detailed implementation guides are needed when working across complex projects where autonomous agents require documented rationale, research notes, and extensible technical specifications to implement features accurately and iteratively.