to-spec

Synthesizes conversation context into a structured spec published to the project issue tracker.

Updated May 11, 2026
One-click install
npx skills add https://github.com/cloudofgeorge/AI-hands-Engineer --skill to-spec-cloudofgeorge
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: to-spec
Source: https://github.com/cloudofgeorge/AI-hands-Engineer/tree/main/skills/engineering/to-spec
Command: npx skills add https://github.com/cloudofgeorge/AI-hands-Engineer --skill to-spec-cloudofgeorge

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a long design discussion into a formal spec (PRD) usually requires tedious re-interviewing and manual write-up. This Skill converts the current conversation and codebase understanding directly into a structured spec and publishes it to the project issue tracker without asking redundant questions. ## Core Features & Use Cases - Conversation-to-Spec Synthesis: Generates a complete spec from existing discussion context, with no user interview required. - Test Seam Planning: Identifies and proposes testing seams in the codebase, preferring existing high-level seams, and confirms them with the user before writing. - Issue Tracker Publishing: Publishes the finished spec to the project issue tracker and applies the ready-for-agent triage label automatically. - Use Case: After discussing a new feature with your AI pair programmer, invoke this Skill to produce a spec with problem statement, user stories, implementation decisions, testing decisions, and out-of-scope notes, then file it as a triaged issue. ## Quick Start Ask the agent to turn the current conversation into a spec and publish it to the issue tracker with the ready-for-agent label.

Frequently Asked Questions about to-spec

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

FAQPage Schema
How do I turn a conversation into a product spec?

Invoke this Skill after discussing a feature with the agent. It synthesizes the existing conversation and codebase context into a spec with problem statement, user stories, implementation decisions, and testing decisions, then publishes it to the issue tracker.

How do I write a PRD without re-explaining requirements?

This Skill explicitly avoids interviewing the user. It relies on what has already been discussed in the conversation, so the spec reflects prior context rather than a fresh question-and-answer session.

What sections does the generated spec template include?

The template includes Problem Statement, Solution, an extensive numbered list of User Stories, Implementation Decisions, Testing Decisions, Out of Scope, and Further Notes. Code snippets are only included when they encode a decision more precisely than prose.

What setup is required before publishing specs to the issue tracker?

The issue tracker and triage label vocabulary must be provided beforehand, typically by running the /setup-matt-pocock-skills command. Without that configuration, the Skill cannot publish or apply the ready-for-agent label.

When should I not use conversation-to-spec synthesis?

Avoid it when the conversation lacks enough context about the feature, since the Skill does not interview the user to fill gaps. In that case, hold a scoping discussion first so the spec has sufficient material to synthesize.