to-prd

Generate a PRD from conversation context and publish it to GitHub or Linear.

Updated Jan 28, 2026
One-click install
npx skills add https://github.com/ttphats/project-detedxs26 --skill to-prd-ttphats
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: to-prd
Source: https://github.com/ttphats/project-detedxs26/tree/main/.augment/skills/custom/mattpocock/to-prd
Command: npx skills add https://github.com/ttphats/project-detedxs26 --skill to-prd-ttphats

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a long planning conversation into a structured Product Requirements Document is tedious and error-prone. This Skill synthesizes the existing conversation context and codebase understanding into a complete PRD and publishes it directly to the project issue tracker, without re-interviewing the user. ## Core Features & Use Cases - Context Synthesis: Converts the current conversation and repository exploration into a structured PRD covering problem statement, solution, user stories, implementation decisions, testing decisions, and scope. - Test Seam Planning: Identifies existing architectural seams for testing before writing the PRD and confirms them with the user. - Issue Tracker Publishing: Publishes the finished PRD to GitHub or Linear via MCP and applies the ready-for-agent triage label. - Use Case: After discussing a new seat-locking feature for a ticketing app, ask the agent to produce a PRD; it explores the codebase, drafts extensive user stories, and posts the PRD as a GitHub issue ready for an implementation agent. ## Quick Start Ask the agent to turn the current conversation into a PRD and publish it to the project issue tracker.

Frequently Asked Questions about to-prd

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

FAQPage Schema
How do I create a PRD from an AI conversation?▼

Ask the agent to turn the current conversation into a PRD. The Skill synthesizes the existing context and codebase exploration into a structured document with problem statement, user stories, and implementation decisions, without asking additional interview questions.

How to publish a PRD to GitHub or Linear automatically?▼

The Skill publishes the finished PRD through GitHub MCP or Linear MCP integrations. If the tracker is not configured, it asks for the tracker type and credentials, then posts the PRD and applies the ready-for-agent triage label.

What sections does a generated PRD include?▼

The PRD template includes a problem statement, solution, an extensive numbered list of user stories, implementation decisions, testing decisions, out-of-scope items, and further notes. It avoids specific file paths so the document stays accurate as code evolves.

Does the PRD skill require existing codebase context?▼

Yes, it explores the repository first to understand the current state, uses the project's domain glossary vocabulary, and respects existing ADRs. It also identifies test seams in the architecture and confirms them with the user before writing.

When should I not use conversation-to-PRD generation?▼

Avoid it when the feature is still ambiguous or the conversation lacks enough substance, since the Skill deliberately does not interview the user. In those cases, gather requirements through discussion first, then generate the PRD.