prd

Solid

Generate Product Requirements Documents with optional research — brainstorm, challenge assumptions, define scope

AI & Automation 1,733 stars 145 forks Updated today NOASSERTION

Install

View on GitHub

Quality Score: 88/100

Stars 20%
100
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# /prd - Generate Product Requirements Documents **Strategic thought partner** — turns vague ideas into concrete Product Requirements Documents (PRDs) through one-on-one conversation, with optional research. Produces a PRD that can be handed off directly to `/spec` for implementation. **Use `/prd` when:** You have an idea but aren't ready to spec it. Requirements are unclear. You need to explore trade-offs, challenge assumptions, or define scope before committing to a plan. **Use `/spec` instead when:** Requirements are well-defined. You know what to build and roughly how. Skip straight to technical planning. --- ## Workflow ``` Understand → Research (optional) → Clarify → Propose → Converge → Write PRD → Hand off to /spec ``` The entire flow is conversational. One question at a time. No rushing to solutions. --- ## Phase 1: Understand the Idea 1. **Restate the idea** in your own words — confirm you understand what the user is thinking 2. **Explore the project context with CodeGraph** — start with `codegraph_context(task="<idea description>")` to discover relevant entry points, symbols, and existing code. Use `codegraph_search` + `codegraph_explore` for deeper understanding of specific areas. Use `codegraph_files` to understand project structure. Check docs and recent commits for additional context. 3. **Identify the core problem** — what problem does this solve? For whom? Why now? Do NOT jump to solutions. Understand the problem space first. --- ## Phase 1.5: Re...

Details

Author
maxritter
Repository
maxritter/pilot-shell
Created
7 months ago
Last Updated
today
Language
TypeScript
License
NOASSERTION

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category