Skip to content
Agent Memory
Skill

/pdd

Transform a rough idea into a detailed design document and implementation plan.

BOOST
From plugin
rho
37328 skills
Install
$ npx -y skills add mikeyobrien/rho --skill pdd --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/pdd

Context preview

The summary Claude sees to decide when to auto-load this skill.

Transform a rough idea into a detailed design document and implementation plan.

SKILL.md

pdd.SKILL.md
name: pdd
description: Transform a rough idea into a detailed design document and implementation plan.
kind: sop

Prompt-Driven Development

Overview

This sop guides you through the process of transforming a rough idea into a detailed design document with an implementation plan and todo list. It follows the Prompt-Driven Development methodology to systematically refine your idea, conduct necessary research, create a comprehensive design, and develop an actionable implementation plan. The process is designed to be iterative, allowing movement between requirements clarification and research as needed.

Parameters

  • **rough_idea** (required): The initial concept or idea you want to develop into a detailed design
  • **project_name** (optional): A short, descriptive name for the project. If not provided, will be generated from the rough idea
  • **project_dir** (optional, default: ".agents/planning/{project_name}"): The base directory where all project files will be stored

**Constraints for parameter acquisition:**

  • You MUST ask for all required parameters upfront in a single prompt rather than one at a time
  • You MUST support multiple input methods including:
  • Direct input: Text provided directly in the conversation
  • File path: Path to a local file containing the rough idea
  • URL: Link to an internal resource (e.g., Quip doc, wiki page)
  • Other methods: You SHOULD be open to other ways the user might want to provide the idea
  • You MUST use appropriate tools to access content based on the input method
  • You MUST confirm successful acquisition of all parameters before proceeding
  • If project_name is not provided, You MUST generate a short kebab-case name from the rough idea, prefixed with the current date in YYYY-MM-DD format (e.g., "2026-01-30-template-manager", "2026-01-30-auth-system")
  • You SHOULD save the acquired rough idea to a consistent location for use in subsequent steps
  • You MUST NOT overwrite the existing project directory because this could destroy previous work and cause data loss
  • You MUST ask for project_dir if it is not given and the generated default directory already exists and has contents from previous iteration

Steps

1. Create Project Structure

Set up a directory structure to organize all artifacts created during the process.

**Constraints:**

  • You MUST create the specified project directory if it doesn't already exist
  • You MUST create the following files:
  • {project_dir}/rough-idea.md (containing the provided rough idea)
  • {project_dir}/idea-honing.md (for requirements clarification)
  • You MUST include a **Connections** section in rough-idea.md that links to:
  • idea-honing.md: `[[idea-honing.md]]` (will be populated during requirements clarification)
  • You MUST create the following subdirectories:
  • {project_dir}/research/ (directory for research notes)
  • {project_dir}/design/ (directory for design documents)
  • {project_dir}/implementation/ (directory for implementation plans)
  • You MUST notify the user when the structure has been created
  • You MUST prompt the user to add all project files to Kiro's context using the command: `/context add {project_dir}/**/*.md`
  • You MUST explain that this will ensure all project files remain in context throughout the process

2. Initial Process Planning

Determine the initial approach and sequence for requirements clarification and research.

**Constraints:**

  • You MUST ask the user if they prefer to:
  • Start with requirements clarification (default)
  • Start with preliminary research on specific topics
  • Provide additional context or information before proceeding
  • You MUST adapt the subsequent process based on the user's preference
  • You MUST explain that the process is iterative and the user can move between requirements clarification and research as needed
  • You MUST wait for explicit user direction before proceeding to any subsequent step
  • You MUST NOT automatically proceed to requirements clarification or research without user confirmation because this could lead the process in a direction the user doesn't want

3. Requirements Clarification

Guide the user through a series of questions to refine the initial idea and develop a thorough specification.

**Constraints:**

  • You MUST create an empty {project_dir}/idea-honing.md file if it doesn't already exist
  • You MUST add a **Connections** section to idea-honing.md that includes:
  • Link to rough-idea.md: `[[rough-idea.md]]`
  • You MUST ask ONLY ONE question at a time and wait for the user's response before asking the next question
  • You MUST NOT list multiple questions for the user to answer at once because this overwhelms users and leads to incomplete responses
  • You MUST NOT pre-populate answers to questions without user input because this assumes user preferences without confirmation
  • You MUST NOT write multiple questions and answers to the idea-honing.md file at once because this skips the interactive clarification process
  • You MUST follow this exact process for each question:

1. Formulate a single question 2. Append the question to {project_dir}/idea-honing.md 3. Present the question to the user in the conversation 4. Wait for the user's complete response, which may require brief back-and-forth dialogue across multiple turns. 5. Once you have their complete response, append the user's answer (or final decision) to {project_dir}/idea-honing.md 6. Only then proceed to formulating the next question

  • You MAY suggest possible answers when asking a question, but MUST wait for the user's actual response
  • You MUST format the idea-honing.md document with clear question and answer sections
  • You MUST include the final chosen answer in the answer section
  • You MAY include alternative options that were considered before the final decision
  • You MUST ensure you have the user's complete response before recording it and moving to the next question
  • You MUST continue asking questions until sufficient detail
Read more
Ships withrho

An always-on personal AI operator that: stays running in the background, remembers context across sessions, and checks in proactively on a schedule. Runs on macOS, Linux, and Android (plus iPhone/iPad via SSH). Built on pi coding agent. Terminal demo

Get the whole plugin
Stats
373
Stars
29
Forks
Active
Maintenance
TypeScript
Language
MIT
License
16d ago
Last commit
8mo ago
Created
3h ago
Added

Repo: mikeyobrien/rho

Other skills on rho.

device
Skill

device

Device controls — vibration, torch, volume, battery status, toast messages. Use for haptic feedback, flashlight, or quick status…

@mikeyobrien@mikeyobrienInstall Skill
dialog
Skill

dialog

Show interactive dialogs for user input — text, confirmations, choices, date/time pickers. Use when you need user input beyond…

@mikeyobrien@mikeyobrienInstall Skill