Skip to content

/starting-a-design-plan

Use when beginning any design process - orchestrates gathering context, clarifying requirements, brainstorming solutions, and documenting validated designs to create implementation-ready design documents

shell
$ npx -y skills add ed3dai/ed3d-plugins --skill starting-a-design-plan --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.
  • You can call itInvoke it directly when you want it.
  • Slash command/starting-a-design-plan
How auto-invocation works

Context preview

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

Use when beginning any design process - orchestrates gathering context, clarifying requirements, brainstorming solutions, and documenting validated designs to create implementation-ready design documents

SKILL.md

starting-a-design-plan.SKILL.md
name: starting-a-design-plan
description: Use when beginning any design process - orchestrates gathering context, clarifying requirements, brainstorming solutions, and documenting validated designs to create implementation-ready design documents
user-invocable: false

Starting a Design Plan

Overview

Orchestrate the complete design workflow from initial idea to implementation-ready documentation through six structured phases: context gathering, clarification, definition of done, brainstorming, design documentation, and planning handoff.

**Core principle:** Progressive information gathering -> clear understanding -> creative exploration -> validated design -> documented plan.

**Announce at start:** "I'm using the starting-a-design-plan skill to guide us through the design process."

Quick Reference

| Phase | Key Activities | Output | |-------|---------------|--------| | **1. Context Gathering** | Ask for freeform description, constraints, goals, URLs, files | Initial context bundle | | **2. Clarification** | Invoke asking-clarifying-questions skill | Disambiguated requirements | | **3. Definition of Done** | Synthesize and confirm deliverables before brainstorming | Confirmed success criteria | | **4. Brainstorming** | Invoke brainstorming skill | Validated design (in conversation) | | **5. Design Documentation** | Invoke writing-design-plans skill | Committed design document | | **6. Planning Handoff** | Offer to invoke writing-plans skill | Implementation plan (optional) |

The Process

**REQUIRED: Create task tracker at start**

Use TaskCreate to create todos for each phase (or TodoWrite in older Claude Code versions):

  • Phase 1: Context Gathering (initial information collected)
  • (conditional) Read project design guidance (if `.ed3d/design-plan-guidance.md` exists)
  • Phase 2: Clarification (requirements disambiguated)
  • Phase 3: Definition of Done (deliverables confirmed)
  • Phase 4: Brainstorming (design validated)
  • Phase 5: Design Documentation (design written to docs/design-plans/)
  • Phase 6: Planning Handoff (implementation plan offered/created)

Use TaskUpdate to mark each phase as in_progress when working on it, completed when finished (or TodoWrite in older versions).

Phase 1: Context Gathering

**Never skip this phase.** Even if the user provides detailed information, ask for anything missing.

Use TaskUpdate to mark Phase 1 as in_progress.

**Ask the user to provide (freeform, not AskUserQuestion):**

"I need some information to start the design process. Please provide what you have:

**What are you designing?**

  • High-level description of what you want to build
  • Goals or success criteria
  • Any known constraints or requirements

**Context materials (very helpful if available):**

  • URLs to relevant documentation, APIs, or examples
  • File paths to existing code or specifications in this repository
  • Any research you've already done

**Project state:**

  • Are you starting fresh or extending existing functionality?
  • Are there existing patterns in the codebase I should follow?
  • Any architectural decisions already made?

Share whatever details you have. We'll clarify anything unclear in the next step."

**Progressive prompting:** If user already provided some of this information, acknowledge what you have and ask only for what's missing.

**Example:** "You mentioned OAuth2 integration. I have the high-level goal. To help design this effectively, I need:

  • Any constraints (regulatory, existing auth system, etc.)
  • URLs to the OAuth2 provider's documentation (if you have them)
  • Whether this is for human users, service accounts, or both"

Mark Phase 1 as completed when you have initial context.

Between Phase 1 and Phase 2: Check for Project Guidance

Before clarification, check for project-specific design guidance.

**Check if `.ed3d/design-plan-guidance.md` exists:**

Use the Read tool to check if `.ed3d/design-plan-guidance.md` exists in the session's working directory.

**If the file exists:**

1. Use TaskCreate to add: "Read project design guidance from [absolute path to .ed3d/design-plan-guidance.md]"

  • Set this task as blocked by Phase 1 (Context Gathering)
  • Update Phase 2 (Clarification) to be blocked by this new task

2. Mark the task in_progress 3. Read the file and incorporate the guidance into your understanding 4. Mark the task completed 5. Proceed to Phase 2

**If the file does not exist:**

Proceed directly to Phase 2. Do not create a task or mention the missing file.

**What project guidance provides:**

  • Domain-specific terminology to use in clarification
  • Architectural constraints or preferences
  • Technologies that are required, preferred, or forbidden
  • Stakeholders and their priorities
  • Project conventions that designs must follow

The guidance informs what questions you ask during clarification.

Phase 2: Clarification

Use TaskUpdate to mark Phase 2 as in_progress.

**REQUIRED SUB-SKILL:** Use ed3d-plan-and-execute:asking-clarifying-questions

Announce: "I'm using the asking-clarifying-questions skill to make sure I understand your requirements correctly."

The clarification skill will:

  • Use subagents to try to disambiguate before raising questions to the user
  • Disambiguate technical terms ("OAuth2" -> which flow?)
  • Identify scope boundaries ("users" -> humans? services? both?)
  • Clarify assumptions ("integrate with X" -> which version?)
  • Understand constraints ("must use Y" -> why?)

Subagents used during clarification must not dispatch additional subagents.

**Output:** Clear understanding of what user means, ready to confirm Definition of Done.

Mark Phase 2 as completed when requirements are disambiguated.

Phase 3: Definition of Done

Before brainstorming the *how*, lock in the *what*. Brainstorming explores texture and approach — it assumes the goal is already clear.

Use TaskUpdate to mark Phase 3 as in_progress.

**Synthesize the Definition of Done from context gathered so far:**

From Phases 1-2 (Co

Read more
Read it on GitHub ↗

Showing the first part of this file.

Ships withed3d-plugins

This is my collection of plugins that I use on a day-to-day basis for getting stuff done with Claude Code. Most of these are development-oriented in some way or another, but also often end up being useful for other things.

Get the whole plugin, auto-invoked