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
What this skill does
# 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?)
**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 (Context Gathering and Clarification), you should be able to infer or extract:
- What the deliverables are (what gets built/changed)
- What success looks like (how we know it's done)
- What's explicitly out of scope
**If the Definition of Done is clear:**
State it back to the user and confirm using AskUserQuestion:
```
Question: "Before we explore approaches, let me confirm what success looks like:"
Options:
- "Yes, that's right" (Definition of Done is accurate)
- "Needs adjustment" (User will clarify what's missing or wrong)
```
Present the Definition of Done as a brief statement (2-4 sentences) covering:
- Primary deliverable(s)
- Success criteria
- Key exclusions (if any were discussed)
**If the Definition of Done is unclear:**
Ask targeted questions to nail it down. Use AskUserQuestion when there are discrete options, or open-ended questions when you need the user to describe their vision.
Examples of clarifying questions:
- "What's the primary deliverable here — is it [X] or [Y]?"
- "How will you know this is done? What would you test or demonstrate?"
- "You mentioned [feature]. Is that in scope for this design, or a future addition?"
**Do not proceed to brainstorming until Definition of Done is confirmed.**
#### Create Design Document Immediately After Confirmation
**REQUIRED:** Once the user confirms the Definition of Done, create the design document file immediately. This captures the DoD at full fidelity before brainstorming begins.
##### Step 1: Get Design Plan Name
The slug becomes part of all acceptance criteria identifiers (e.g., `my-feature.AC1.1`) and appears in test names. Ask the user to choose it explicitly.
**Generate 2-3 suggested slugs** based on the conversation context. Good slugs are:
- Lowercase with hyphens (no spaces, underscores, or special characters)
- **Terse but unambiguous** — prefer short forms that don't create confusion (e.g., `authn` not `authentication`, but not `auth` since that's ambiguous with `authz`)
- Recognizable months later
**Use AskUserQuestion:**
```
Question: "What should we call this design plan? The name becomes the prefix for all acceptance criteria (e.g., `{slug}.AC1.1`) and appears in test names.
If you have a ticketing system, you can use the ticket name (e.g., PROJ-1234)."
Options:
- "[auto-generated-slug-1]" (e.g., "oauth2-svc-authn")
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.