Feature Design Assistant

Transform rough ideas into production-ready feature specs

✨ The solution you've been looking for

Verified
Tested and verified by our team
16036 Stars

Turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when planning new features, designing architecture, or making significant changes to the codebase.

feature-design software-architecture requirements-gathering collaborative-planning technical-specs project-management design-patterns development-workflow
Repository

See It In Action

Interactive preview & real-world examples

Live Demo
Skill Demo Animation

AI Conversation Simulator

See how users interact with this skill

User Prompt

I need to design a user notification system for our web app. It should support email, SMS, and in-app notifications with user preferences.

Skill Processing

Analyzing request...

Agent Response

Complete feature specification with architecture diagrams, API design, data models, testing strategy, and prioritized implementation tasks

Quick Start (3 Steps)

Get up and running in minutes

1

Install

claude-code skill install feature-design-assistant

claude-code skill install feature-design-assistant
2

Config

3

First Trigger

@feature-design-assistant help

Commands

CommandDescriptionRequired Args
@feature-design-assistant new-feature-planningDesign a complex feature from initial concept to implementation-ready specsNone
@feature-design-assistant architecture-decision-makingEvaluate multiple technical approaches and select the best solutionNone
@feature-design-assistant legacy-system-enhancementPlan backwards-compatible improvements to existing featuresNone

Typical Use Cases

New Feature Planning

Design a complex feature from initial concept to implementation-ready specs

Architecture Decision Making

Evaluate multiple technical approaches and select the best solution

Legacy System Enhancement

Plan backwards-compatible improvements to existing features

Overview

Feature Design Assistant

Help turn ideas into fully formed designs and specs through structured information gathering and collaborative validation.

Announce at start: “I’m using the feature-design-assistant skill to design this feature.”

Phase 1: Context Discovery

First, explore the codebase to understand:

  • Project structure and tech stack
  • Existing patterns and conventions
  • Related features or modules
  • Recent changes in relevant areas

Phase 2: Structured Information Gathering

Use AskUserQuestion to batch collect information efficiently. Each call can ask up to 4 questions.

Round 1: Core Requirements (4 questions)

 1{
 2  "questions": [
 3    {
 4      "question": "What is the primary goal of this feature?",
 5      "header": "Goal",
 6      "multiSelect": false,
 7      "options": [
 8        { "label": "New Functionality", "description": "Add entirely new capability to the system" },
 9        { "label": "Enhancement", "description": "Improve or extend existing feature" },
10        { "label": "Bug Fix", "description": "Fix incorrect behavior or issue" },
11        { "label": "Refactoring", "description": "Improve code quality without changing behavior" }
12      ]
13    },
14    {
15      "question": "Who are the primary users of this feature?",
16      "header": "Users",
17      "multiSelect": true,
18      "options": [
19        { "label": "End Users", "description": "External customers using the product" },
20        { "label": "Admins", "description": "Internal administrators or operators" },
21        { "label": "Developers", "description": "Other developers using APIs or SDKs" },
22        { "label": "System", "description": "Automated processes or background jobs" }
23      ]
24    },
25    {
26      "question": "What is the expected scope of this feature?",
27      "header": "Scope",
28      "multiSelect": false,
29      "options": [
30        { "label": "Small (1-2 days)", "description": "Single component, limited changes" },
31        { "label": "Medium (3-5 days)", "description": "Multiple components, moderate complexity" },
32        { "label": "Large (1-2 weeks)", "description": "Cross-cutting concerns, significant changes" },
33        { "label": "Unsure", "description": "Need to explore further to estimate" }
34      ]
35    },
36    {
37      "question": "Are there any hard deadlines or constraints?",
38      "header": "Timeline",
39      "multiSelect": false,
40      "options": [
41        { "label": "Urgent", "description": "Need this ASAP, within days" },
42        { "label": "This Sprint", "description": "Should be done within current sprint" },
43        { "label": "Flexible", "description": "No hard deadline, quality over speed" },
44        { "label": "Planning Only", "description": "Just designing now, implementing later" }
45      ]
46    }
47  ]
48}

Round 2: Technical Requirements (4 questions)

 1{
 2  "questions": [
 3    {
 4      "question": "Which layers of the system will this feature touch?",
 5      "header": "Layers",
 6      "multiSelect": true,
 7      "options": [
 8        { "label": "Data Model", "description": "Database schema, models, migrations" },
 9        { "label": "Business Logic", "description": "Services, domain logic, rules" },
10        { "label": "API", "description": "REST/GraphQL endpoints, contracts" },
11        { "label": "UI", "description": "Frontend components, user interface" }
12      ]
13    },
14    {
15      "question": "What are the key quality requirements?",
16      "header": "Quality",
17      "multiSelect": true,
18      "options": [
19        { "label": "High Performance", "description": "Must handle high load or be very fast" },
20        { "label": "Strong Security", "description": "Sensitive data, auth, access control" },
21        { "label": "High Reliability", "description": "Cannot fail, needs redundancy" },
22        { "label": "Easy Maintenance", "description": "Needs to be easily understood and modified" }
23      ]
24    },
25    {
26      "question": "How should errors be handled?",
27      "header": "Errors",
28      "multiSelect": false,
29      "options": [
30        { "label": "Fail Fast", "description": "Stop immediately on any error" },
31        { "label": "Graceful Degrade", "description": "Continue with reduced functionality" },
32        { "label": "Retry & Recover", "description": "Automatic retry with recovery logic" },
33        { "label": "Context Dependent", "description": "Different strategies for different cases" }
34      ]
35    },
36    {
37      "question": "What testing approach is preferred?",
38      "header": "Testing",
39      "multiSelect": false,
40      "options": [
41        { "label": "TDD (Recommended)", "description": "Write tests first, then implementation" },
42        { "label": "Test After", "description": "Implement first, add tests after" },
43        { "label": "Minimal Tests", "description": "Only critical path testing" },
44        { "label": "No Tests", "description": "Skip testing for this feature" }
45      ]
46    }
47  ]
48}

Round 3: Integration & Dependencies (4 questions)

 1{
 2  "questions": [
 3    {
 4      "question": "Does this feature need external integrations?",
 5      "header": "Integrations",
 6      "multiSelect": true,
 7      "options": [
 8        { "label": "Database", "description": "New tables, queries, or migrations" },
 9        { "label": "External APIs", "description": "Third-party service calls" },
10        { "label": "Message Queue", "description": "Async processing, events" },
11        { "label": "None", "description": "No external integrations needed" }
12      ]
13    },
14    {
15      "question": "Are there dependencies on other features or teams?",
16      "header": "Dependencies",
17      "multiSelect": true,
18      "options": [
19        { "label": "Auth System", "description": "User authentication or authorization" },
20        { "label": "Other Features", "description": "Depends on features being developed" },
21        { "label": "External Team", "description": "Needs input from another team" },
22        { "label": "None", "description": "Fully independent feature" }
23      ]
24    },
25    {
26      "question": "How should we handle backwards compatibility?",
27      "header": "Compat",
28      "multiSelect": false,
29      "options": [
30        { "label": "Must Maintain", "description": "Cannot break existing clients" },
31        { "label": "Version API", "description": "Create new version, deprecate old" },
32        { "label": "Breaking OK", "description": "Can make breaking changes" },
33        { "label": "Not Applicable", "description": "New feature, no existing users" }
34      ]
35    },
36    {
37      "question": "What documentation is needed?",
38      "header": "Docs",
39      "multiSelect": true,
40      "options": [
41        { "label": "API Docs", "description": "Endpoint documentation" },
42        { "label": "User Guide", "description": "How-to for end users" },
43        { "label": "Dev Guide", "description": "Technical implementation details" },
44        { "label": "None", "description": "No documentation needed" }
45      ]
46    }
47  ]
48}

Round 4: Clarifying Questions (Context-Dependent)

Based on previous answers, ask follow-up questions. Examples:

If UI layer selected:

 1{
 2  "questions": [
 3    {
 4      "question": "What UI framework/approach should we use?",
 5      "header": "UI Tech",
 6      "multiSelect": false,
 7      "options": [
 8        { "label": "React", "description": "React components with hooks" },
 9        { "label": "Vue", "description": "Vue.js components" },
10        { "label": "Server-Side", "description": "Server-rendered HTML templates" },
11        { "label": "Existing Pattern", "description": "Follow current project conventions" }
12      ]
13    }
14  ]
15}

If High Security selected:

 1{
 2  "questions": [
 3    {
 4      "question": "What security measures are required?",
 5      "header": "Security",
 6      "multiSelect": true,
 7      "options": [
 8        { "label": "Input Validation", "description": "Strict input sanitization" },
 9        { "label": "Rate Limiting", "description": "Prevent abuse and DoS" },
10        { "label": "Audit Logging", "description": "Track all sensitive actions" },
11        { "label": "Encryption", "description": "Encrypt data at rest/transit" }
12      ]
13    }
14  ]
15}

Phase 3: Approach Exploration

After gathering requirements, propose 2-3 approaches:

 1## Approach Options
 2
 3### Option A: [Name] (Recommended)
 4**Pros:** ...
 5**Cons:** ...
 6**Best for:** ...
 7
 8### Option B: [Name]
 9**Pros:** ...
10**Cons:** ...
11**Best for:** ...
12
13### Option C: [Name]
14**Pros:** ...
15**Cons:** ...
16**Best for:** ...

Use AskUserQuestion to confirm approach:

 1{
 2  "questions": [
 3    {
 4      "question": "Which approach would you like to proceed with?",
 5      "header": "Approach",
 6      "multiSelect": false,
 7      "options": [
 8        { "label": "Option A (Recommended)", "description": "Brief summary of approach A" },
 9        { "label": "Option B", "description": "Brief summary of approach B" },
10        { "label": "Option C", "description": "Brief summary of approach C" }
11      ]
12    }
13  ]
14}

Phase 4: Design Presentation

Present design in sections (300-500 words each), validate after each:

  1. Architecture Overview - High-level structure
  2. Data Model - Entities, relationships, schema
  3. API Design - Endpoints, request/response
  4. Component Design - Internal modules, interfaces
  5. Error Handling - Error cases, recovery strategies
  6. Testing Strategy - What and how to test

After each section, use AskUserQuestion:

 1{
 2  "questions": [
 3    {
 4      "question": "Does this section look correct?",
 5      "header": "Review",
 6      "multiSelect": false,
 7      "options": [
 8        { "label": "Looks Good", "description": "Continue to next section" },
 9        { "label": "Minor Changes", "description": "Small adjustments needed" },
10        { "label": "Major Revision", "description": "Significant changes required" },
11        { "label": "Questions", "description": "Need clarification before proceeding" }
12      ]
13    }
14  ]
15}

Phase 5: Documentation & Tasks

Save Design Document

Write to docs/designs/YYYY-MM-DD-<topic>-design.md:

 1# Feature: [Name]
 2
 3## Summary
 4[Brief description]
 5
 6## Requirements
 7[From Phase 2 answers]
 8
 9## Architecture
10[From Phase 4]
11
12## Implementation Tasks
13[Task checklist]

Generate Implementation Tasks

 1## Implementation Tasks
 2
 3- [ ] **Task Title** `priority:1` `phase:model` `time:15min`
 4  - files: src/file1.py, tests/test_file1.py
 5  - [ ] Write failing test for X
 6  - [ ] Run test, verify it fails
 7  - [ ] Implement minimal code
 8  - [ ] Run test, verify it passes
 9  - [ ] Commit
10
11- [ ] **Another Task** `priority:2` `phase:api` `deps:Task Title` `time:10min`
12  - files: src/api.py
13  - [ ] Write failing test
14  - [ ] Implement and verify
15  - [ ] Commit

Phase 6: Execution Handoff

 1{
 2  "questions": [
 3    {
 4      "question": "How would you like to proceed with implementation?",
 5      "header": "Next Step",
 6      "multiSelect": false,
 7      "options": [
 8        { "label": "Execute Now", "description": "Run /feature-pipeline in this session" },
 9        { "label": "New Session", "description": "Start fresh session for implementation" },
10        { "label": "Later", "description": "Save design, implement manually later" },
11        { "label": "Revise Design", "description": "Go back and modify the design" }
12      ]
13    }
14  ]
15}

Key Principles

  • Batch questions efficiently - Use all 4 question slots when appropriate
  • Use multiSelect for non-exclusive options - Layers, features, requirements
  • Use single-select for decisions - Approach, timeline, strategy
  • Mark recommendations - Add “(Recommended)” to preferred options
  • Progressive refinement - General → Specific questions
  • Validate incrementally - Check understanding at each phase
  • YAGNI ruthlessly - Remove unnecessary features from designs

What Users Are Saying

Real feedback from the community

Environment Matrix

Dependencies

No specific dependencies required

Context Window

Token Usage ~5K-15K tokens for comprehensive feature designs

Security & Privacy

Information

Author
davila7
Updated
2026-01-30
Category
productivity-tools