Agent skill

Feature Design Assistant

by davila7 in davila7/claude-code-templates

Turn ideas into fully formed designs and specs through natural collaborative dialogue.

MITAuto-check passed

Install Feature Design Assistant

skills CLI
$ npx skills add davila7/claude-code-templates --skill feature-design-assistant -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install davila7/claude-code-templates feature-design-assistant --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/davila7/claude-code-templates.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cli-tool/components/skills/development/feature-design-assistant .claude/skills/feature-design-assistant && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
feature-design-assistant
GitHub stars
32k
Used in
1 other repo
Token cost
~3k tokens
SKILL.md length
259 words
Files
1
Skills in repo
478
Repo updated
First seen
Licence
MIT

At a glance

Turn ideas into fully formed designs and specs through natural collaborative dialogue.

  • Works in 6 steps: Context Discovery → Structured Information Gathering → Approach Exploration → …
  • Planning new features
  • SKILL.md covers Phase 1: Context Discovery, Phase 2: Structured…, Phase 3: Approach Exploration and Phase 4: Design Presentation, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Feature Design Assistant is an agent skill from davila7/claude-code-templates. 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.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: CLI tool for configuring and monitoring Claude Code. The licence is MIT.

When your agent uses it

  • Planning new features
  • Designing architecture
  • Making significant changes to the codebase

Example prompts

  • “/feature-design-assistant”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Context Discovery
  2. Structured Information Gathering
  3. Approach Exploration
  4. Design Presentation
  5. Documentation & Tasks
  6. Execution Handoff

What it can do on your machine

Read from SKILL.md and the folder at commit 46b4d8b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are json and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Feature Design Assistant loads about 3k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 259 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from davila7/claude-code-templates at commit 46b4d8b, republished under its MIT licence (© davila7). 259 words, ~3,033 tokens.

Download SKILL.mdSave it as .claude/skills/feature-design-assistant/SKILL.md (or your agent's skills folder).
name
feature-design-assistant
description
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 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)
json
{
  "questions": [
    {
      "question": "What is the primary goal of this feature?",
      "header": "Goal",
      "multiSelect": false,
      "options": [
        { "label": "New Functionality", "description": "Add entirely new capability to the system" },
        { "label": "Enhancement", "description": "Improve or extend existing feature" },
        { "label": "Bug Fix", "description": "Fix incorrect behavior or issue" },
        { "label": "Refactoring", "description": "Improve code quality without changing behavior" }
      ]
    },
    {
      "question": "Who are the primary users of this feature?",
      "header": "Users",
      "multiSelect": true,
      "options": [
        { "label": "End Users", "description": "External customers using the product" },
        { "label": "Admins", "description": "Internal administrators or operators" },
        { "label": "Developers", "description": "Other developers using APIs or SDKs" },
        { "label": "System", "description": "Automated processes or background jobs" }
      ]
    },
    {
      "question": "What is the expected scope of this feature?",
      "header": "Scope",
      "multiSelect": false,
      "options": [
        { "label": "Small (1-2 days)", "description": "Single component, limited changes" },
        { "label": "Medium (3-5 days)", "description": "Multiple components, moderate complexity" },
        { "label": "Large (1-2 weeks)", "description": "Cross-cutting concerns, significant changes" },
        { "label": "Unsure", "description": "Need to explore further to estimate" }
      ]
    },
    {
      "question": "Are there any hard deadlines or constraints?",
      "header": "Timeline",
      "multiSelect": false,
      "options": [
        { "label": "Urgent", "description": "Need this ASAP, within days" },
        { "label": "This Sprint", "description": "Should be done within current sprint" },
        { "label": "Flexible", "description": "No hard deadline, quality over speed" },
        { "label": "Planning Only", "description": "Just designing now, implementing later" }
      ]
    }
  ]
}
Round 2: Technical Requirements (4 questions)
json
{
  "questions": [
    {
      "question": "Which layers of the system will this feature touch?",
      "header": "Layers",
      "multiSelect": true,
      "options": [
        { "label": "Data Model", "description": "Database schema, models, migrations" },
        { "label": "Business Logic", "description": "Services, domain logic, rules" },
        { "label": "API", "description": "REST/GraphQL endpoints, contracts" },
        { "label": "UI", "description": "Frontend components, user interface" }
      ]
    },
    {
      "question": "What are the key quality requirements?",
      "header": "Quality",
      "multiSelect": true,
      "options": [
        { "label": "High Performance", "description": "Must handle high load or be very fast" },
        { "label": "Strong Security", "description": "Sensitive data, auth, access control" },
        { "label": "High Reliability", "description": "Cannot fail, needs redundancy" },
        { "label": "Easy Maintenance", "description": "Needs to be easily understood and modified" }
      ]
    },
    {
      "question": "How should errors be handled?",
      "header": "Errors",
      "multiSelect": false,
      "options": [
        { "label": "Fail Fast", "description": "Stop immediately on any error" },
        { "label": "Graceful Degrade", "description": "Continue with reduced functionality" },
        { "label": "Retry & Recover", "description": "Automatic retry with recovery logic" },
        { "label": "Context Dependent", "description": "Different strategies for different cases" }
      ]
    },
    {
      "question": "What testing approach is preferred?",
      "header": "Testing",
      "multiSelect": false,
      "options": [
        { "label": "TDD (Recommended)", "description": "Write tests first, then implementation" },
        { "label": "Test After", "description": "Implement first, add tests after" },
        { "label": "Minimal Tests", "description": "Only critical path testing" },
        { "label": "No Tests", "description": "Skip testing for this feature" }
      ]
    }
  ]
}
Round 3: Integration & Dependencies (4 questions)
json
{
  "questions": [
    {
      "question": "Does this feature need external integrations?",
      "header": "Integrations",
      "multiSelect": true,
      "options": [
        { "label": "Database", "description": "New tables, queries, or migrations" },
        { "label": "External APIs", "description": "Third-party service calls" },
        { "label": "Message Queue", "description": "Async processing, events" },
        { "label": "None", "description": "No external integrations needed" }
      ]
    },
    {
      "question": "Are there dependencies on other features or teams?",
      "header": "Dependencies",
      "multiSelect": true,
      "options": [
        { "label": "Auth System", "description": "User authentication or authorization" },
        { "label": "Other Features", "description": "Depends on features being developed" },
        { "label": "External Team", "description": "Needs input from another team" },
        { "label": "None", "description": "Fully independent feature" }
      ]
    },
    {
      "question": "How should we handle backwards compatibility?",
      "header": "Compat",
      "multiSelect": false,
      "options": [
        { "label": "Must Maintain", "description": "Cannot break existing clients" },
        { "label": "Version API", "description": "Create new version, deprecate old" },
        { "label": "Breaking OK", "description": "Can make breaking changes" },
        { "label": "Not Applicable", "description": "New feature, no existing users" }
      ]
    },
    {
      "question": "What documentation is needed?",
      "header": "Docs",
      "multiSelect": true,
      "options": [
        { "label": "API Docs", "description": "Endpoint documentation" },
        { "label": "User Guide", "description": "How-to for end users" },
        { "label": "Dev Guide", "description": "Technical implementation details" },
        { "label": "None", "description": "No documentation needed" }
      ]
    }
  ]
}
Round 4: Clarifying Questions (Context-Dependent)

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

If UI layer selected:

json
{
  "questions": [
    {
      "question": "What UI framework/approach should we use?",
      "header": "UI Tech",
      "multiSelect": false,
      "options": [
        { "label": "React", "description": "React components with hooks" },
        { "label": "Vue", "description": "Vue.js components" },
        { "label": "Server-Side", "description": "Server-rendered HTML templates" },
        { "label": "Existing Pattern", "description": "Follow current project conventions" }
      ]
    }
  ]
}

If High Security selected:

json
{
  "questions": [
    {
      "question": "What security measures are required?",
      "header": "Security",
      "multiSelect": true,
      "options": [
        { "label": "Input Validation", "description": "Strict input sanitization" },
        { "label": "Rate Limiting", "description": "Prevent abuse and DoS" },
        { "label": "Audit Logging", "description": "Track all sensitive actions" },
        { "label": "Encryption", "description": "Encrypt data at rest/transit" }
      ]
    }
  ]
}

Phase 3: Approach Exploration

After gathering requirements, propose 2-3 approaches:

markdown
## Approach Options

### Option A: [Name] (Recommended)
**Pros:** ...
**Cons:** ...
**Best for:** ...

### Option B: [Name]
**Pros:** ...
**Cons:** ...
**Best for:** ...

### Option C: [Name]
**Pros:** ...
**Cons:** ...
**Best for:** ...

Use AskUserQuestion to confirm approach:

json
{
  "questions": [
    {
      "question": "Which approach would you like to proceed with?",
      "header": "Approach",
      "multiSelect": false,
      "options": [
        { "label": "Option A (Recommended)", "description": "Brief summary of approach A" },
        { "label": "Option B", "description": "Brief summary of approach B" },
        { "label": "Option C", "description": "Brief summary of approach C" }
      ]
    }
  ]
}

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:

json
{
  "questions": [
    {
      "question": "Does this section look correct?",
      "header": "Review",
      "multiSelect": false,
      "options": [
        { "label": "Looks Good", "description": "Continue to next section" },
        { "label": "Minor Changes", "description": "Small adjustments needed" },
        { "label": "Major Revision", "description": "Significant changes required" },
        { "label": "Questions", "description": "Need clarification before proceeding" }
      ]
    }
  ]
}

Phase 5: Documentation & Tasks

Save Design Document

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

markdown
# Feature: [Name]

## Summary
[Brief description]

## Requirements
[From Phase 2 answers]

## Architecture
[From Phase 4]

## Implementation Tasks
[Task checklist]
Generate Implementation Tasks
markdown
## Implementation Tasks

- [ ] **Task Title** `priority:1` `phase:model` `time:15min`
  - files: src/file1.py, tests/test_file1.py
  - [ ] Write failing test for X
  - [ ] Run test, verify it fails
  - [ ] Implement minimal code
  - [ ] Run test, verify it passes
  - [ ] Commit

- [ ] **Another Task** `priority:2` `phase:api` `deps:Task Title` `time:10min`
  - files: src/api.py
  - [ ] Write failing test
  - [ ] Implement and verify
  - [ ] Commit

Phase 6: Execution Handoff

json
{
  "questions": [
    {
      "question": "How would you like to proceed with implementation?",
      "header": "Next Step",
      "multiSelect": false,
      "options": [
        { "label": "Execute Now", "description": "Run /feature-pipeline in this session" },
        { "label": "New Session", "description": "Start fresh session for implementation" },
        { "label": "Later", "description": "Save design, implement manually later" },
        { "label": "Revise Design", "description": "Go back and modify the design" }
      ]
    }
  ]
}

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

© davila7, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in cli-tool/components/skills/development/feature-design-assistant of davila7/claude-code-templates.

Open the folder on GitHubat commit 46b4d8b

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in davila7/claude-code-templates, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Feature Design Assistant next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Feature Design Assistant compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Feature Design Assistant this skilldavila7/claude-code-templates32k1 repos~3kAutomated safety check: PassMIT
DESIGN.md Spec Reviewdifferent-ai/openwork24k—~1.4kAutomated safety check: PassCustom licence
Quick Design SpecDonchitos/Claude-Code-Game-Studios26k—~2.9kAutomated safety check: PassMIT
Design Systemaffaan-m/ECC276k—~698Automated safety check: PassMIT
Design Guidepaperclipai/paperclip99k1 repos~3.1kAutomated safety check: PassMIT
Spec Writergarrytan/gstack136k—~14kAutomated safety check: NotesMIT

Similar skills

  • DESIGN.md Spec Review

    different-ai/openwork

    Advisory review of a diff that flags user-facing UI changes breaking numbered rules in the repository's DESIGN.md, reporting at medium or low severity only.

    24k GitHub stars~1.4k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Quick Design Spec

    Donchitos/Claude-Code-Game-Studios

    Writes a short design spec for small gameplay adjustments such as tuning, tweaks and minor additions, and redirects anything larger to a full design document.

    26k GitHub stars~2.9k tokensUpdated yesterday
    Game DevelopmentAuto-check passed
  • Design System

    affaan-m/ECC

    Generate a design system from an existing codebase or audit one for visual consistency: extract tokens (colors, typography, spacing, shadows) into design-tokens.json and CSS custom properties with…

    276k GitHub stars~698 tokensUpdated 4 days ago
    Frontend & DesignAuto-check passed
  • Design Guide

    paperclipai/paperclip

    Paperclip UI design system guide for building consistent, reusable frontend components.

    99k GitHub starsUsed in 1 repo~3.1k tokens
    Frontend & DesignAuto-check passed
  • Spec Writer

    garrytan/gstack

    Converts a vague idea into a precise, executable spec in five phases, files it as an issue and can start an agent on it in a fresh worktree.

    136k GitHub stars~14k tokensUpdated today
    DevelopmentAuto-check: notes
  • Audits a design against Dieter Rams' ten principles of good design, scores each with evidence, and hands off a make-plan prompt for a new, refined or redesigned outcome.

    99k GitHub stars~4.6k tokensUpdated today
    Frontend & DesignAuto-check passed

More from davila7/claude-code-templates

All 478 skills in this repo
  • Perplexity Web Search

    davila7/claude-code-templates

    Runs web-grounded searches through Perplexity's Sonar models over OpenRouter for current events, recent literature and cited facts beyond the model's training cutoff.

    32k GitHub starsUsed in 11 repos~3.5k tokens
    Auto-check: notes
  • Neuropixels Data Analysis

    davila7/claude-code-templates

    Analyzes Neuropixels recordings from SpikeGLX or Open Ephys through preprocessing, drift correction, Kilosort4 spike sorting, quality metrics and curation.

    32k GitHub starsUsed in 9 repos~2.8k tokens
    Auto-check passed
  • Scientific Venue Templates

    davila7/claude-code-templates

    Supplies LaTeX templates and formatting rules for journals, conferences, posters, and grant proposals, then can check a draft against them.

    32k GitHub starsUsed in 9 repos~5.1k tokens
    Auto-check: notes
  • Brand Voice Content Creator

    davila7/claude-code-templates

    Analyzes a brand's existing writing to lock in a consistent voice, then builds SEO blog posts and platform-specific social content around it.

    32k GitHub starsUsed in 3 repos~1.9k tokens
    Auto-check passed
  • CAPA Officer

    davila7/claude-code-templates

    Guides corrective and preventive action (CAPA) work in a quality management system, from initiation and root cause analysis through effectiveness verification.

    32k GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed
  • Fda Consultant Specialist

    davila7/claude-code-templates

    Senior FDA consultant and specialist for medical device companies including HIPAA compliance and requirement management.

    32k GitHub starsUsed in 1 repo~2.7k tokens
    Auto-check passed

Questions about Feature Design Assistant

What does Feature Design Assistant do?

Turn ideas into fully formed designs and specs through natural collaborative dialogue. Feature Design Assistant is an agent skill from davila7/claude-code-templates. Turn ideas into fully formed designs and specs through natural collaborative dialogue.

When should I use Feature Design Assistant?

Feature Design Assistant fits situations like: planning new features; designing architecture; making significant changes to the codebase.

How do I install Feature Design Assistant in Claude Code?

Run `npx skills add davila7/claude-code-templates --skill feature-design-assistant -a claude-code`. Or copy the skill folder (cli-tool/components/skills/development/feature-design-assistant in davila7/claude-code-templates) into .claude/skills/feature-design-assistant in your project. Claude Code loads it when a task matches its description.

How do I install Feature Design Assistant in Codex?

Run `npx skills add davila7/claude-code-templates --skill feature-design-assistant -a codex`. Or copy the skill folder (cli-tool/components/skills/development/feature-design-assistant in davila7/claude-code-templates) into .agents/skills/feature-design-assistant in your project. Codex loads it when a task matches its description.

Can I use Feature Design Assistant in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add davila7/claude-code-templates --skill feature-design-assistant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feature-design-assistant, .gemini/skills/feature-design-assistant, .github/skills/feature-design-assistant and .opencode/skills/feature-design-assistant in your project.

What does Feature Design Assistant need to run?

SKILL.md names no scripts, command-line tools or credentials: Feature Design Assistant is instructions for the agent only.

Does Feature Design Assistant access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Feature Design Assistant safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Feature Design Assistant use?

Feature Design Assistant is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Feature Design Assistant use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Feature Design Assistant?

Skills that share tags, products or a category with Feature Design Assistant: DESIGN.md Spec Review (different-ai/openwork, 24k stars), Quick Design Spec (Donchitos/Claude-Code-Game-Studios, 26k stars), Design System (affaan-m/ECC, 276k stars) and Design Guide (paperclipai/paperclip, 99k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Feature Design Assistant?

davila7 (a GitHub user) maintains it in davila7/claude-code-templates, which has 32,483 GitHub stars. The repository holds 478 skills in this directory. The repository was last updated on October 9, 2026.

Source: davila7/claude-code-templates on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.