Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Design Research

ASecurity

Conduct research and create design documents before implementation. Use when analyzing requirements, exploring solutions, creating architecture designs, or investigating codebase patterns. Invoked by: "research", "design", "analyze", "investigate", "explore codebase".

76 stars
0 votes
0 copies
1 views
Added 2/8/2026
developmentgobashtestingrefactoringapiperformance

Works with

api

Security Analysis

A100/100

Scanned 2/12/2026

Install to Claude Code

$npx -y skills add majiayu000/claude-skill-registry --skill design-research --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Design Research?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Design Research
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majiayu000-design-research/badge)](https://www.skillsdirectory.com/skills/majiayu000-design-research)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: design-research
description: >-
  Conduct research and create design documents before implementation.
  Use when analyzing requirements, exploring solutions, creating architecture
  designs, or investigating codebase patterns.
  Invoked by: "research", "design", "analyze", "investigate", "explore codebase".
context: fork
agent: Explore
---

# Research and Design Process SOP

**Version**: 1.0.0
**Last Updated**: 2026-01-11
**Status**: Active

---

## Overview

### Purpose
This process is the critical first phase before creating a design document. It ensures the user request is fully understood, the codebase is thoroughly analyzed, multiple solutions are considered, and the best approach is selected with solid foundation for design.

### When to Use
**ALWAYS**: New features, complex refactorings, architectural changes, breaking changes
**SKIP**: Simple bug fixes, trivial changes, explicit implementation instructions

---

## Process Workflow

### Flow Diagram
```
[User Request] --> [Request Understanding] --> [Repository Analysis]
                            |
                            v
              [Solution Exploration] --> [Recommendation & Decision]
                            |
                            v
                    [Design Document]
```

### Phase Summary
| Phase | Duration | Focus |
|-------|----------|-------|
| 1. Request Understanding | 10-20 min | Clarify requirements |
| 2. Repository Analysis | 20-40 min | Understand codebase |
| 3. Solution Exploration | 15-30 min | Generate alternatives |
| 4. Recommendation | 5-10 min | Document & approve |

**Total Duration**: 50-90 minutes

---

## Key Principles

1. **Conversation First** - Collaborative, not automated
2. **Deep Understanding** - Use comprehensive approach, read ALL relevant code
3. **Question Everything** - Challenge assumptions, ask clarifying questions
4. **Explore Alternatives** - Always present multiple approaches
5. **Align with Patterns** - Follow existing codebase conventions
6. **Document Findings** - Create clear, actionable research reports
7. **Platform Considerations** - Consider platform-specific differences when applicable

---

## Research Agent Responsibilities

### Must Do
- Act as consultant (advise and guide)
- Be thorough (read ALL code, no assumptions)
- Be conversational (engage, ask questions, discuss)
- Be critical (question if better approaches exist)
- Be comprehensive (consider all layers)
- Be pattern-aware (identify and follow existing patterns)
- Be honest (admit uncertainty, ask for help)
- Document everything (findings, conversations, decisions)
- Consider platform differences when applicable

### Must NOT Do
- Jump to implementation (no code changes during research)
- Make unilateral decisions (always collaborate)
- Skip analysis (every request deserves investigation)
- Ignore alternatives (always present multiple options)
- Assume understanding (ask clarifying questions)
- Violate architecture (respect established patterns)
- Ignore platform differences when applicable

---

## Phase 1: Request Understanding

**Objective**: Fully understand what user wants to achieve
**Duration**: 10-20 minutes

See [RESEARCH_GUIDE.md](RESEARCH_GUIDE.md) for detailed steps.

### Quick Checklist

- [ ] Read user request thoroughly
- [ ] Identify core objective
- [ ] Note constraints mentioned
- [ ] Flag ambiguous points
- [ ] Ask clarifying questions
- [ ] Define success criteria
- [ ] Get user confirmation

### Questions to Ask
- What is user trying to achieve?
- Is this new feature, bug fix, refactoring, or optimization?
- What is the scope? (UI? State management? Routing? API?)
- Are there explicit/implicit requirements?
- Are there platform-specific requirements?

---

## Phase 2: Repository Analysis

**Objective**: Deeply understand current codebase and architecture
**Duration**: 20-40 minutes

See [RESEARCH_GUIDE.md](RESEARCH_GUIDE.md) for detailed steps.

### Quick Checklist

- [ ] Use Glob/Grep to find relevant files
- [ ] Read all relevant files (components, screens, Redux, navigation, tests)
- [ ] Read project rules for guidelines
- [ ] Identify existing patterns
- [ ] Map dependencies and impacts
- [ ] Find similar implementations

### Search Patterns
```bash
# Find components
Glob: "src/components/**/*{name}*.*"

# Find pages/screens/views
Glob: "src/{pages,screens,views}/**/*{name}*.*"

# Find state management
Glob: "src/{store,state,redux}/**/*{name}*.*"

# Find routing/navigation
Glob: "src/{routes,navigation,router}/**/*.*"

# Find tests
Glob: "{__tests__,tests,spec}/**/*{feature}*.*"
```

---

## Phase 3: Solution Exploration

**Objective**: Generate and evaluate multiple solution approaches
**Duration**: 15-30 minutes

### Always Create At Least 3 Alternatives

```markdown
### Approach 1: Minimal Change (Simplest)
**Description**: Add feature with minimal refactoring
**Effort**: 1-2 days | **Risk**: Low
**Pros**: Quick, low risk, backward compatible
**Cons**: Doesn't address technical debt, may not be extensible

### Approach 2: Refactoring (Recommended)
**Description**: Add feature + refactor to improve architecture
**Effort**: 3-4 days | **Risk**: Medium
**Pros**: Improves code quality, follows best practices, extensible
**Cons**: More work upfront, touches more files

### Approach 3: Complete Redesign (Thorough)
**Description**: Redesign system entirely
**Effort**: 10-15 days | **Risk**: High
**Pros**: Solves underlying issues, future-proof
**Cons**: High effort and risk, many breaking changes
```

### Trade-off Analysis

For each approach, document:
1. **Alignment with Architecture** - Project patterns compliance?
2. **Complexity** - Implementation complexity, files affected, risk?
3. **Maintainability** - Easy to understand/extend, technical debt?
4. **Performance** - Performance implications?
5. **Testing** - How testable? Coverage needed?
6. **Migration** - Rollback strategy? Backward compatibility?
7. **Platform Compatibility** - Works across target platforms?

---

## Phase 4: Recommendation & Decision

**Objective**: Make final recommendation and get user approval
**Duration**: 5-10 minutes

### Present Final Recommendation

```markdown
## Final Recommendation

### Chosen Approach: [Approach Name]

### Summary
[2-3 sentence summary]

### Why This Approach
1. [Alignment with architecture]
2. [Balances effort/quality]
3. [Follows existing patterns]
4. [Platform compatibility]

### What Will Be Changed
- Types: [files]
- Redux: [files]
- Components: [files]
- Screens: [files]
- Navigation: [files]

### Estimated Effort
- Duration: X days
- Complexity: Low/Medium/High
- Risk: Low/Medium/High

### Risks & Mitigations
| Risk | Mitigation |
|------|------------|
| {Risk} | {Strategy} |
```

### Get User Approval

```markdown
Does this approach look good to you?
- [ ] Yes, proceed to design document
- [ ] I have questions/concerns
- [ ] I prefer a different approach
```

---

## Output: Create Research Report

Once approved, create feature folder and research file:

1. **Create folder**: `/docs/ignored/<feature_name>/`
2. **Create subfolders**: `design/`, `development/`, `research/`
3. **Create research file**: `/docs/ignored/<feature_name>/research/<feature_name>_research.md`

Use template: [DESIGN_TEMPLATE.md](DESIGN_TEMPLATE.md)

---

## Quick Reference

### Decision Criteria

**Choose Minimal Approach When**:
- Timeline very tight (< 2 days)
- Low complexity
- Temporary solution acceptable

**Choose Refactoring Approach When**:
- Moderate timeline (2-5 days)
- Medium complexity
- Quality improvement opportunity
- Reasonable effort/benefit ratio

**Choose Redesign Approach When**:
- Ample timeline (> 1 week)
- High complexity
- Existing design fundamentally flawed
- Long-term benefits justify cost

---

## Troubleshooting

| Issue | Solution |
|-------|----------|
| Requirements unclear | Ask clarifying questions before proceeding |
| Too many alternatives | Focus on top 3 most viable approaches |
| Can't find existing patterns | Search broader, check similar features |
| User wants to skip research | Explain risks, offer abbreviated process |
| Platform-specific issues | Document separately per platform |

---

## Related Skills

| Skill | Purpose | When to Use |
|-------|---------|-------------|
| `/dev-feature` | Full feature workflow | After research, for implementation |
| `/review-code` | Code review | After implementation |

> **Note**: Skill paths (`/skill-name`) work after deployment. In the template repo, skills are in domain folders.

---

**End of SOP**

Attribution

majiayu000majiayu000
View sourceMore from majiayu000 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Browser Extension Developer

Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

284722 votes

Seo Optimizer

SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.

2192 votes

Google Official Seo Guide

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

1862 votes

Tanstack Start

Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per ...

9881 votes

Pentest

PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.

5491 votes
View all in development →