Skip to content
Development
Skill

/multi-role

Parallel analysis with multiple roles and integrated report. Trigger with "analyze from multiple perspectives", "multi-role analysis", "check both security and performance".

From plugin
claude-code-cookbook
1.1k39 skills9 agents39 commands8 MCP

Claude Code

$ npx -y skills add wasabeef/claude-code-cookbook --skill multi-role --agent claude-code

SKILL.md

multi-role.SKILL.md
description: 'Parallel analysis with multiple roles and integrated report. Trigger with "analyze from multiple perspectives", "multi-role analysis", "check both security and performance".'
allowed-tools:
  - Read
  - Grep
  - Glob

Parallel analysis with multiple roles and integrated report

A command that analyzes the same target in parallel with multiple roles and generates an integrated report.

Usage

/multi-role <role1>,<role2> [--agent|-a] [analysis_target]
/multi-role <role1>,<role2>,<role3> [--agent|-a] [analysis_target]

Available Roles

Specialized Analysis Roles

  • `security`: Security audit expert
  • `performance`: Performance optimization expert
  • `analyzer`: Root cause analysis expert
  • `frontend`: Frontend and UI/UX expert
  • `mobile`: Mobile development expert
  • `backend`: Backend and server-side expert

Development Support Roles

  • `reviewer`: Code review expert
  • `architect`: System architect
  • `qa`: Test engineer

**Important**:

  • Place the `--agent` option immediately after specifying roles
  • Write your message after `--agent`
  • Correct example: `/multi-role qa,architect --agent Evaluate the plan`
  • Incorrect example: `/multi-role qa,architect Evaluate the plan --agent`

Options

  • `--agent` or `-a`: Execute each role as a sub-agent in parallel (recommended for large-scale analysis)
  • When using this option, if role descriptions include proactive delegation phrases (like "use PROACTIVELY"), more aggressive automatic delegation becomes enabled

Basic Examples

# Dual analysis of security and performance (normal)
/multi-role security,performance
"Evaluate this API endpoint"

# Parallel analysis of large-scale system (sub-agents)
/multi-role security,performance --agent
"Comprehensively analyze system security and performance"

# Integrated analysis of frontend, mobile, and performance
/multi-role frontend,mobile,performance
"Consider optimization proposals for this screen"

# Multifaceted evaluation of architecture design (sub-agents)
/multi-role architect,security,performance --agent
"Evaluate microservices design"

Analysis Process

Phase 1: Parallel Analysis

Each role independently analyzes the same target

  • Perform evaluation from specialized perspective
  • Make judgments based on role-specific criteria
  • Generate independent recommendations

Phase 2: Integrated Analysis

Structure and integrate results

  • Organize evaluation results from each role
  • Identify overlaps and contradictions
  • Clarify complementary relationships

Phase 3: Integrated Report

Generate final recommendations

  • Prioritized action plan
  • Explicit trade-offs
  • Implementation roadmap

Output Format Examples

For 2-role Analysis

Multi-role Analysis: Security + Performance
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Analysis Target: API endpoint /api/users

Security Analysis Results:
Authentication: JWT verification properly implemented
Authorization: Role-based access control incomplete
Encryption: API keys logged in plain text

Evaluation Score: 65/100
Importance: High (due to sensitive data access)

Performance Analysis Results:
Response Time: Average 180ms (within target of 200ms)
Database Queries: N+1 problem detected
Caching: Redis cache not implemented

Evaluation Score: 70/100
Importance: Medium (currently within acceptable range)

Interrelated Analysis:
Synergistic Opportunities:
- Consider encryption when implementing Redis cache
- Improve logging for both security and performance gains

Trade-off Points:
- Authorization check strengthening ↔ Impact on response time
- Log encryption ↔ Reduced debugging efficiency

Integrated Priorities:
Critical: Fix API key plain text output
High: Resolve N+1 queries
Medium: Implement Redis cache + encryption
Low: Refine authorization control

Implementation Roadmap:
Week 1: Implement API key masking
Week 2: Database query optimization
Weeks 3-4: Cache layer design and implementation
Month 2: Progressive strengthening of authorization control

For 3-role Analysis

Multi-role Analysis: Frontend + Mobile + Performance
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Analysis Target: User Profile Screen

Frontend Analysis Results:
Usability: Intuitive layout
Accessibility: 85% WCAG 2.1 compliance
Responsive: Issues with tablet display

Mobile Analysis Results:
Touch Targets: 44pt+ ensured
One-handed Operation: Important buttons placed at top
Offline Support: Not implemented

Performance Analysis Results:
Initial Display: LCP 2.1s (good)
Image Optimization: WebP not supported
Lazy Loading: Not implemented

Integrated Recommendations:
1. Mobile optimization (one-handed operation + offline support)
2. Image optimization (WebP + lazy loading)
3. Tablet UI improvements

Priority: Mobile > Performance > Frontend
Implementation Period: 3-4 weeks

Effective Combination Patterns

Security-focused

/multi-role security,architect
"Authentication system design"

/multi-role security,frontend
"Login screen security"

/multi-role security,mobile
"Mobile app data protection"

Performance-focused

/multi-role performance,architect
"Scalability design"

/multi-role performance,frontend
"Web page speed optimization"

/multi-role performance,mobile
"App performance optimization"

User Experience-focused

/multi-role frontend,mobile
"Cross-platform UI"

/multi-role frontend,performance
"Balance between UX and performance"

/multi-role mobile,performance
"Mobile UX optimization"

Comprehensive Analysis

/multi-role architect,security,performance
"Overall system evaluation"

/multi-role frontend,mobile,performance
"Comprehensive user experience evaluation"

/multi-role security,performance,mobile
"Comprehensive mobile app diagnosis"

Collaboration with Claude

# Combine with file analysis
cat src/components/UserProfile.tsx
/multi-role frontend,mobile
"Evaluate this component from multiple perspectives"

# Evaluate design docu
Read more
@wasabeef
Ships withclaude-code-cookbook

A collection of commands, roles, and automation scripts for Claude Code. Automate your workflow without unnecessary confirmations, allowing you to focus on what matters.

1.1k39 skills9 agents8 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
1.1k
Star history of wasabeef/claude-code-cookbook on GitHub, a chart by star-history.com

Other skills on claude-code-cookbook.

check-fact

check-fact

Verify information accuracy against codebase and documentation. Trigger with "is this correct?", "fact check", "verify this", "is…

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills11d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc12d293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react2d252k
@facebook@facebookInstall Skill

Questions about multi-role.

Which coding agents can use multi-role?
multi-role installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.