parallel-agents

Orchestrates multiple specialized agents for multi-domain code analysis and review.

Updated Aug 5, 2026
One-click install
npx skills add https://github.com/pd-phuc/laravel-template --skill parallel-agents-pd-phuc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: parallel-agents
Source: https://github.com/pd-phuc/laravel-template/tree/main/.claude/skills/parallel-agents
Command: npx skills add https://github.com/pd-phuc/laravel-template --skill parallel-agents-pd-phuc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Complex engineering tasks often span multiple domains—security, backend, frontend, testing—and a single perspective misses critical issues. This Skill coordinates multiple specialized agents so comprehensive analysis, feature reviews, and security audits are covered from every relevant angle in one session. ## Core Features & Use Cases - Multi-Agent Orchestration: Invoke 17 specialized agents (security-auditor, backend-specialist, test-engineer, and more) individually, sequentially, or in structured patterns. - Orchestration Patterns: Predefined workflows for comprehensive analysis, feature review, and security audits with a defined synthesis protocol. - Context Passing & Resume: Share findings between agents and resume previous agent work within a single session. - Use Case: Before shipping a new API feature, run the explorer-agent to map the codebase, then the security-auditor and backend-specialist for review, and finally the test-engineer to verify coverage—consolidated into one prioritized report. ## Quick Start Ask the AI to use the security-auditor, backend-specialist, and test-engineer agents to comprehensively review the current codebase and synthesize the findings.

Frequently Asked Questions about parallel-agents

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run multiple AI agents on the same codebase?▼

Invoke agents sequentially by naming them in order, such as asking the explorer-agent to map the structure first, then domain specialists to analyze it. Findings can be passed between agents and merged into a single synthesis report.

What agents are available for code review and analysis?▼

Seventeen specialized agents are available, including security-auditor, backend-specialist, frontend-specialist, test-engineer, database-architect, and performance-optimizer. Built-in Explore and Plan agents handle fast read-only search and research.

When should I use multi-agent orchestration instead of a single agent?▼

Use orchestration for complex tasks spanning multiple expertise domains, such as full security audits or feature work touching backend, frontend, and database. Single agents are better for quick fixes and single-domain tasks.

Can I resume a previous agent's work in the same session?▼

Yes, you can resume a previous agent by referencing its agent ID and adding new requirements. All agents share session context, so earlier findings remain available to subsequent agents.

How are results from multiple agents combined?▼

A synthesis protocol consolidates all agent outputs into one report with a task summary, per-agent contributions, prioritized recommendations, and action items. This avoids fragmented separate outputs from each agent.