parallel-agents

Orchestrates multiple specialized agents for multi-domain analysis and coordinated task execution.

2|Updated May 30, 2026
One-click install
npx skills add https://github.com/virahitvin8/crafty-gis --skill parallel-agents-virahitvin8
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: parallel-agents
Source: https://github.com/virahitvin8/crafty-gis/tree/main/GIT_STAR/.agent/skills/parallel-agents
Command: npx skills add https://github.com/virahitvin8/crafty-gis --skill parallel-agents-virahitvin8

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Complex tasks often span multiple expertise domains—security, backend, frontend, testing—and a single agent perspective misses critical issues. This Skill coordinates multiple specialized agents so comprehensive reviews and multi-domain work happen in one orchestrated session. ## Core Features & Use Cases - Multi-Agent Orchestration Patterns: Predefined patterns for comprehensive analysis, feature review, and security audits using sequential chains and context passing. - 17 Specialized Agents: A catalog of domain agents (security-auditor, backend-specialist, test-engineer, devops-engineer, and more) with trigger phrases for selection. - Synthesis Protocol: A structured template that consolidates findings from all agents into one unified report with prioritized recommendations and action items. - Use Case: When reviewing a new authentication feature, invoke the security-auditor for vulnerabilities, the backend-specialist for API quality, and the test-engineer for coverage, then synthesize all findings into a single remediation plan. ## Quick Start Ask the assistant to run a comprehensive review of the codebase using the security-auditor, backend-specialist, and test-engineer agents, then 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 with natural language commands, such as asking the explorer-agent to map the structure first, then domain agents like security-auditor and backend-specialist. Pass findings from earlier agents as context to later ones, then synthesize all results.

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

Use orchestration when a task spans two or more expertise domains, such as a feature touching backend, frontend, and database, or a review needing security, performance, and testing perspectives. Single-domain tasks and quick fixes are better handled by one agent.

What specialized agents are available for code review?

Seventeen agents are available, including security-auditor, penetration-tester, backend-specialist, frontend-specialist, test-engineer, devops-engineer, database-architect, and performance-optimizer. Each maps to trigger phrases like "security", "API", or "tests".

Can I resume a previous agent's work in a later session?

Yes, the orchestration supports resuming a previous agent by referencing its agent ID and adding new requirements. Findings can also flow between agents through explicit context passing.

What are the limitations of parallel agent orchestration?

Orchestration adds coordination overhead, so it is not suited for simple single-domain tasks or small fixes. It also depends on selecting the right agents and ordering them logically: discovery, analysis, implementation, then testing.