skills.rest
softspark
softsparkCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

teams

Launch pre-configured agent teams for coordinated multi-agent workflows.

161|21|Updated Mar 26, 2026
Search Tags:#debugging#orchestration#code-review#security-audit#feature-development#agent-teams
One-click install
npx skills add https://github.com/softspark/ai-toolkit --skill teams-softspark
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: teams
Source: https://github.com/softspark/ai-toolkit/tree/main/app/skills/teams
Command: npx skills add https://github.com/softspark/ai-toolkit --skill teams-softspark

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the friction of composing and launching multiple specialized agents for complex engineering workflows by providing vetted, pre-configured team presets, ownership rules, aggregation strategies, and standardized outputs so teams can get results faster and more consistently.

Core Features & Use Cases

  • Preset Team Compositions: One-step presets for review, debug, feature, fullstack, research, security, and migration workflows.
  • Ownership & Aggregation: Built-in ownership rules and aggregation strategies (consensus, relay, map-reduce) to synthesize multi-agent outputs into single deliverables like REVIEW.md, DEBUG_REPORT.md, or SECURITY_AUDIT.md.
  • Confirmation & Safety Checks: Validates preset names and checks required environment flag before launching to prevent accidental execution.
  • Use Case: Launch an automated code review team to produce a severity-ranked review summary for a pull request.

Quick Start

Type /teams review followed by an optional task description to launch a pre-configured review team for the current changes.

Frequently Asked Questions about teams

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

FAQPage Schema
How do I launch pre-configured agent teams for a code review?▼

To launch agent teams for a code review, type the /teams review command with an optional task description to instantly initiate a pre-configured review team for your current changes.

Can I use multi-agent workflows for security audits and feature development?▼

Yes, multi-agent workflows support security audits and feature development by deploying specialist agents to collaborate on these complex engineering tasks and generate structured output documents.

Do I need an environment variable to run multi-agent orchestration?▼

Yes, running multi-agent orchestration requires setting the CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS environment variable, as the system validates this safety flag before launching any agents.

How do multiple agents aggregate their outputs into a single report?▼

Multiple agents aggregate their outputs using built-in aggregation strategies like consensus, relay, or map-reduce to synthesize results into single deliverables such as REVIEW.md or DEBUG_REPORT.md.

What is the best way to coordinate specialist agents for a migration?▼

The best way to coordinate specialist agents for a migration is using pre-configured team presets that enforce ownership rules and aggregation strategies for consistent, fast results.

Related Skills

Explore More Software Engineering Skills→
alinaqialinaqi
705

agent-teams

Orchestrate AI agents through a strict TDD pipeline to create pull requests.

Community
Advanced
cloudvoyantcloudvoyant

pr-fix

Fetch open pull requests and generate proposed code fixes for unresolved review comments.

Official
Intermediate
AnveioAnveio
1

task-pull-request

Automate GitHub pull request creation, reviews, feedback, and merges via gh CLI.

Community
Intermediate
krzemienskikrzemienski
2

dispatching-parallel-agents

Dispatch parallel agents to investigate independent failures with MCP result aggregation.

Community
Advanced