agent-collaboration

Standardize multi-agent collaboration with worktree awareness and decision logging.

9|1|Updated Jul 21, 2025
One-click install
npx skills add https://github.com/usepowershell/PoshMcp --skill agent-collaboration-usepowershell
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-collaboration
Source: https://github.com/usepowershell/PoshMcp/tree/main/.copilot/skills/agent-collaboration
Command: npx skills add https://github.com/usepowershell/PoshMcp --skill agent-collaboration-usepowershell

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Centralizes and standardizes collaboration patterns for all squad agents to reduce duplication, ensure consistent worktree awareness, decision recording, and cross-agent communication.

Core Features & Use Cases

  • Worktree awareness: agents reference the TEAM ROOT and relative .squad paths to stay aligned across the repository.
  • Decision recording: provides a consistent method for writing decisions to the inbox (e.g., .squad/decisions/inbox/) with clear metadata.
  • Cross-agent communication: encourages requesting input from teammates when needed, coordinating with the coordinator, and avoiding unilateral work.
  • Use Case: when a feature requires input from multiple agents, apply these patterns to log the decision and notify relevant teammates.

Quick Start

Apply these collaboration patterns by using the TEAM ROOT from your spawn prompt and writing the first decision to .squad/decisions/inbox/{your-name}-{brief-slug}.md.

Frequently Asked Questions about agent-collaboration

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

FAQPage Schema
How do I standardize multi-agent collaboration to prevent conflicting actions in shared worktrees?

To standardize multi-agent collaboration, apply structured patterns for worktree awareness, decision logging to a shared inbox, and reviewer protocols to prevent conflicting actions. This ensures all squad agents coordinate shared workspaces consistently.

How does decision recording work for squad agents coordinating shared workspaces?

Decision recording works by having agents write decisions to a shared inbox directory, such as .squad/decisions/inbox/, using a standardized file naming convention with clear metadata. This centralizes team communication and prevents unilateral work.

What's the best way to log multi-agent decisions and request input from teammates?

The best way to log multi-agent decisions is writing a markdown file to the .squad/decisions/inbox/ directory using your TEAM ROOT path. This structured approach notifies relevant teammates and coordinates input requests effectively.

When do I need centralized collaboration patterns for my agent teamwork?

You need centralized collaboration patterns when a feature requires input from multiple agents operating in the same repository. Applying these patterns ensures consistent worktree awareness, cross-agent communication, and structured decision recording.

Can I use these collaboration patterns to coordinate agents without a dedicated coordinator?

These collaboration patterns are designed for multi-agent environments where teams coordinate shared workspaces. While they encourage requesting input from teammates and coordinating with a coordinator, the structured inbox-based workflows also standardize communication independently.

Why does my squad agent need to reference the TEAM ROOT when logging decisions?

Your squad agent needs to reference the TEAM ROOT to stay aligned across the repository and ensure decisions are written to the correct relative .squad paths. This prevents duplication and maintains consistent worktree awareness.