agent

Launch Clean Claude agents with optional reactive links for multi-agent coordination.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/antoinersw/pbi-versioning --skill agent-antoinersw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent
Source: https://github.com/antoinersw/pbi-versioning/tree/main/.claude/skills/agent
Command: npx skills add https://github.com/antoinersw/pbi-versioning --skill agent-antoinersw

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Start and coordinate Clean Claude agents with optional reactive links to other agents, enabling collaborative automation and triage in conversations.

Core Features & Use Cases

  • Start an agent by name with optional reactive links to other agents (e.g., qa-engineer, architect).
  • Route work and feedback between linked agents in a single command to coordinate multi-step tasks.
  • Escalation keywords route issues to the appropriate role for decision-making.

Quick Start

Invoke the /agent command with the desired agent name and optional --link arguments to start a multi-agent workflow.

Frequently Asked Questions about agent

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

FAQPage Schema
How do I coordinate multiple agents in a single workflow?

Multi-agent orchestration is coordinated by launching a Clean Claude agent with reactive links, routing tasks and feedback between linked roles like qa-engineer or architect using escalation keywords.

What are reactive links in multi-agent automation?

Reactive links connect a primary agent to secondary agents, enabling automatic routing of work and feedback across roles in a conversation context to coordinate multi-step tasks.

How do I start an agent with linked roles for task triage?

Start an agent by invoking the command with the desired agent name and optional --link arguments to attach roles like qa-engineer or architect for collaborative task triage.

Can I route feedback between different agents in a conversation?

Yes, feedback is routed between linked agents using defined escalation keywords, directing issues to the appropriate role for decision-making within the shared conversation context.

Do I need any dependencies to run a multi-agent workflow?

No external dependencies are required to run multi-agent workflows, as the skill operates independently to launch agents and manage reactive links within the conversation.

When should I use linked agents instead of a single agent?

Use linked agents when tasks require multi-role coordination and feedback routing across distinct roles, whereas a single agent suffices for isolated, non-collaborative automation tasks.