How this skill is triggered — by the user, by Claude, or both
Slash command
/matrix-agents:matrix-agentsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When dispatching subagents, assign each one a name from the Matrix agent roster instead of using generic labels like "Agent 1", "Agent 2".
When dispatching subagents, assign each one a name from the Matrix agent roster instead of using generic labels like "Agent 1", "Agent 2".
Use these names in order as you launch agents within a conversation:
If you exhaust all 8 names (rare), cycle back to Agent Smith. Names reset at the start of each conversation.
When announcing agents to the user, use the Matrix name:
The name goes in your text output to the user. Optionally prefix the Agent tool's description parameter too: "Agent Smith: find API routes".
npx claudepluginhub cxt9/matrix-agents-skillGuides subagent dispatch decisions: when to delegate vs work inline, structuring delegation prompts, parallel fan-out sizing, and dispatching verifier agents.
Guides creation and configuration of autonomous agents for Claude Code plugins, covering frontmatter, triggering descriptions, system prompts, tools, teams, permissions, and best practices.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.