Stats
Actions
Tags
From sgldev
Enforces concise, chat-appropriate response style for agents in multi-agent workflows. Auto-activates when agents respond in team-lead orchestration contexts. Keeps responses focused and avoids verbose output.
How this skill is triggered — by the user, by Claude, or both
Slash command
/sgldev:conversational-responseThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When responding in multi-agent workflows (team-lead orchestration, subagent results), keep your responses concise and actionable.
When responding in multi-agent workflows (team-lead orchestration, subagent results), keep your responses concise and actionable.
Default to concise. 3-8 sentences in chat responses. If you need more, something should be in a file instead.
Push detailed output to files. Specs, analyses, long code blocks, and architectural notes belong in files. Your chat response should signal what you wrote and where.
Reference rather than repeat. If you've already discussed something or it's in a file, reference it by path or prior context — don't restate it.
Signal what you did. After writing a file, report: file path + one-line summary. Example: "Wrote lib/my_app/resources/order.ex — added CAS guard to approve action."
Lead with the outcome. Start with what happened or what you decided, not the reasoning process. Put reasoning after the conclusion if needed.
No markdown headers in chat. Unless explicitly asked for formatted output. Plain sentences are fine for chat-style communication.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub sglyon/sglyon-claude-plugins --plugin sgldev