菜单
Scaffolds a new autonomous sub-agent with its own prompt, system instructions, and tool permissions. NOT for stateless procedural skills (use `create-skill`) and NOT for creating GitHub Actions workflows (use `create-agentic-workflow`).
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/richfrem/agent-plugins-skills --skill create-sub-agent命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Scaffolds a new top-level agent plugin directory. NOT for scaffolding single skills (use `create-skill`) and NOT for adding MCP integrations to existing plugins (use `create-mcp-integration`).
This skill should be used when the user wants to "create a marketplace", "setup a marketplace catalog", "scaffold marketplace.json", "initialize a plugin registry", or "configure a Gemini CLI extension". Use this even if they just mention "setting up a marketplace".
Cooperative Multi-Agent Coordination Loop. Spawns a lightweight companion sub-agent (Gemini 3.5 Flash Low) to perform spec discovery, planning, and implementation. The primary agent (Claude) acts as the QA Director, answering Gemini's questions, approving the spec/plan, and running verification tests. Assumes the superpowers plugin is installed in the target repository.
基于 SOC 职业分类
正在显示 SKILL.md
| name | create-sub-agent |
| plugin | agent-scaffolders |
| description | Scaffolds a new autonomous sub-agent with its own prompt, system instructions, and tool permissions. NOT for stateless procedural skills (use `create-skill`) and NOT for creating GitHub Actions workflows (use `create-agentic-workflow`). |
| argument-hint | [agent-name or use-case description] |
| allowed-tools | Bash, Read, Write |
Follow the create-sub-agent skill workflow to design and generate a Claude Code agent file.
$ARGUMENTS — optional agent name or brief use-case description passed as initial context
to the design interview. Omit to start with open discovery.$ARGUMENTS is provided, use it as the starting context for agent name / purpose.md filevalidate_agent.py.github/agents/ or .claude/agents/ and ensure the path is tracked in .gitignore.Agent .md file with complete YAML frontmatter (name, description with <example> blocks,
model, maxTokens, color, permissions.allowedTools, permissions.deny) and a second-person
system prompt targeting 500-3,000 characters.
Plugin agents: flat .md file — plugins/<plugin-name>/agents/<agent-name>.md
skills/<name>/SKILL.md subdirectory format, but agents do NOT.feature-dev, code-simplifier, hookify).Local/project agents: .claude/agents/<agent-name>.md (also flat, no subdirectory).
To make an agent visible to GitHub Copilot or Claude Code for this repository, follow the Discovery-First Publication pattern:
.github/agents/ (Copilot) or .claude/agents/ (Claude)..gitignore allows the specific agent file or subdirectory.See Agent Discovery and Publication Pattern for details.
$ARGUMENTS is empty: conduct the full Phase 1 design interview — do not pre-fill