菜单
Single agent, direct interaction. The simplest Workshop setup. Use for quick tasks, exploration, or when one agent is enough.
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。
基于 SOC 职业分类
Declarative multi-stage workflows. Define staged pipelines where each stage feeds its result to the next. Use for structured multi-agent tasks.
GitHub integration via gh CLI. List issues, create PRs, comment on issues. Use for agents that bridge GitHub and the Workshop board.
Autonomous board worker. Receives work items, implements them, reports results. Designed for agents that poll the board and execute tasks independently.
Work board driven development. Post typed work items with dependencies, agents poll by role. Use for multi-step features where ordering matters.
Multiple LLM backends in one workshop. Claude and Codex agents working together. Use when different models have different strengths.
Scheduled agent for periodic checks. Use for CI monitoring, PR scanning, health checks, or any polling-based workflow.
| name | solo |
| description | Single agent, direct interaction. The simplest Workshop setup. Use for quick tasks, exploration, or when one agent is enough. |
| license | MIT |
| metadata | {"author":"joshrotenberg","version":"1.0"} |
One agent, one conversation. Use ask for back-and-forth, cast for background work.
configure(backend: AgentWorkshop.Backends.Claude,
backend_config: ClaudeWrapper.Config.new(working_dir: "."),
model: "sonnet", permission_mode: :bypass_permissions)
agent(:dev, "You are a helpful software engineer.")
ask(:dev, "What's in this project?")
ask(:dev, "Add tests for the retry module")
cast(:dev, "Refactor the config module")
status()
await(:dev)