← 返回 Skills 市场
347
总下载
0
收藏
0
当前安装
5
版本数
在 OpenClaw 中安装
/install orchestrix-guide
功能描述
Orchestrix multi-agent workflow guide for OpenClaw. Defines two operational phases: (1) Planning Phase — sequential agent orchestration in a single tmux wind...
安全使用建议
This is a coherent tmux-based orchestration manual rather than code. Before installing or using it: 1) Understand it will instruct the agent to send keystrokes into tmux and to auto-accept 'trust' and approval prompts — that can acknowledge prompts that you might otherwise want to inspect. 2) Verify the referenced scripts (e.g., .orchestrix-core/scripts/start-orchestrix.sh, monitor-agent.sh) are present in your project and review their contents for dangerous commands. 3) If you plan to run this on a machine with sensitive data, test in an isolated environment or sandbox first. 4) Consider disabling autonomous invocation or manually supervising runs if you are uncomfortable with automatic acceptance behaviors.
功能分析
Type: OpenClaw Skill
Name: orchestrix-guide
Version: 3.0.0
The skill bundle defines a complex multi-agent orchestration workflow that automates 'Claude Code' via tmux. It explicitly mandates the use of the '--dangerously-skip-permissions' flag, which bypasses critical security prompts for the AI agent. Furthermore, the instructions in SKILL.md rely on executing multiple external shell scripts (e.g., start-orchestrix.sh, monitor-agent.sh, and handoff-detector.sh) located in a hidden '.orchestrix-core' directory that are not provided in the bundle, making their actual behavior unverifiable. While these capabilities are plausibly for the stated purpose of automated development, the combination of high-privilege execution and opaque external dependencies poses a significant security risk.
能力评估
Purpose & Capability
Name/description claim a tmux-based multi-agent orchestration guide and the SKILL.md provides detailed tmux send-keys protocols, completion-detection, and handoff procedures — these requirements match the stated purpose and there are no unrelated env vars, binaries, or install steps.
Instruction Scope
Instructions stay within the orchestration domain (sending tmux keystrokes, capturing panes, checking files, running monitor/start scripts). However the guide explicitly instructs automatically accepting 'trust this folder' prompts and auto-responding to approval prompts (sending 'y'), which grants the controller broad authority to acknowledge prompts on behalf of the interactive agent; review these behaviors before use.
Install Mechanism
No install spec or external downloads — skill is instruction-only, so nothing is written to disk by the skill itself. Lower installation risk, but referenced scripts (e.g., .orchestrix-core/scripts/monitor-agent.sh, start-orchestrix.sh) are expected to exist in the project and must be inspected manually.
Credentials
The skill declares no required environment variables, credentials, or config paths. The operations described read terminal panes and local project files (expected for a tmux orchestration guide) and do not request unrelated secrets.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent/autonomous presence beyond normal agent invocation. That said, its recommended automated acceptance behavior increases the potential for side effects when the skill is run.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install orchestrix-guide - 安装完成后，直接呼叫该 Skill 的名称或使用
/orchestrix-guide触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v3.0.0
**Major update: tmux command protocol and completion detection fully revised, plus new test phase.**
- Standardized tmux command protocol to a strict 3-step pattern (send content → wait 1s → Enter) for all Claude Code CLI interactions.
- Added detailed handling and timing for multi-line content, agent switching, /clear usage, and trust dialog auto-accept.
- Reworked task completion detection rules: now uses Claude Code’s “Xxxed for <duration>” message as primary signal, plus enhanced polling scripts and approval automation.
- New global workflow adds Phase C (Testing): epic smoke test, fix, and retest loop until all pass.
- Scripts like monitor-agent.sh and ensure-session.sh are now referenced for robust automation.
- Documentation clarified, edge cases and error handling explictly described.
v2.0.0
# orchestrix-guide 2.0.0
- Major rewrite: reorganized guide to define two operational phases—Planning (sequential agent orchestration in a single tmux window) and Development (automated multi-window collaboration with HANDOFF).
- Simplified architecture and clarified the required tmux send-keys three-step protocol for all OpenClaw⇄Agent interactions.
- Presented a streamlined, phase-based workflow: clear distinction, task order, and cutover criteria between Planning and Development.
- Defined precise, prioritized multi-level strategies for automated task completion detection.
- Provided concise shell code snippets for each step and phase, supporting both automation and manual execution.
- Deprecated lower-level explanations and lengthy rationale, focusing on actionable, prescriptive instructions for end-to-end Orchestrix automation.
v1.2.0
Add mandatory 3-step command sequence rule (/clear → /o agent → *command) and dynamic tmux window creation for parallel Agent collaboration
v1.1.0
Add tmux send-keys operation protocol and 4-level task completion detection strategy for OpenClaw integration
v1.0.0
Initial release: comprehensive guide for operating Orchestrix agents via OpenClaw
元数据
常见问题
Orchestrix Guide 是什么？
Orchestrix multi-agent workflow guide for OpenClaw. Defines two operational phases: (1) Planning Phase — sequential agent orchestration in a single tmux wind... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 347 次。
如何安装 Orchestrix Guide？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install orchestrix-guide」即可一键安装，无需额外配置。
Orchestrix Guide 是免费的吗？
是的，Orchestrix Guide 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Orchestrix Guide 支持哪些平台？
Orchestrix Guide 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（macos, linux）。
谁开发了 Orchestrix Guide？
由 dorayo（@dorayo）开发并维护，当前版本 v3.0.0。
推荐 Skills