← 返回 Skills 市场
技能编排器
作者
Windymonkeys
· GitHub ↗
· v2.0.2
· MIT-0
122
总下载
0
收藏
1
当前安装
4
版本数
在 OpenClaw 中安装
/install skill-orchestrator
功能描述
Multi-skill orchestrator: decompose complex asks, discover skills, plan parallel/serial steps, checkpoints, merge outputs; optional JSON bundle for hosts. Us...
安全使用建议
This skill appears to do what it says: it discovers local Skills (from the listed folders or SKILL_PATH), plans and coordinates them, and merges outputs. Before enabling it: 1) Ensure SKILL_PATH and the local skill folders only contain Skills you trust, because this orchestrator will read SKILL.md files and invoke those Skills. 2) Be cautious about using phrases like "directly execute" or enabling bypassPermissions — that will skip checkpoints and can lead to risky actions if downstream Skills perform deployments or external calls. 3) Confirm your agent's network/OS/tooling permissions — this instruction-only Skill relies on the host agent to actually call ClawHub, invoke sub-agents, or run tools; those capabilities determine real risk. 4) If you need higher assurance, inspect a few discovered SKILL.md files (especially any that claim to perform deployments or external API calls) and confirm they don't request unrelated credentials. If the skill had requested unrelated env vars, network endpoints, or included an installer download, the assessment would change.
能力评估
Purpose & Capability
Name/description match the declared behavior: discovering Skills from local folders and SKILL_PATH, ranking candidates, building a plan graph, launching sub-tasks, merging results, and optionally emitting a JSON bundle. The declared config paths (~/.workbuddy/skills, .workbuddy/memory, ~/.claw/skills, project .workbuddy/skills) and SKILL_PATH env var are directly needed for skill discovery and are appropriate.
Instruction Scope
All runtime instructions in SKILL.md are focused on orchestration: parsing user intent, scanning SKILL.md frontmatter in the listed directories, optional ClawHub queries when local results < 2, composing task graphs, launching sub-agents, producing checkpoints, merging results, and optionally writing limited metadata to .workbuddy/memory. Note: there is an explicit 'bypassPermissions' mode triggered if the user says 'directly execute' which will skip confirmations — this is a functional choice but increases risk if used without care.
Install Mechanism
Instruction-only skill (no install script, no downloads, no code files executed). Lowest-risk install footprint — nothing will be written or fetched by an installer. The skill relies on host agent capabilities (file read, network) to operate as described.
Credentials
Only SKILL_PATH env var and well-scoped config paths are required. No API keys, tokens, or other secrets are requested. The declared memory write behavior is limited to session metadata and summaries (explicitly excludes keys/sensitive content).
Persistence & Privilege
always:false (no forced global inclusion). The skill may write small records to .workbuddy/memory (session_id, brief summary), which is declared. The main privilege to watch is the 'bypassPermissions' execution mode that can skip checkpoints when the user explicitly requests direct execution; combined with the agent's own tool access this could enable higher-risk actions without interactive confirmation.
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 skill-orchestrator - 安装完成后，直接呼叫该 Skill 的名称或使用
/skill-orchestrator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
v2.0.2
## skill-orchestrator v2.0.3
- Added references/machine-contract.md documenting optional machine-readable JSON outputs (`plan`/`events`/`merge`).
- Updated documentation to clarify and recommend – but not require – JSON report bundles for host/script integration.
- Expanded frontmatter with a `metadata.openclaw.requires` field listing possible config/env dependencies (e.g., `SKILL_PATH`, skills directories).
- Rewrote and reorganized markdown for improved clarity, cross-referencing new and existing reference docs.
- Documented that all file access (skills, memory) is optional—fallback to built-in skill matrix always applies if missing.
- No logic or API changes; this update is documentation- and protocol-focused.
v2.0.1
Initial publish (2.0.1): multi-skill orchestration playbook—intent parsing, skill discovery/scoring, parallel/serial plan templates, optional checkpoints, execution-style progress, result merge & conflict handling, safety/bypassPermissions rules, built-in fallbacks, and references (registry, engine, tracker, merger, human-in-the-loop). OpenClaw metadata (emoji, homepage). No runtime binaries required.
v2.0.0
技能编排器 v2.0 重大升级：
- 全新分步流程文档，详细覆盖意图解析、Skill发现、编排计划、执行追踪、结果整合等全环节。
- 新增执行模式、并联-串联调度、冲突检测与自动裁决、多Skill协作下的进度可视化。
- 增加 Checkpoint 用户确认节点，高风险操作支持暂停与计划编辑。
- 引入模拟/兜底Skill机制，确保在Skill不可用时仍可输出方案。
- 文档结构全面优化，覆盖更多典型场景，输出格式和边界限制更加清晰。
v1.0.0
- Initial release of Skill Orchestrator (技能编排器) version 1.0.
- Enables automatic parsing, decomposition, and orchestration of multiple expert Skills to fulfill complex user requests.
- Features an expert matrix across business, tech, content creation, legal, career, and emotional support fields.
- Implements intelligent task parsing, expert Skill matching, task orchestration, and integrated result delivery.
- Built-in priority and fallback strategies for efficient, reliable Skill scheduling.
- Includes safeguards for sensitive or high-risk scenarios, with clear boundaries and fallback suggestions.
元数据
常见问题
技能编排器 是什么？
Multi-skill orchestrator: decompose complex asks, discover skills, plan parallel/serial steps, checkpoints, merge outputs; optional JSON bundle for hosts. Us... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 122 次。
如何安装 技能编排器？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install skill-orchestrator」即可一键安装，无需额外配置。
技能编排器 是免费的吗？
是的，技能编排器 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
技能编排器 支持哪些平台？
技能编排器 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 技能编排器？
由 Windymonkeys（@windymonkeys）开发并维护，当前版本 v2.0.2。
推荐 Skills