← 返回 Skills 市场
Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.
8786
总下载
12
收藏
68
当前安装
1
版本数
在 OpenClaw 中安装
/install task-decomposer
功能描述
Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.
安全使用建议
Install only if you want an agent to help plan workflows and discover skills. Before letting it install or create anything, review each proposed skill source, avoid automatic `-g -y` installs, confirm required credentials or scheduled jobs, and keep a way to remove any added skills.
功能分析
Type: OpenClaw Skill
Name: task-decomposer
Version: 1.0.0
The skill 'task-decomposer' is designed to help the AI agent break down complex tasks, identify required capabilities, search for existing skills on skills.sh, and generate new skills. The `SKILL.md` provides detailed instructions for the agent on how to perform these steps, including using `npx skills find`, `npx skills add`, and `npx skills init` commands, which are legitimate tools within the OpenClaw ecosystem. There is no evidence of prompt injection attempting to subvert the agent's behavior, exfiltrate data, execute arbitrary malicious code, or establish persistence. All commands and URLs (e.g., `https://skills.sh`, `https://github.com/clawdbot-skills/task-decomposer`) are clearly stated and align with the skill's documented purpose.
能力评估
Purpose & Capability
The stated purpose matches the artifact: task decomposition, capability mapping, skill discovery, and skill creation. The concern is that installing or creating skills can persistently change the agent's future capabilities.
Instruction Scope
Activation is broad for complex multi-step requests, and the workflow includes external skill search plus install/create recommendations. Skill creation requires confirmation in a final note, but install approval is not clearly required.
Install Mechanism
The documentation repeatedly uses global noninteractive install commands such as `npx skills add <owner/repo@skill> -g -y`, which can install third-party skills without an explicit review checkpoint.
Credentials
Network search, code execution, scheduling, credentials, and API integrations are proportionate for an automation planner, but each follow-on capability should be scoped to the user's request.
Persistence & Privilege
Global skill installation, generated skill files, and scheduled-job planning may persist beyond the current task; rollback, source review, and confirmation steps are under-specified.
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 task-decomposer - 安装完成后，直接呼叫该 Skill 的名称或使用
/task-decomposer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
v1.0.0
Initial release of the Task Decomposer & Skill Generator.
- Decomposes complex user requests into atomic, executable subtasks with clear dependencies.
- Identifies required capabilities for each subtask using a universal capability taxonomy.
- Searches for existing skills on skills.sh to fulfill each subtask; recommends installation or new skill creation if needed.
- Provides comprehensive templates and instructions for creating new skills when gaps are identified.
- Supports automation of multi-step workflows and aids workflow planning by generating clear execution plans.
元数据
常见问题
Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces. 是什么？
Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 8786 次。
如何安装 Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install task-decomposer」即可一键安装，无需额外配置。
Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces. 是免费的吗？
是的，Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces. 完全免费（开源免费），可自由下载、安装和使用。
Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces. 支持哪些平台？
Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces. 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 Decomposes complex user requests into executable subtasks, identifies required capabilities, searches for existing skills at skills.sh, and creates new skills when no solution exists. This skill should be used when the user submits a complex multi-step request, wants to automate workflows, or needs help breaking down large tasks into manageable pieces.？
由 10e9928a（@10e9928a）开发并维护，当前版本 v1.0.0。
推荐 Skills