← 返回 Skills 市场
tcbywing

Delegate Task

作者 tcbywing · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
107
总下载
0
收藏
5
当前安装
1
版本数
在 OpenClaw 中安装
/install delegate-task
功能描述
Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and sk...
使用说明 (SKILL.md)

Delegate Tasks to OpenSpace

OpenSpace is connected as an MCP server. You have 4 tools available: execute_task, search_skills, fix_skill, upload_skill.

When to use

  • You lack the capability — the task requires tools or capabilities beyond what you can access
  • You tried and failed — you produced incorrect results; OpenSpace may have a tested skill for it
  • Complex multi-step task — the task involves many steps, tools, or environments that benefit from OpenSpace's skill library and orchestration
  • User explicitly asks — user requests delegation to OpenSpace

Tools

execute_task

Delegate a task to OpenSpace. It will search for relevant skills, execute, and auto-evolve skills if needed.

execute_task(task="Monitor Docker containers, find the highest memory one, restart it gracefully", search_scope="all")
Parameter Required Default Description
task yes Task instruction in natural language
search_scope no "all" Local + cloud; falls back to local-only if no API key
max_iterations no 20 Max agent iterations — increase for complex tasks, decrease for simple ones

Check response for evolved_skills. If present with upload_ready: true, decide whether to upload (see "When to upload" below).

{
  "status": "success",
  "response": "Task completed successfully",
  "evolved_skills": [
    {
      "skill_dir": "/path/to/skills/new-skill",
      "name": "new-skill",
      "origin": "captured",
      "change_summary": "Captured reusable workflow pattern",
      "upload_ready": true
    }
  ]
}

search_skills

Search for available skills before deciding whether to handle a task yourself or delegate.

search_skills(query="docker container monitoring", source="all")
Parameter Required Default Description
query yes Search query (natural language or keywords)
source no "all" Local + cloud; falls back to local-only if no API key
limit no 20 Max results
auto_import no true Auto-download top cloud skills locally

fix_skill

Manually fix a broken skill.

fix_skill(
  skill_dir="/path/to/skills/weather-api",
  direction="The API endpoint changed from v1 to v2, update all URLs and add the new 'units' parameter"
)
Parameter Required Description
skill_dir yes Path to skill directory (must contain SKILL.md)
direction yes What's broken and how to fix — be specific

Response has upload_ready: true → decide whether to upload.

upload_skill

Upload a skill to the cloud community. For evolved/fixed skills, metadata is pre-saved — just provide skill_dir and visibility.

upload_skill(
  skill_dir="/path/to/skills/weather-api",
  visibility="public"
)

For new skills (no auto metadata — defaults apply, but richer metadata improves discoverability):

upload_skill(
  skill_dir="/path/to/skills/my-new-skill",
  visibility="public",
  origin="imported",
  tags=["weather", "api"],
  created_by="my-bot",
  change_summary="Initial upload of weather API skill"
)
Parameter Required Default Description
skill_dir yes Path to skill directory (must contain SKILL.md)
visibility no "public" "public" or "private"
origin no auto How the skill was created
parent_skill_ids no auto Parent skill IDs
tags no auto Tags
created_by no auto Creator
change_summary no auto What changed

When to upload

Situation Action
Skill was originally from the cloud Upload back as "public" — return the improvement to the community
Fix/evolution is generally useful Upload as "public"
Fix/evolution is project-specific Upload as "private", or skip
User says to share Upload with the visibility the user wants

Notes

  • execute_task may take minutes — this is expected for multi-step tasks.
  • upload_skill requires a cloud API key; if it fails, the evolved skill is still saved locally.
  • After every OpenSpace call, tell the user what happened: task result, any evolved skills, and your upload decision.
安全使用建议
This skill delegates work to an external OpenSpace MCP and can download and upload local skill directories. Before installing or using it: (1) ask the publisher which cloud endpoint it talks to and which environment variable name(s) it expects for API keys; (2) prefer running it in a sandbox or with filesystem restrictions so only a dedicated skills folder (no sensitive files) is accessible; (3) disable or set search_scope to "local" if you don't want cloud lookups/imports; (4) if you must provide an API key, create a limited-scope key and avoid reusing broad credentials; (5) require manual review/confirmation before any upload and set upload visibility to private by default; (6) if the publisher cannot explain credential names, endpoints, and upload governance, treat the skill as untrusted.
功能分析
Type: OpenClaw Skill Name: delegate-task Version: 1.0.0 The skill provides high-risk capabilities for autonomous task execution and cloud-based code sharing via the 'OpenSpace' MCP server. Key concerns include the `upload_skill` tool, which can exfiltrate local directories to a cloud community, and the `search_skills` tool's `auto_import` feature, which automatically downloads and executes remote code. While these functions align with the stated goal of a 'collective' agent ecosystem, the inherent risks of remote code execution (RCE) and data exfiltration through the `execute_task` and `upload_skill` tools in SKILL.md warrant a suspicious classification.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
Name and description match the behaviour described in SKILL.md (delegation to an external MCP with tools to search, execute, fix, and upload skills). However, the skill assumes connectivity to a cloud MCP and the presence of a cloud API key for search/upload operations but declares no required environment variables or endpoints. That omission is an incoherence: legitimate cloud integration would normally declare which credential(s) are needed and/or which endpoint is used.
Instruction Scope
The instructions direct the agent to read and write local skill directories (skill_dir paths), auto-download cloud skills locally (auto_import), and upload local directories to a community cloud. Those operations involve filesystem access and network transfer of potentially sensitive code/data. The SKILL.md gives broad discretion to 'decide whether to upload' evolved skills but provides no guardrails for excluding secrets or sensitive files, nor does it name the cloud endpoint or credential variable(s). This broad, underspecified scope increases risk of accidental exfiltration.
Install Mechanism
This is an instruction-only skill with no install spec and no code files, so there is no installer or archive to fetch. The install surface is minimal; the main risk comes from runtime actions (downloads/uploads), not from an installer.
Credentials
SKILL.md references a 'cloud API key' and fallback behavior when no API key is present, but requires.env and primary credential fields are empty. The skill therefore fails to declare the credentials it will need at runtime. Because it can upload local directories to the cloud, requesting an unspecified API key without naming scopes or constraints is disproportionate and ambiguous.
Persistence & Privilege
The skill does not request always:true and uses the platform default allowing autonomous invocation. It will save evolved/fixed skills locally and can upload them to the community (persisting them externally). That behaviour is coherent with its purpose but is a significant privilege: it can create files and transmit them off-host. Users should be aware that uploads may be public unless visibility is set to private.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install delegate-task
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /delegate-task 触发
  4. 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 delegate-task skill for OpenSpace integration. - Enables task delegation to OpenSpace for coding, DevOps, web research, and desktop automation. - Provides four tools: execute_task, search_skills, fix_skill, and upload_skill. - Includes guidance on when to delegate, search, fix, or upload skills. - Outlines best practices for sharing skill improvements with the cloud community.
元数据
Slug delegate-task
版本 1.0.0
许可证 MIT-0
累计安装 5
当前安装数 5
历史版本数 1
常见问题

Delegate Task 是什么?

Delegate tasks to OpenSpace — a full-stack autonomous worker for coding, DevOps, web research, and desktop automation, backed by an extensive MCP tool and sk... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 107 次。

如何安装 Delegate Task?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install delegate-task」即可一键安装,无需额外配置。

Delegate Task 是免费的吗?

是的,Delegate Task 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Delegate Task 支持哪些平台?

Delegate Task 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 Delegate Task?

由 tcbywing(@tcbywing)开发并维护,当前版本 v1.0.0。

💬 留言讨论