Token导航 LogoToken导航TokenDH.com
开发敏感数据clawhub未标认证来源可访问clear审计提醒

project-coordinator项目协调员

Agent Skill

project-coordinator 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

4,892

周安装

208

GitHub Stars

公开资料未说明

下载量

1,714
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:project-coordinator(项目协调员)
来源仓库:https://github.com/kaigegao1110/project-coordinator
安装命令:
openclaw skills install project-coordinator
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install project-coordinator

简介

生成一个独立的项目协调器会话,该会话拥有项目的上下文,将工作分解为任务,并生成用于并行执行的子代理。

SKILL.md

name
project-coordinator
version
1.0.12
homepage
https://github.com/KaigeGao1110/Project-Coordinator
description
|
dependencies
required
{}
configPaths
[]
permissions
dataPolicy
archivedData
internal workspace only
neverExternal
true

Installation

Option 1: ClawhHub CLI (recommended)

openclaw skills install project-coordinator
# or
clawhub install project-coordinator

Option 2: From GitHub

# Clone the repo
git clone https://github.com/KaigeGao1110/Project-Coordinator.git ~/.openclaw/skills/project-coordinator

# Or download directly
curl -L https://github.com/KaigeGao1110/Project-Coordinator/archive/refs/heads/main.zip -o /tmp/project-coordinator.zip
unzip /tmp/project-coordinator.zip -d ~/.openclaw/skills/
mv ~/.openclaw/skills/Project-Coordinator-main ~/.openclaw/skills/project-coordinator

Project Coordinator Skill

A skill for structuring multi-agent project execution with isolated session architecture.


Manifest

name: project-coordinator
version: 1.0.11
description: |
  Spawns an isolated Project Coordinator session that owns a project's context,
  breaks work into tasks, and spawns subagents for parallel execution.
  The Coordinator reports back to the main session when done.
permissions:
  - spawn: subagent sessions (via sessions_spawn)
  - read: workspace files
  - exec: shell commands via subagents
dataPolicy:
  archivedData: internal workspace only
  neverExternal: true

Architecture

Main Session (never runs code directly)
  └── Project Coordinator (spawned per project, mode="run")
        └── Subagents (spawned by Coordinator, run tasks in parallel)

Token efficiency: Each project Coordinator is isolated. Old project sessions accumulate zero main-session tokens after completion.

Least-privilege design: The Coordinator does NOT read session transcript files directly. All transcript reading, sanitization, and archiving is delegated to a dedicated archive-subagent using the archive-project skill.


Trigger Conditions

Activated when:

  • User says "start a new project" or "let's work on [project]"
  • A task is complex and needs multiple subagents
  • A task will take more than a few minutes
  • When user says "archive this" after a project is done → spawn archive-subagent

Do NOT activate for: quick questions, simple lookups, one-liner tasks.

Trigger 3: Slash command

Type //start followed by your project description to activate the Project Coordinator. Example: "//start build a Chrome extension"


Project Coordinator Pattern

Step 1: Define the Project

Collect from the user:

  • Project name (e.g., "cureforge-hr-assessment")
  • Project description (1-2 sentences)
  • Key deliverables
  • Any known constraints

Step 2: Spawn Project Coordinator

sessions_spawn(
  task=f"""You are the Project Coordinator for {project_name}.

Project: {project_description}

Your job:
1. Understand the full scope of this project
2. Break it into independent tasks
3. Spawn subagents to execute tasks in parallel
4. Monitor subagent progress
5. Compile results and report back to main session

When done, write a summary and await further instructions.
""",
  label=f"coordinator-{project_name}",
  runtime="subagent",
  model="minimax-m2.7-highspeed",
  mode="run"
)

Step 3: Monitor Progress

  • Use subagents(action="list") to track subagent status
  • Receive completion announcements via inter-session messages
  • If a subagent fails, decide whether to retry or adapt

Step 4: Compile and Report

When all subagents complete:

  1. Review all outputs
  2. Write a final summary
  3. Save any deliverables before the Coordinator session ends

Step 5: Archiving (Delegated)

When a project is complete and archiving is requested:

  1. The Coordinator spawns an archive-subagent
  2. The archive-subagent uses the archive-project skill to handle:

- Locating the correct session transcripts - Sanitizing credentials - Writing ARCHIVE.md - Committing to workspace

  1. The Coordinator monitors the archive-subagent and reports completion

The Coordinator itself does NOT read session transcript files directly.


Coordinator's Tool Usage

Note: The Coordinator should NOT directly read, copy, move, or delete session transcript files. All such operations must be performed by a dedicated archive-subagent using the archive-project skill.

Subagent sandboxing: When spawning subagents, each subagent runs in an isolated sandbox with workspace-only filesystem access. Subagents cannot access credentials, environment variables, or session transcripts outside their scope. Network access is restricted per platform policy.

The Coordinator SHOULD directly call tools:

  • exec — run commands, check files
  • write — create output files
  • read — examine code or documents
  • sessions_spawn — spawn subagents for parallel work
  • subagents — monitor subagent status

Subagent Naming Convention

Format: {project}-{role}

Examples:

  • cureforge-gke-migration
  • cureforge-rabbitmq-queue
  • cureforge-review

Session Management Rules

  • One Coordinator per project (isolated token accounting)
  • Do NOT run multiple unrelated projects in one Coordinator
  • When a project is complete, the Coordinator stops — no lingering sessions
  • For long-running projects: Coordinator can spawn child Coordinators for sub-phases

After Project Completion

  1. Report completion to Main session (brief summary)
  2. Notify the user
  3. User decides: archive / continue / hold

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

72.66%
按下载量换算1,245

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills