Token导航 LogoToken导航

Agent Skill · 开发

project-coordinator(项目协调员)

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。

project-coordinator 是开发类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在开发类的 21,746 个 Skill 里排第 6,297。

总安装 4,892周安装 208GitHub Stars 公开资料未说明下载 1,714核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.13

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

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

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。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install project-coordinator;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

project-coordinator 怎么安装?

在终端执行 openclaw skills install project-coordinator。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

project-coordinator 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

project-coordinator 需要什么权限?

权限级别是接触敏感数据。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。

project-coordinator 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

project-coordinator 用的人多吗?

公开数据是累计安装 4,892 次,近一周安装 208 次,下载 1,714 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

project-coordinator 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
project-coordinator

项目协调员 · 本页

4,892—接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

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

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

接触敏感数据

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills