What makes Agent Team Skill notable?

1.9K downloads. Trust evidence available

How should Agent Team Skill be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Agent Team Skill

Manage AI agent team members with roles, skills, and task delegation. Use when: listing team members, adding/updating agents, setting the team leader, checki...

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.9k

Updated

Oct 9, 2026

Version

2.1.9

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.9K downloads reported by the source. Last updated 10/9/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 9, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 9, 2026
Adoption signal: 1.9K downloadsadoption · observed Oct 9, 2026
Latest release: 2.1.9release · observed Mar 31, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17f355cjws1d88r3kn7t9jx9x83qfx7:agent-team-skill

Install using `clawhub skill install s17f355cjws1d88r3kn7t9jx9x83qfx7:agent-team-skill` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/realqiyan/agent-team-skill before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-realqiyan-agent-team-skill/snapshot"

Documentation

CLAWHUB

145,520 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: agent-team-skill
description: "Manage AI agent team members with roles, skills, and task delegation. Use when: listing team members, adding/updating agents, setting the team leader, checking who has specific expertise, delegating tasks to the right agent, or coordinating multi-agent workflows. Keywords: team member, agent list, leader, expertise, delegation, PDCA workflow."
license: MIT
homepage: https://github.com/realqiyan/agent-team-skill
allowed-tools: Bash(python3:*) Read(*.json)
compatibility: Requires Python 3.10+
metadata:
  clawdbot:
    emoji: "🤖"
    requires:
      bins:
        - python3
---

# Agent Team Skill

Manage AI agent team members with skills, roles, and task delegation.

## Team Members

List all team member information:

```bash
python3 scripts/team.py list
```

**Common scenarios:**
- Check who is the current team leader
- Find members with specific expertise before task assignment
- Review team structure and available roles

Output example:
```markdown
## Team Members

**Alice** ⭐ Leader - coordination,planning,decision-making
- agent_id: alice
- expertise: task breakdown, comprehensive decisions, agent coordination
- not_good_at: code development, investment analysis

**Bob** - Backend Developer - backend,API,database
- agent_id: bob
- expertise: Python,Go,PostgreSQL
- not_good_at: frontend,design

# Total: 2 member(s), Leader: Alice (alice)
```

### ⚡ Task Delegation Rules (Core Principle)

**Delegation Timing:**
1. First complete prep work: understand requirements, clarify goals, confirm constraints
2. When entering implementation: identify the best person for execution, delegate to them
3. Follow up after delegation: check output quality, ensure requirements are met

**Delegation Context (what to pass):**
When delegating, always provide:
- Original requirements and success criteria
- Relevant background and context
- Your execution plan and any constraints
- Expected output format

**Delegation Failover:**
If teammate fails to complete:
1. First attempt: Send back with specific feedback for revision
2. Second attempt: Reassign to another teammate with adjusted context
3. Third attempt: Escalate to leader OR execute yourself

## 🔄 Task Processing Flow (Highest Priority)

**Plan → Do → Check → Act**

**IMPORTANT: This is a continuous improvement cycle. If task is incomplete in Act phase, loop back to Plan.**

### 1. Plan — Planning Phase

**Goal: Prepare thoroughly, avoid blind execution**

- Understand requirements and clarify questions
- Define goals and success criteria
- Identify risks and determine ownership
- Create execution plan

### 2. Do — Execution Phase

**Goal: Execute the plan while maintaining progress**

- Execute or delegate based on ownership
- Track progress and key decisions

### 3. Check — Checking Phase

**Goal: Verify results against requirements**

- Verify completeness and quality
- Check compliance with standards

### 4. Act — Acting Phase

**Goal: Summarize and decide next steps*

integrations/openclaw/agent-team/README.md

# Agent Team Plugin

OpenClaw plugin that automatically injects team member information and collaboration rules into system context at session start.

## Why Use the Plugin?

The plugin provides these advantages over manually calling the skill:

1. **100% Reliable Loading**: Uses `before_prompt_build` hook to inject team information before session starts, no dependency on AI agent主动 calling tools
2. **Zero Startup Delay**: Team information is directly injected into system context without needing to guide AI to execute `python3 scripts/team.py list`
3. **Simplified Interaction**: AI agent gets team context directly, no extra steps needed

## What Gets Injected

The plugin injects:

- **Team Members**: Names, roles, expertise, and weaknesses
- **Leader Authority**: Approve task completion, reassign when delegation fails
- **Task Processing Flow**: Plan → Do → Check → Act (PDCA cycle)
- **Recording Rules**: Progress tracking in `memory/YYYY-MM-DD.md`
- **Task Delegation Rules**: Timing and process for delegating tasks to teammates

## Installation

### Method 1: Link to Global Extensions Directory (Recommended)

```bash
# Create symlink to OpenClaw global extensions directory
ln -s $(pwd) ~/.openclaw/extensions/agent-team
```

### Method 2: Specify Path in OpenClaw Config

Add to `~/.openclaw/config.json`:

```json
{
  "plugins": {
    "load": {
      "paths": ["/path/to/agent-team-skill/integrations/openclaw/agent-team"]
    },
    "entries": {
      "agent-team": {
        "enabled": true
      }
    }
  }
}
```

### Method 3: As Workspace Extension

Copy `integrations/openclaw/agent-team` directory to project's `.openclaw/extensions/` directory and enable in config:

```json
{
  "plugins": {
    "allow": ["agent-team"]
  }
}
```

## Configuration

Plugin supports these configuration options (set via `plugins.entries.agent-team.config`):

| Option | Type | Default | Description |
|--------|------|---------|-------------|
| `dataFile` | string | `~/.agent-team/team.json` | Team data file path |
| `enabled` | boolean | `true` | Enable or disable plugin |

Config example:

```json
{
  "plugins": {
    "entries": {
      "agent-team": {
        "enabled": true,
        "config": {
          "dataFile": "/custom/path/team.json"
        }
      }
    }
  }
}
```

## Data Format

Team data is stored in JSON format:

```json
{
  "team": {
    "agent-001": {
      "agent_id": "agent-001",
      "name": "Alice",
      "role": "Backend Developer",
      "is_leader": true,
      "enabled": true,
      "tags": ["backend", "database"],
      "expertise": ["python", "postgresql"],
      "not_good_at": ["frontend", "design"],
      "load_workflow": true,
      "group": "backend-team"
    }
  }
}
```

### New Fields (Optional)

| Field | Type | Default | Description |
|-------|------|---------|-------------|
| `load_workflow` | boolean | `true` for leader, `false` for others | Whether to inject PDCA workflow prompts |
| `group` | string | `null` | Group name for c

README.md

# Agent Team Skill

AI agent team management tool for managing team member information, including skills, roles, and task delegation.

**This skill must be used together with the OpenClaw plugin.**

## How It Works

The skill consists of two components that work together:

1. **Plugin** (`integrations/openclaw/agent-team/`) - OpenClaw native plugin that automatically injects team information and collaboration rules into system context at session start
2. **Skill** (`scripts/team.py`) - CLI tool for managing team member data (CRUD operations)

The plugin reads team data from `~/.agent-team/team.json` and injects it into the AI agent's context, enabling:
- Team member awareness
- Leader authority (approve completion, reassign tasks)
- PDCA workflow: Plan → Do → Check → Act
- Task delegation rules
- Progress recording in `memory/YYYY-MM-DD.md`

## Features

- 👥 **Member Management** - Manage team member information including skills, roles, and task assignment
- 👑 **Leader Authority** - Leader can approve task completion and reassign when delegation fails
- 🔄 **PDCA Workflow** - Plan → Do → Check → Act task processing cycle
- 📝 **Progress Recording** - Track task progress in `memory/YYYY-MM-DD.md`
- ⚡ **Auto Injection** - Plugin automatically loads team information at session start
- 🌐 **Global Sharing** - Team data is globally shared across sessions

## Installation

### Step 1: Install Plugin (Required)

The plugin must be installed for the skill to work properly.

```bash
# Method 1: Link to global extensions directory
ln -s $(pwd)/integrations/openclaw/agent-team ~/.openclaw/extensions/agent-team

# Method 2: Specify path in config
# Edit ~/.openclaw/config.json
```

Config example:
```json
{
  "plugins": {
    "load": {
      "paths": ["/path/to/agent-team-skill/integrations/openclaw/agent-team"]
    },
    "entries": {
      "agent-team": {
        "enabled": true
      }
    }
  }
}
```

For detailed configuration, see [integrations/openclaw/agent-team/README.md](./integrations/openclaw/agent-team/README.md).

### Step 2: Verify Python 3.10+

```bash
python3 --version
```

## Usage

### Managing Team Members

After installing the plugin, use the CLI to manage team data:

```bash
python3 scripts/team.py <command> [options]
```

| Command | Description |
|---------|-------------|
| `list` | List all members |
| `update` | Add/update member |
| `reset` | Reset member data |

### List Members

```bash
python3 scripts/team.py list
```

Output example:
```markdown
## Team Members

**Alice** ⭐ Leader - coordination,planning,decision-making
- agent_id: alice
- expertise: task breakdown, comprehensive decisions, agent coordination
- not_good_at: code development, investment analysis

**Bob** - Backend Developer - backend,API,database
- agent_id: bob
- expertise: Python,Go,PostgreSQL
- not_good_at: frontend,design

# Total: 2 member(s), Leader: Alice (alice)
```

### Add/Update Member

```bash
python3 scripts/team.py update \
  --agent-id "agent-00

_meta.json

{
  "ownerId": "kn77s9bqv0bx1q2n8stm9esqhd822r4p",
  "slug": "agent-team-skill",
  "version": "2.1.9",
  "publishedAt": 1774929725725
}

agent-team-skill-workspace/iteration-1/eval-1-list-members/with_skill/outputs/team-list-output.md

# Team Members List Output

## Command Executed
```bash
python3 /home/yhb/work/agent-team-skill/scripts/team.py list
```

## Output

## Team Members

**小Q** ⭐ Leader - 协调,统筹,决策,兜底
- agent_id: main
- expertise: 任务拆解与分配,上传下达,结果负责,批判思维,推进改进,质量把关,深度分析,综合决策,agent统筹协调,兜底解决问题
- not_good_at: 代码开发,投资分析,交易执行

**小码** - 开发主管 - 开发,编程,代码,架构
- agent_id: coder
- expertise: 需求分析,架构设计,方案设计,编码,代码审查,重构规划
- not_good_at: 投资相关问题,非开发类工作

**小谦** - 投资顾问 - 基金,期权,投资,持仓,策略,股票
- agent_id: qian
- expertise: 基金分析,股票技术分析,期权策略,持仓管理,投资组合分析,投资规划,组合回测,风险评估,财经资讯查询,股票价格查询,K线查询,技术指标查询,财经新闻查询
- not_good_at: 交易执行,下单操作,代码开发,非投资和金融类问题

**大钱** - 交易员 - 交易,执行,下单
- agent_id: trader
- expertise: 交易执行,下单操作,订单管理,仓位调整
- not_good_at: 投资分析,策略制定,代码开发,非交易类工作

**小权** - 期权策略分析师 - 期权,策略,深度分析
- agent_id: options
- expertise: 期权策略深度分析,波动率建模,多腿组合设计,风险收益模拟,Greeks敏感性分析
- not_good_at: 交易执行,非期权类问题

**Bob** - Backend Developer - backend,api,database
- agent_id: bob
- expertise: Python,Go
- not_good_at: frontend

# Total: 6 member(s), Leader: 小Q (main)

## Analysis

The team currently has 6 members:

| Name | Agent ID | Role | Leader | Tags | Key Expertise |
|------|----------|------|--------|------|---------------|
| 小Q | main | Leader | Yes | 协调,统筹,决策,兜底 | Task coordination, decision-making, quality control |
| 小码 | coder | 开发主管 | No | 开发,编程,代码,架构 | Architecture design, coding, code review |
| 小谦 | qian | 投资顾问 | No | 基金,期权,投资,持仓,策略,股票 | Investment analysis, portfolio management |
| 大钱 | trader | 交易员 | No | 交易,执行,下单 | Trade execution, order management |
| 小权 | options | 期权策略分析师 | No | 期权,策略,深度分析 | Options strategy, volatility modeling |
| Bob | bob | Backend Developer | No | backend,api,database | Python, Go |

### Key Observations
1. The team has a clear leader (小Q) who handles coordination and decision-making
2. Roles are well-defined with complementary expertise:
   - Development: 小码, Bob
   - Investment/Finance: 小谦, 大钱, 小权
   - Leadership/Coordination: 小Q
3. Each member has clear "not good at" areas for task delegation guidance
4. Data stored in: `~/.agent-team/team.json`

Github ReposUpdated 5h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.