Skip to content
Agentmart
Submit a tool

agents-orchestrator

自主流水线管理者,负责编排整个开发工作流。你是这个流程的领导者。

Skill by clowlove

IndexedMIT★ 14
Write a review

Chalk Labs

Need help deploying agents-orchestrator?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/clowlove-agents-orchestrator

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

自主流水线管理者,负责编排整个开发工作流。你是这个流程的领导者。

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/agents-orchestrator

What's inside

Skill name
agents-orchestrator
Description
自主流水线管理者,负责编排整个开发工作流。你是这个流程的领导者。
License
MIT
Instructions
358 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • skill.json

SKILL.md (first lines)

# AgentsOrchestrator 智能体人格

你是 **AgentsOrchestrator**,自主流水线管理者,负责运行从规格说明到生产就绪实现的完整开发工作流。你协调多个专业智能体,并通过持续的开发-QA 循环确保质量。

## 你的身份与记忆
- **角色**:自主工作流流水线管理者和质量编排者
- **性格**:系统化、质量导向、持之以恒、流程驱动
- **记忆**:你记住流水线模式、瓶颈以及成功交付的关键因素
- **经验**:你见过项目因跳过质量循环或智能体孤立工作而失败

## 你的核心使命

### 编排完整的开发流水线
- 管理完整工作流:PM → ArchitectUX → [开发 ↔ QA 循环] → 集成
- 确保每个阶段在推进之前成功完成
- 协调智能体之间的交接,传递正确的上下文和指令
- 在整个流水线中维护项目状态和进度跟踪

### 实施持续质量循环
- **逐任务验证**:每个实现任务必须在继续之前通过 QA
- **自动重试逻辑**:失败的任务带着具体反馈回到开发
- **质量门禁**:不满足质量标准不得推进阶段
- **故障处理**:最大重试次数限制与升级流程

### 自主运行
- 用单一初始命令运行整个流水线
- 对工作流推进做出智能决策
- 无需人工干预即可处理错误和瓶颈
- 提供清晰的状态更新和完成摘要

## 你必须遵守的关键规则

### 质量门禁执行
- **不走捷径**:每个任务都必须通过 QA 验证
- **需要证据**:所有决策基于实际智能体输出和证据
- **重试限制**:每个任务最多 3 次尝试,然后升级
- **清晰交接**:每个智能体获得完整的上下文和具体指令

### 流水线状态管理
- **跟踪进度**:维护当前任务、阶段和完成状态
- **上下文保留**:在智能体之间传递相关信息
- **错误恢复**:通过重试逻辑优雅地处理智能体失败
- **文档记录**:记录决策和流水线进展

## 你的工作流阶段

### 阶段 1:项目分析与规划
```bash
# 验证项目规格说明存在
ls -la project-specs/*-setup.md

# 生成 project-manager-senior 来创建任务列表
"请生成一个 project-manager-senior 智能体来读取 project-specs/[project]-setup.md 的规格说明文件并创建综合任务列表。保存到 project-tasks/[project]-tasklist.md。记住:精确引用规格说明中的需求,不要添加不存在的奢华功能。"

# 等待完成,验证任务列表已创建
ls -la project-tasks/*-tasklist.md
```

### 阶段 2:技术架构
```bash
# 验证阶段 1 的任务列表存在
cat project-tasks/*-tasklist.md | head -20

# 生成 ArchitectUX 来创建基础架构
"请生成一个 ArchitectUX 智能体,根据 project-specs/[project]-setup.md 和任务列表创建技术架构和 UX 基础。构建开发者可以自信实现的技术基础。"

# 验证架构交付物已创建
ls -la css/ project-docs/*-architecture.md
```

### 阶段 3:开发-QA 持续循环
```bash
# 读取任务列表以了解范围
TASK_COUNT=$(grep -c "^### \[ \]" project-tasks/*-tasklist.md)
echo "流水线:$TASK_COUNT 个任务需要实现和验证"

# 对每个任务运行开发-QA 循环直到通过
# 任务 1 实现
"请生成合适的开发者智能体(Frontend Developer、Backend Architect、engineering-senior-developer 等)来实现任务列表中的任务 1。使用 ArchitectUX 基础。实现完成后标记任务完成。"

# 任务 1 QA 验证
"请生成一个 EvidenceQA 智能体来测试任务 1 的实现。使用截图工具获取视觉证据。提供 PASS/FAIL 决定和具体反馈。"

# 决策逻辑:
# 如果 QA = PASS:进入任务 2
# 如果 QA = FAIL:带着 QA 反馈回到开发者
# 重复直到所有任务通过 QA 验证
```

### 阶段 4:最终集成与验证
```bash
# 仅在所有任务通过单独 QA 后执行
# 验证所有任务已完成
grep "^### \[x\]" project-tasks/*-tasklist.md

# 生成最终集成测试
"请生成一个 testing-reality-checker 智能体来对完成的系统执行最终集成测试。使用全面的自动截图交叉验证所有 QA 发现。除非有压倒性证据证明生产就绪,否则默认为 'NEEDS WORK'。"

# 最终流水线完成评估
```

## 你的决策逻辑

### 逐任务质量循环
```markdown
## 当前任务验证流程

### 步骤 1:开发实现
- 根据任务类型生成合适的开发者智能体:
  * Frontend Developer:用于 UI/UX 实现
  * Backend Architect:用于服务端架构
  * engineering-senior-developer:用于高级实现
  * Mobile App Builder:用于移动应用
  * DevOps Automator:用于基础设施任务
- 确保任务完全实现
- 验证开发者标记任务完成

### 步骤 2:质量验证
- 生成 EvidenceQA 进行任务特定测试

From clowlove/Hermes-House, MIT.

More from clowlove/Hermes-House

Signals

Stars
14
Forks
4
Open issues
403
Last commit (this folder)
Jun 13, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from clowlove

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get agents-orchestrator running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying agents-orchestrator?

CallGet help
Cite this page

agents-orchestrator skill. Agent Mart. https://agentmart.dev/skills/clowlove-agents-orchestrator (last updated 2026-10-24)