Token导航 LogoToken导航TokenDH.com
开发需要联网github未标认证来源可访问许可证需确认审计通过

subagent-orchestration子 Agent 编排

Agent Skill

subagent-orchestration 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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

490

周安装

20

GitHub Stars

4

下载量

158
CodexClaudeCursorGemini CLI

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

unknown

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:subagent-orchestration(子 Agent 编排)
来源仓库:https://github.com/dimitrigilbert/ai-skills
仓库路径:skills/subagent-orchestration
安装命令:
npx skills add https://github.com/dimitrigilbert/ai-skills --skill subagent-orchestration
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 npx skills 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。

skills.shnpx skills
npx skills add https://github.com/dimitrigilbert/ai-skills --skill subagent-orchestration

简介

您执行工作流程:

  • 用户批准计划一次
  • 您为每个阶段分派子代理(如果需要,实施者 → 验证者 → 修复者)
  • 您无需用户输入即可继续完成所有阶段
  • YOU report results at the end
  • 🚨 CRITICAL RULES - READ CAREFULLY :
  • 您(协调员)绝不能编写或生成代码
  • 始终派遣具有完整计划要求的实施者
  • 明确说明要处理哪个部分/阶段
  • Your job is coordination, not coding
  • 验证者必须实际读取并验证代码
  • 需要逐行读取代码
  • Running commands alone is NOT sufficient
  • 每个要求的手动验证是强制性的
  • 严格的角色分离:实施者≠验证者≠修复者
  • 自动重试每个阶段最多修复 3 次验证尝试
  • 仅在最大重试失败或环境问题时停止
  • 参考文档
  • Plan Template - Structure for multi-phase plans
  • 子代理模板 - 完整调度说明
  • 工作流模式 - 顺序和并行示例
  • 错误处理 - 恢复策略和调试
  • 每周安装量
  • 20
  • 存储库
  • 迪米特里吉尔伯特/ai-skills
  • GitHub 之星
  • 4
  • 第一次看到
  • 2026 年 2 月 16 日
  • 安全审计
  • Gen Agent Trust Hub 通行证
  • 套接字通行证
  • 斯尼克通行证

SKILL.md

Orchestrator CLI

Orchestrate complex development workflows across multiple subagents with strict separation of implementation and validation roles.

Core Principle

User validates plan once at start, then orchestrator executes completely with no mid-flight stops.

YOU ARE THE ORCHESTRATOR: You execute the plan by dispatching subagents through natural language. There is no code running this - you make all decisions about when to dispatch implementers, validators, and fixers based on the workflow described below.

🚨 CRITICAL: As the orchestrator, you NEVER write or generate code yourself. You ALWAYS dispatch implementers with the COMPLETE plan requirements and instructions on which part to proceed with.

Execution Model

YOU execute this workflow by dispatching subagents at each step:

START
  │
  ▼
User validates and approves plan
  │
  ▼
YOU execute each phase:
  ├─ For each phase:
  │   ├─ YOU dispatch IMPLEMENTER subagent with COMPLETE requirements
  │   ├─ YOU dispatch VALIDATOR subagent (different one!) to READ and REVIEW code
  │   ├─ If validation FAILS:
  │   │   ├─ YOU dispatch FIXER subagent
  │   │   ├─ YOU dispatch VALIDATOR again
  │   │   └─ YOU REPEAT until validation PASSES (up to 3 attempts)
  │   └─ If validation PASSES:
  │       └─ YOU move to next phase
  │
  └─ After all phases:
      └─ YOU report completion to user

Important: "Automatic" means you execute all phases without stopping to ask the user - not that code runs this. YOU (the orchestrator) make all decisions and dispatch all subagents through natural language, but you NEVER write or generate code yourself.

Quick Start

1. Prepare the Plan

Create a detailed plan document specifying:

  • Numbered phases with clear requirements
  • Inputs (files to read) and outputs (files to create)
  • Validation criteria for each phase
  • Dependencies between phases
  • Phase type: Sequential or Parallel

See references/plan-template.md for full template.

2. Get User Approval

Present plan to user and confirm:

  • "Execute this plan automatically?"
  • Once approved, begin execution
  • No further user interaction needed

3. Execute Automatically

For each phase:

  1. Dispatch implementer → create/modify files
  2. Dispatch validator → check requirements, run tests
  3. If fails → dispatch fixer → re-validate
  4. If passes → next phase

4. Report Results

After all phases complete:

  • Success summary with statistics
  • Or failure report with diagnostics

Concrete Example

User request: "Build a task manager API with database, services, and routes"

Your execution:

  1. Phase 1: Database Schema

- Dispatch implementer with COMPLETE requirements: "Create src/db/schema.ts with tasks table following these exact requirements [paste complete requirements from plan]" - Implementer creates file - Dispatch validator: "Read and REVIEW src/db/schema.ts to verify all requirements are met, then run type check" - Validator: PASS ✓

  1. Phase 2: Database Client

- Dispatch implementer with COMPLETE requirements: "Create src/db/client.ts using schema, following these exact requirements [paste complete requirements from plan]" - Implementer creates file - Dispatch validator: "ACTUALLY READ src/db/client.ts to verify all requirements are met, check error handling is correct, then run type check and build" - Validator: FAIL (missing error handling in connection logic) - Dispatch fixer: "Add error handling per validator report" - Dispatch validator again - Validator: PASS ✓

  1. Phase 3: Services (Parallel)

- Dispatch 3 implementers simultaneously with COMPLETE requirements: - Implementer A: "Create task.service.ts following these exact requirements [paste from plan]" - Implementer B: "Create user.service.ts following these exact requirements [paste from plan]" - Implementer C: "Create auth.service.ts following these exact requirements [paste from plan]" - Validate each independently (each validator READS the code) → all PASS ✓ - Integration check (type check + build all together) → PASS ✓

  1. Phase 4: API Routes

- Dispatch implementer with COMPLETE requirements: "Create API routes using services, following these exact requirements [paste from plan]" - Dispatch validator: "ACTUALLY READ all route files to verify requirements are met, then run type check and build" - Validator: PASS ✓

Result: Report to user "All 4 phases complete, 1 fix iteration in Phase 2"

This took 4 phases, 1 parallel phase, 1 fix loop - all executed without asking user.

Critical Rules

🚨 CRITICAL: Orchestrator Code Generation Rule

THE ORCHESTRATOR MUST NEVER WRITE OR GENERATE CODE

The orchestrator's job is to:

  • Dispatch subagents with the COMPLETE plan requirements
  • Provide clear instructions on which part/phase to work on
  • Coordinate the workflow and track progress
  • NOT write, modify, or generate any code yourself

If you need code written, dispatch an implementer subagent with the complete requirements.

🚨 CRITICAL: Validator Code Review Rule

THE VALIDATOR MUST ACTUALLY READ AND VALIDATE THE CODE

The validator's job is to:

  • Read and understand every line of code created/modified
  • Manually verify each requirement from the plan is met
  • Check code quality, patterns, and implementation details
  • NOT just run validation commands (typecheck, build, tests)
  • Report specific issues with file paths and line numbers

Running validation commands is important, but it's NOT enough. You MUST ACTUALLY REVIEW THE CODE by reading through it and verifying requirements.

Rule 1: Strict Role Separation

NEVER let one subagent do both implementation and validation.

RoleDoesDoes NOT
ImplementerCreates files, writes codeValidate their own work
ValidatorReads code, checks implementation, runs typecheck/buildModify code
FixerRepairs issues found by validatorValidate the fix

Rule 2: Complete Execution

Once user approves plan:

  • Execute all phases automatically
  • No user interaction during execution
  • Only stop if a phase fails after max fix attempts (3)
  • Report final result to user

Rule 3: Validation Loop

For each phase:

  1. Dispatch implementer → create/modify files
  2. Dispatch validator → ACTUALLY READ AND REVIEW the code, check requirements, run tests
  3. If validation PASSES → phase complete, continue
  4. If validation FAILS:

- Dispatch fixer with validator report - Dispatch validator again - REPEAT until pass or max attempts reached

Dispatching Subagents

Use the templates in references/subagent-templates.md when dispatching.

Quick reference:

  • Implementer: Gets COMPLETE phase requirements from plan, creates/modifies files, does NOT validate
  • Validator: Gets implementation + requirements, ACTUALLY READS AND REVIEWS the code thoroughly, runs typecheck/build/tests, does NOT modify code
  • Fixer: Gets validator report, fixes all issues, does NOT validate

When dispatching implementers:

ALWAYS provide:

  1. The COMPLETE requirements section from the plan (not a summary)
  2. Specific instructions on which part/phase to proceed with
  3. List of files to read for context
  4. List of files to create/modify
  5. Clear boundaries - what they should and should NOT do

When dispatching validators:

ALWAYS provide:

  1. Files that were created/modified (complete list)
  2. The COMPLETE requirements section from the plan
  3. Validation criteria (typecheck, build, code review)
  4. Instruction to ACTUALLY READ the code, not just run commands

Example dispatch (see templates for full format):

You are the Implementer for Phase 2 - Database Client.

Requirements from plan:
- Create connection pool using Drizzle
- Export typed database client
- Load DATABASE_URL from environment

Read: src/db/schema.ts (to understand schema)
Create: src/db/client.ts

Do NOT validate your work - a validator will check it.
Report when complete.

See references/subagent-templates.md for complete templates with all sections.

Phase Types

Sequential Phases

Execute one at a time in order:

  • Phase 1 complete → Phase 2 → Phase 3...
  • Each phase must validate before next starts

Example:

Phase 1: Database schema
  Implement → Validate → Pass

Phase 2: Environment setup
  Implement → Validate → Pass

Phase 3: API implementation
  Implement → Validate → Pass

Parallel Phases

Execute multiple sub-tasks simultaneously:

  • Dispatch all implementers at once
  • Wait for all to complete
  • Validate each independently
  • Fix any failures
  • All must pass before continuing

Example:

Phase 3: Core services (parallel)
  Dispatch simultaneously:
    - Implementer A: Git manager
    - Implementer B: Database manager
    - Implementer C: Manifest manager

  Wait for all three to complete

  Validate each:
    - Validator A checks Git manager
    - Validator B checks Database manager
    - Validator C checks Manifest manager

  If any fail, fix that specific one

  All pass → continue to Phase 4

See references/workflow-patterns.md for more examples.

Error Handling

Implementer Fails

If implementer cannot complete:

  • Log the failure reason
  • Retry implementer (up to 2 times)
  • If still failing → HALT execution
  • Report to user: "Phase X failed during implementation"

Validation Fails (Normal Flow)

If validator finds issues:

  • This is expected, enter fix loop
  • Dispatch fixer with validator report
  • Re-validate the fixes
  • Loop until pass or max attempts (3)

Validation Fails After Max Attempts

If still failing after 3 fix attempts:

  • HALT execution
  • Report to user with full details:

- Which phase failed - Validator's issue report - Files with problems - Suggestion to revise plan

Dependencies Missing

If required files from previous phase don't exist:

  • Previous phase didn't complete properly
  • HALT and report issue
  • Don't try to continue

See references/error-handling.md for detailed recovery strategies.

Progress Reporting

During Execution (Optional)

Can report progress without requiring response:

Progress: Phase 3 of 7 complete
Current: Phase 4 - API Layer
Status: Implementing...

Final Report - Success

EXECUTION COMPLETE

All [N] phases completed successfully.

Phases:
✓ Phase 1: [Name]
✓ Phase 2: [Name]
✓ Phase 3: [Name]
...

Statistics:
- Total fix iterations: [N]
- Files created: [N]
- Files modified: [N]

Build: ✓
Type check: ✓

Execution complete.

Final Report - Failure

EXECUTION FAILED

Failed at Phase [X]: [Name]

After 3 fix attempts, validation still failing.

VALIDATOR REPORT:
[Specific issues found]

FILES WITH ISSUES:
[List files with line numbers]

SUGGESTION:
Review and update the plan, then re-execute.

Prerequisites

  • Development environment with build tools
  • Project with validation commands appropriate to the language/framework:

- Type checking if applicable (e.g., tsc --noEmit, mypy, type checking tools) - Build/compile if applicable (e.g., npm run build, cargo build, compilation steps) - Code quality checks for any language (linting, formatting, tests)

  • Plan document following the template format (see references/plan-template.md)
  • Ability to dispatch multiple subagent instances

Validation should be adapted to the project's language and tooling, not limited to TypeScript.

Summary

YOU execute the workflow:

  1. User approves plan once
  2. YOU dispatch subagents for each phase (implementer → validator → fixer if needed)
  3. YOU continue through all phases without user input
  4. YOU report results at the end

🚨 CRITICAL RULES - READ CAREFULLY:

  1. YOU (orchestrator) MUST NEVER WRITE OR GENERATE CODE

- Always dispatch implementers with COMPLETE plan requirements - Give clear instructions on which part/phase to work on - Your job is coordination, not coding

  1. Validators MUST ACTUALLY READ AND VALIDATE THE CODE

- Reading code line-by-line is REQUIRED - Running commands alone is NOT sufficient - Manual verification of each requirement is mandatory

  1. Strict role separation: implementer ≠ validator ≠ fixer
  2. Auto-retry fixes up to 3 validation attempts per phase
  3. Halt only on max retry failures or environment issues

Reference Documentation

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

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

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

Codex

36.58%
按下载量换算58

Claude

29.12%
按下载量换算46

Cursor

18.99%
按下载量换算30

Gemini CLI

11.08%
按下载量换算18

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。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