subagents-orchestration-guide SKILL.md skillA

subagents-orchestration-guide from shinpr/ai-coding-project-boilerplate is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

mdr add shinpr/ai-coding-project-boilerplate/subagents-orchestration-guide@git:20261003.24e6460

Pins git:20261003.24e6460 in mdr.lock. Pin the fingerprint instead.

Audit grade

A, 17 of 17 checks passed

Kind

SKILL.md skill

Repository

shinpr/ai-coding-project-boilerplate

Path

.claude/skills-zh-CN/subagents-orchestration-guide/SKILL.md

Versions recorded

5

Latest version

git:20261003.24e6460, committed Oct 3, 2026

First version recorded

Sep 12, 2026

Size

30,339 bytes

Repository stars

234

License

MIT

通过基于规模的规划、审批、实现、验证和上报流程协调子智能体。用于将工作路由给子智能体、执行已批准的工作计划，或恢复自主执行时使用。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 子智能体实用指南 - 我（Claude）的编排准则

## 核心原则：我是编排者

**明确的用户指示**：用户明确指示并授权已调用流程中命名的每一次子智能体调用。当前置条件满足时，执行每一个适用的调用。

### 必需的行动
- **新的全周期任务**：从 requirement-analyzer 开始，然后收敛需求，并根据其依据选择结构规模（Structural Scale）
- **流程执行期间**：遵循所选的规模流程及其转换条件
- **每个阶段**：将该阶段委派给其声明职责与其产出匹配的智能体
- **停止点**：仅在用户于该停止点确认后才继续
- **调查**：将所有调查委派给 requirement-analyzer 或 codebase-analyzer（Grep/Glob/Read 是专家内部工具）
- **分析/设计**：委派给其声明职责包含所需产出的专家
- **首个行动**：对于新的全周期任务，在任何其他步骤之前，将用户需求传递给 requirement-analyzer

### 首个行动规则

在收到新的全周期任务时，将用户需求传递给 requirement-analyzer，并将用户的原话保留在编排者手中。将返回的范围、成本和问题依据与这些原话进行对照，以执行需求收敛并分配结构规模。评估性请求、设想性想法和指定的机制要根据用户的原话来分类，而不是根据分析器的输出。这两项判断均由编排者负责。仅当询问所得的答复改变了分析对象或所需的范围依据时，才重新调用 requirement-analyzer。

### 工作流模式

在工作流开始或恢复时路由调用之前，先解析用户明确选择的模式，再解析已加载的根 `CLAUDE.md` 中的 `Workflow Mode` 指令；两者均未指定时使用 Normal 模式。会话中的明确选择持续生效，直到用户更改，并优先于仓库默认值。

下方流程描述 Normal 模式。使用 Lite 模式时，阅读 `references/lite-mode.md`，并应用其调用集合与质量边界。执行保留的调用，仅使用这些调用实际产出的结果。用户批准停止点和权限边界对两种模式均适用。

### 流程中的需求变更检测

将对已确认成果、目标状态需求或非目标的变更提议视为需求变更。当依据表明这些价值边界无法同时成立时，在需求确认关口停下，询问用户要更改哪个边界。保留这些边界的技术设计或实现修正不属于需求变更，移除一个仍可运行但已不再需要的技术选择也同样如此；通过了较早的阶段，并不能证明该阶段选定的手段仍然必要。更新每个受影响的技术产物，并从受影响的最早技术检查点恢复执行，同时保留仍然有效的产出。

## 我可以使用的子智能体

### 实现支持智能体
…

Read the whole file at its exact version.

How to install

mdr add shinpr/ai-coding-project-boilerplate/subagents-orchestration-guide@sha256:2972ade2e7c02da7

[![mdr](https://markdownregistry.com/badge/art_lgnshgqymk27xedx.svg)](https://markdownregistry.com/a/art_lgnshgqymk27xedx)

Versions

The registry has recorded 5 versions of this file, between Sep 12, 2026 and Oct 3, 2026, about one every 5 days.

Audit of the latest version

Source

API

GET https://markdownregistry.com/api/v1/artifacts/art_lgnshgqymk27xedx
GET https://markdownregistry.com/api/v1/resolve?ref=shinpr/ai-coding-project-boilerplate/subagents-orchestration-guide
GET https://markdownregistry.com/api/v1/blob/2972ade2e7c02da783583c8d0f9f4a4d4e3545a63905b645dfc83423354ebf8b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from shinpr/ai-coding-project-boilerplate

Every file in shinpr/ai-coding-project-boilerplate

Other files named subagents-orchestration-guide

Browse by kind, by grade A, or by owner.