agent-sort

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Agent Sort

Agent分类

Use this skill when a repo needs a project-specific ECC surface instead of the default full install.

The goal is not to guess what "feels useful." The goal is to classify ECC components with evidence from the actual codebase.

当仓库需要项目专属的ECC配置而非默认完整安装时，请使用本skill。

我们的目标不是猜测哪些「看起来有用」，而是基于实际代码库的证据对ECC组件进行分类。

When to Use

适用场景

A project only needs a subset of ECC and full installs are too noisy
The repo stack is clear, but nobody wants to hand-curate skills one by one
A team wants a repeatable install decision backed by grep evidence instead of opinion
You need to separate always-loaded daily workflow surfaces from searchable library/reference surfaces
A repo has drifted into the wrong language, rule, or hook set and needs cleanup

项目只需要ECC的子集，完整安装冗余内容过多
仓库技术栈清晰，但没有人想逐个手动筛选skill
团队想要基于grep证据而非主观意见的可复用安装决策
你需要将始终加载的日常工作流配置与可搜索的库/参考配置分开
仓库的语言、规则或hook配置出现偏差，需要清理

Non-Negotiable Rules

硬性规则

Use the current repository as the source of truth, not generic preferences
Every DAILY decision must cite concrete repo evidence
LIBRARY does not mean "delete"; it means "keep accessible without loading by default"
Do not install hooks, rules, or scripts that the current repo cannot use
Prefer ECC-native surfaces; do not introduce a second install system

以当前仓库作为唯一事实依据，而非通用偏好
每一项DAILY分类的决策都必须引用具体的仓库证据
LIBRARY不代表「删除」，而是「保持可访问但默认不加载」
不要安装当前仓库无法使用的hook、规则或脚本
优先使用ECC原生配置，不要引入第二套安装系统

Outputs

输出产物

Produce these artifacts in order:

DAILY inventory
LIBRARY inventory
install plan
verification report
optional
```
skill-library
```
router if the project wants one

按顺序生成以下产物：

DAILY清单
LIBRARY清单
安装计划
验证报告
如果项目需要，可选生成
```
skill-library
```
路由

Classification Model

分类模型

Use two buckets only:

```
DAILY
```
- should load every session for this repo
- strongly matched to the repo's language, framework, workflow, or operator surface
```
LIBRARY
```
- useful to retain, but not worth loading by default
- should remain reachable through search, router skill, or selective manual use

仅使用两个分组：

```
DAILY
```
- 该仓库的每个会话都应该加载
- 与仓库的语言、框架、工作流或操作层面高度匹配
```
LIBRARY
```
- 有保留价值，但不值得默认加载
- 应该可以通过搜索、路由skill或选择性手动使用访问到

Evidence Sources

证据来源

Use repo-local evidence before making any classification:

file extensions
package managers and lockfiles
framework configs
CI and hook configs
build/test scripts
imports and dependency manifests
repo docs that explicitly describe the stack

Useful commands include:

bash

rg --files
rg -n "typescript|react|next|supabase|django|spring|flutter|swift"
cat package.json
cat pyproject.toml
cat Cargo.toml
cat pubspec.yaml
cat go.mod

在做出任何分类前请优先使用仓库本地证据：

文件扩展名
包管理器和锁文件
框架配置
CI和hook配置
构建/测试脚本
导入语句和依赖清单
明确描述技术栈的仓库文档

有用的命令包括：

bash

rg --files
rg -n "typescript|react|next|supabase|django|spring|flutter|swift"
cat package.json
cat pyproject.toml
cat Cargo.toml
cat pubspec.yaml
cat go.mod

Parallel Review Passes

并行审查流程

If parallel subagents are available, split the review into these passes:

Agents
- classify
```
agents/*
```
Skills
- classify
```
skills/*
```
Commands
- classify
```
commands/*
```
Rules
- classify
```
rules/*
```
Hooks and scripts
- classify hook surfaces, MCP health checks, helper scripts, and OS compatibility
Extras
- classify contexts, examples, MCP configs, templates, and guidance docs

If subagents are not available, run the same passes sequentially.

如果可用并行子Agent，将审查拆分为以下流程：

Agents
- 分类
```
agents/*
```
  下的内容
Skills
- 分类
```
skills/*
```
  下的内容
Commands
- 分类
```
commands/*
```
  下的内容
Rules
- 分类
```
rules/*
```
  下的内容
Hooks和脚本
- 分类hook配置、MCP健康检查、辅助脚本和操作系统兼容性相关内容
其他额外内容
- 分类上下文、示例、MCP配置、模板和指南文档

如果没有可用子Agent，按顺序串行执行以上流程。

Core Workflow

核心工作流

1. Read the repo

1. 读取仓库信息

Establish the real stack before classifying anything:

languages in use
frameworks in use
primary package manager
test stack
lint/format stack
deployment/runtime surface
operator integrations already present

在进行任何分类前先确认实际技术栈：

正在使用的语言
正在使用的框架
主要包管理器
测试技术栈
lint/格式化技术栈
部署/运行时环境
已存在的操作集成

2. Build the evidence table

2. 构建证据表

For every candidate surface, record:

component path
component type
proposed bucket
repo evidence
short justification

Use this format:

text

skills/frontend-patterns | skill | DAILY | 84 .tsx files, next.config.ts present | core frontend stack
skills/django-patterns   | skill | LIBRARY | no .py files, no pyproject.toml       | not active in this repo
rules/typescript/*       | rules | DAILY | package.json + tsconfig.json            | active TS repo
rules/python/*           | rules | LIBRARY | zero Python source files             | keep accessible only

针对每个候选配置项，记录：

组件路径
组件类型
建议分组
仓库证据
简短理由

使用以下格式：

text

skills/frontend-patterns | skill | DAILY | 84 .tsx files, next.config.ts present | core frontend stack
skills/django-patterns   | skill | LIBRARY | no .py files, no pyproject.toml       | not active in this repo
rules/typescript/*       | rules | DAILY | package.json + tsconfig.json            | active TS repo
rules/python/*           | rules | LIBRARY | zero Python source files             | keep accessible only

3. Decide DAILY vs LIBRARY

3. 决定DAILY还是LIBRARY

Promote to

DAILY

when:

the repo clearly uses the matching stack
the component is general enough to help every session
the repo already depends on the corresponding runtime or workflow

Demote to

LIBRARY

when:

the component is off-stack
the repo might need it later, but not every day
it adds context overhead without immediate relevance

符合以下条件则归入

DAILY

：

仓库明确使用匹配的技术栈
组件通用性足够，能为每个会话提供帮助
仓库已经依赖对应的运行时或工作流

符合以下条件则归入

LIBRARY

：

组件与当前技术栈不匹配
仓库后续可能需要，但不是日常必需
会增加上下文开销，但没有即时相关性

4. Build the install plan

4. 构建安装计划

Translate the classification into action:

DAILY skills -> install or keep in
```
.claude/skills/
```
DAILY commands -> keep as explicit shims only if still useful
DAILY rules -> install only matching language sets
DAILY hooks/scripts -> keep only compatible ones
LIBRARY surfaces -> keep accessible through search or
```
skill-library
```

If the repo already uses selective installs, update that plan instead of creating another system.

将分类结果转化为可执行操作：

DAILY skill -> 安装或保留在
```
.claude/skills/
```
目录下
DAILY command -> 仅在仍有用的情况下保留为明确的垫片
DAILY 规则 -> 仅安装匹配的语言集
DAILY hook/脚本 -> 仅保留兼容的内容
LIBRARY 配置 -> 通过搜索或
```
skill-library
```
保持可访问

如果仓库已经使用选择性安装，直接更新原有计划，不要创建新的系统。

5. Create the optional library router

5. 创建可选的库路由

If the project wants a searchable library surface, create:

```
.claude/skills/skill-library/SKILL.md
```

That router should contain:

a short explanation of DAILY vs LIBRARY
grouped trigger keywords
where the library references live

Do not duplicate every skill body inside the router.

如果项目需要可搜索的库配置，创建：

```
.claude/skills/skill-library/SKILL.md
```

该路由应该包含：

DAILY和LIBRARY的简要说明
分组触发关键词
库参考内容的存放位置

不要在路由中复制每个skill的完整内容。

6. Verify the result

6. 验证结果

After the plan is applied, verify:

every DAILY file exists where expected
stale language rules were not left active
incompatible hooks were not installed
the resulting install actually matches the repo stack

Return a compact report with:

DAILY count
LIBRARY count
removed stale surfaces
open questions

应用计划后，验证以下内容：

每个DAILY文件都存在于预期位置
过时的语言规则没有处于激活状态
不兼容的hook没有被安装
最终安装的内容确实与仓库技术栈匹配

返回一份精简报告，包含：

DAILY数量
LIBRARY数量
已移除的过时配置
待解决问题

Handoffs

后续流转

If the next step is interactive installation or repair, hand off to:

```
configure-ecc
```

If the next step is overlap cleanup or catalog review, hand off to:

```
skill-stocktake
```

If the next step is broader context trimming, hand off to:

```
strategic-compact
```

如果下一步是交互式安装或修复，流转到：

```
configure-ecc
```

如果下一步是重叠清理或目录审查，流转到：

```
skill-stocktake
```

如果下一步是更广泛的上下文裁剪，流转到：

```
strategic-compact
```

Output Format

输出格式

Return the result in this order:

text

STACK
- language/framework/runtime summary

DAILY
- always-loaded items with evidence

LIBRARY
- searchable/reference items with evidence

INSTALL PLAN
- what should be installed, removed, or routed

VERIFICATION
- checks run and remaining gaps

按以下顺序返回结果：

text

STACK
- language/framework/runtime summary

DAILY
- always-loaded items with evidence

LIBRARY
- searchable/reference items with evidence

INSTALL PLAN
- what should be installed, removed, or routed

VERIFICATION
- checks run and remaining gaps