Communitygithub.com

Agent Sort – 项目级 ECC 精简分类

基于代码库实际证据,为指定仓库构建 ECC 安装计划:将 skills、commands、rules、hooks 和 extras 按 DAILY(每日工作流)和 LIBRARY(可检索库)分类。当 ECC 需要按项目实际需求裁剪而非全量安装时使用。

Agent Sort – 项目级 ECC 精简分类 是什么?

Agent Sort 是一个专门用于精简 AI 助手(如 Claude Code、Cursor 等)的 ECC(扩展能力集合)的工具。它通过并行或串行的代码库感知审查流程,将 ECC 组件分为 DAILY(每日工作流必备)和 LIBRARY(可检索库)两类。其核心原则是“用证据说话”——每个 DAILY 分类决策都必须引用仓库中的具体证据,如文件扩展名、包管理器、依赖清单、CI 配置等。该工具支持主流平台与语言(TypeScript、Python、Rust、Flutter 等),并能生成详细的安装计划、验证报告和可选的技能库路由文件。它的价值在于:让团队不必凭感觉手动筛选技能,而是通过可重复的证据驱动流程,得到一份真正贴合项目栈的 ECC 精简配置,从而降低上下文噪声,提升日常开发效率。

兼容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/everything-claude-code/tree/main/skills/agent-sort

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Agent Sort – 项目级 ECC 精简分类 是做什么的?

当仓库需要针对项目的 ECC 表面而非默认全量安装时,使用此技能。

目标不是猜测“什么感觉有用”。目标是根据实际代码库的证据对 ECC 组件进行分类。

使用时机

  • 项目只需要 ECC 的子集,全量安装过于嘈杂
  • 项目栈已明确,但无人愿意逐个手工筛选技能
  • 团队希望基于 grep 证据而非个人意见做出可重复的安装决策
  • 需要将每日工作流中始终加载的表面与可检索的库/参考表面分开
  • 仓库已漂移到了错误的语言、规则或钩子集,需要清理

不可协商的规则

  • 使用当前仓库作为真理源,而非通用偏好
  • 每个 DAILY 决策必须引用具体的仓库证据
  • LIBRARY 并不意味着“删除”,而是“保持可访问,但不默认加载”
  • 不要安装当前仓库无法使用的钩子、规则或脚本
  • 优先使用 ECC 原生表面,不要引入第二套安装系统

输出物

按顺序生成以下制品:

  1. DAILY 清单
  2. LIBRARY 清单
  3. 安装计划
  4. 验证报告
  5. 可选的 skill-library 路由器(如果项目需要)

分类模型

仅使用两个分类桶:

  • DAILY
    • 每次会话都应为该仓库加载
    • 与仓库的语言、框架、工作流或操作表面强烈匹配
  • LIBRARY
    • 保留有用,但不值得默认加载
    • 应通过搜索、技能路由或选择性手动使用保持可访问

证据来源

在做出任何分类之前,使用仓库本地证据:

  • 文件扩展名
  • 包管理器和锁定文件
  • 框架配置
  • CI 和钩子配置
  • 构建/测试脚本
  • 导入和依赖清单
  • 明确描述项目栈的仓库文档

有用的命令包括:

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

并行审查流程

如果并行子代理可用,则将审查拆分为以下流程:

  1. Agents
    • 分类 agents/*
  2. Skills
    • 分类 skills/*
  3. Commands
    • 分类 commands/*
  4. Rules
    • 分类 rules/*
  5. Hooks 和脚本
    • 分类钩子表面、MCP 健康检查、辅助脚本和操作系统兼容性
  6. Extras
    • 分类上下文、示例、MCP 配置、模板和指导文档

如果子代理不可用,则依次运行相同的流程。

核心工作流

1. 读取仓库

在分类任何内容之前,先确定实际的栈:

  • 使用中的语言
  • 使用中的框架
  • 主要包管理器
  • 测试栈
  • lint/format 栈
  • 部署/运行时表面
  • 已有的操作符集成

2. 构建证据表

对于每个候选表面,记录:

  • 组件路径
  • 组件类型
  • 建议的分类桶
  • 仓库证据
  • 简短理由

使用此格式:

skills/frontend-patterns | skill | DAILY | 84 个 .tsx 文件,存在 next.config.ts | 核心前端栈
skills/django-patterns   | skill | LIBRARY | 无 .py 文件,无 pyproject.toml       | 该仓库中未激活
rules/typescript/*       | rules | DAILY | package.json + tsconfig.json            | 活跃的 TS 仓库
rules/python/*           | rules | LIBRARY | 零个 Python 源文件                 | 仅保持可访问

3. 决定 DAILY 还是 LIBRARY

升级为 DAILY,当:

  • 仓库明确使用匹配的栈
  • 组件足够通用,有助于每次会话
  • 仓库已经依赖于相应的运行时或工作流

降级为 LIBRARY,当:

  • 组件不在栈中
  • 仓库将来可能需要它,但不是每天
  • 它增加了上下文开销而没有直接相关性

4. 构建安装计划

将分类转化为行动:

  • DAILY skills -> 安装或保留在 .claude/skills/ 中
  • DAILY commands -> 仅在仍有用时保留为显式 shim
  • DAILY rules -> 仅安装匹配的语言集
  • DAILY hooks/scripts -> 仅保留兼容的
  • LIBRARY 表面 -> 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,则更新该计划,而不是创建另一个系统。

5. 创建可选的库路由器

如果项目需要可检索的库表面,创建:

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

该路由器应包含:

  • 对 DAILY 与 LIBRARY 的简短解释
  • 分组的触发关键词
  • 库引用的存放位置

不要在路由器中重复每个技能体的内容。

6. 验证结果

应用计划后,验证:

  • 每个 DAILY 文件都位于预期位置
  • 未留下过时的语言规则
  • 未安装不兼容的钩子
  • 最终的安装确实与仓库栈匹配

返回一份紧凑的报告,包含:

  • DAILY 数量
  • LIBRARY 数量
  • 移除的过时表面
  • 未解决的问题

交接

如果下一步是交互式安装或修复,则交接给:

  • configure-ecc

如果下一步是重叠清理或目录审查,则交接给:

  • skill-stocktake

如果下一步是更广泛的上下文修剪,则交接给:

  • strategic-compact

输出格式

按以下顺序返回结果:

STACK
- 语言/框架/运行时摘要

DAILY
- 始终加载的项目及其证据

LIBRARY
- 可检索/参考的项目及其证据

INSTALL PLAN
- 应安装、移除或路由的内容

VERIFICATION
- 已运行的检查和剩余差距

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/claude-api

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

affaan-m/everything-claude-code

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

affaan-m/everything-claude-code-conventions

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.

affaan-m/gget

gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs.

affaan-m/literature-review

Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.

affaan-m/motion-ui

Production-ready UI motion system for React/Next.js. Use when implementing animations, transitions, or motion patterns.

affaan-m/project-guidelines-example

Example project-specific skill template based on a real production application.

affaan-m/pubmed-database

Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring.

affaan-m/scholar-evaluation

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.

affaan-m/uspto-database

USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

相关技能