Agent skill

Agent Sort

by affaan-m in affaan-m/ECC

通过将技能、命令、规则、钩子和额外内容并行进行仓库感知审查,为特定仓库构建基于证据的 ECC 安装计划,将其分为 DAILY 和 LIBRARY 两类。当 ECC 应精简为项目实际所需而非加载完整包时使用。

MITAuto-check passed

Install Agent Sort

skills CLI
$ npx skills add affaan-m/ECC --skill agent-sort -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install affaan-m/ECC agent-sort --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/zh-CN/skills/agent-sort .claude/skills/agent-sort && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-sort
GitHub stars
276k
Token cost
~691 tokens
SKILL.md length
185 words
Files
1
Skills in repo
683
Repo updated
First seen
Licence
MIT

At a glance

通过将技能、命令、规则、钩子和额外内容并行进行仓库感知审查,为特定仓库构建基于证据的 ECC 安装计划,将其分为 DAILY 和 LIBRARY 两类。当 ECC 应精简为项目实际所需而非加载完整包时使用。

  • Works in 6 steps: 读取仓库 → 构建证据表 → 决定 DAILY 还是 LIBRARY → …
  • SKILL.md covers 何时使用, 不可协商的规则, 输出 and 分类模型, plus 5 more sections
  • Calls rg, supabase and flutter

What it does

Agent Sort is an agent skill from affaan-m/ECC. 通过将技能、命令、规则、钩子和额外内容并行进行仓库感知审查,为特定仓库构建基于证据的 ECC 安装计划,将其分为 DAILY 和 LIBRARY 两类。当 ECC 应精简为项目实际所需而非加载完整包时使用。

Its SKILL.md is about 690 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. The licence is MIT.

Example prompts

  • “/agent-sort”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. 读取仓库
  2. 构建证据表
  3. 决定 DAILY 还是 LIBRARY
  4. 构建安装计划
  5. 创建可选的路由器
  6. 验证结果

What it can do on your machine

Read from SKILL.md and the folder at commit 4eb71d9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • rg
    • supabase
    • flutter

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use supabase, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Sort loads about 691 tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 185 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~29
When it runs · the whole SKILL.md, loaded when a task matches
~691

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from affaan-m/ECC at commit 4eb71d9, republished under its MIT licence (© affaan-m). 185 words, ~691 tokens.

Download SKILL.mdSave it as .claude/skills/agent-sort/SKILL.md (or your agent's skills folder).
name
agent-sort
description
通过将技能、命令、规则、钩子和额外内容并行进行仓库感知审查,为特定仓库构建基于证据的 ECC 安装计划,将其分为 DAILY 和 LIBRARY 两类。当 ECC 应精简为项目实际所需而非加载完整包时使用。
origin
ECC

技能分类

当仓库需要项目特定的 ECC 表面而非默认完整安装时,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中的证据对 ECC 组件进行分类。

何时使用

  • 项目只需要 ECC 的子集,完整安装过于嘈杂
  • 仓库技术栈明确,但无人希望逐个手动筛选技能
  • 团队希望获得基于 grep 证据而非主观意见的可重复安装决策
  • 需要将始终加载的日常工作流表面与可搜索的库/参考表面分离
  • 仓库已偏离至错误的语言、规则或钩子集,需要清理

不可协商的规则

  • 以当前仓库为事实来源,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";它意味着"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;不要引入第二个安装系统

输出

按顺序生成以下工件:

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

分类模型

仅使用两个分类:

  • DAILY
    • 应为该仓库的每个会话加载
    • 与仓库的语言、框架、工作流或操作者表面强匹配
  • LIBRARY
    • 保留有用,但不值得默认加载
    • 应通过搜索、路由器技能或选择性手动使用保持可访问

证据来源

在进行任何分类之前,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

并行审查轮次

如果并行子代理可用,将审查分为以下轮次:

  1. 代理
    • 分类 agents/*
  2. 技能
    • 分类 skills/*
  3. 命令
    • 分类 commands/*
  4. 规则
    • 分类 rules/*
  5. 钩子和脚本
    • 分类钩子表面、MCP 健康检查、辅助脚本和操作系统兼容性
  6. 额外项
    • 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,则按顺序运行相同的轮次。

核心工作流

1. 读取仓库

在分类任何内容之前,确定实际技术栈:

  • 使用的语言
  • 使用的框架
  • 主要包管理器
  • 测试技术栈
  • 代码检查/格式化技术栈
  • 部署/运行时表面
  • 已存在的操作者集成
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
  • 仓库证据
  • 简短理由

使用此格式:

text
skills/frontend-patterns | skill | DAILY | 84 个 .tsx 文件,存在 next.config.ts | 核心前端技术栈
skills/django-patterns   | skill | LIBRARY | 无 .py 文件,无 pyproject.toml       | 此仓库中未激活
rules/typescript/*       | rules | DAILY | 存在 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

提升至 DAILY 当:

  • 仓库明确使用匹配的技术栈
  • 组件足够通用,有助于每个会话
  • 仓库已依赖相应的运行时或工作流

降级至 LIBRARY 当:

  • 组件与技术栈不匹配
  • 仓库可能以后需要,但不是每天
  • 它增加了上下文开销而无直接相关性
4. 构建安装计划

将分类转化为行动:

  • DAILY 技能 -> 安装或保留在 .claude/skills/
  • DAILY 命令 -> 仅当仍然有用时保留为显式 shim
  • DAILY 规则 -> 仅安装匹配的语言集
  • DAILY 钩子/脚本 -> 仅保留兼容的
  • LIBRARY 表面 -> 通过搜索或 skill-library 保持可访问

如果仓库已使用选择性安装,则更新该计划而非创建另一个系统。

5. 创建可选的路由器

如果项目需要可搜索的库表面,创建:

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

该路由器应包含:

  • DAILY 与 LIBRARY 的简短说明
  • 分组的触发关键词
  • 库参考的存放位置

不要在路由器内重复每个技能的主体。

6. 验证结果

应用计划后,验证:

  • 每个 DAILY 文件存在于预期位置
  • 未保留过时的语言规则
  • 未安装不兼容的钩子
  • 最终安装确实匹配仓库技术栈

返回一个简洁的报告,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,交接至:

  • configure-ecc

如果下一步是重叠清理或目录审查,交接至:

  • skill-stocktake

如果下一步是更广泛的上下文修剪,交接至:

  • strategic-compact

输出格式

按此顺序返回结果:

text
栈
- 语言/框架/运行时摘要

日常
- 始终加载的条目及证据

库
- 可搜索/参考的条目及证据

安装计划
- 应安装、移除或路由的内容

验证
- 已运行的检查及剩余差距

© affaan-m, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in docs/zh-CN/skills/agent-sort of affaan-m/ECC.

Open the folder on GitHubat commit 4eb71d9

Compare with similar skills

Agent Sort next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Sort compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Sort this skillaffaan-m/ECC276k—~691Automated safety check: PassMIT
Sortedglebis/claude-skills391—~2kAutomated safety check: PassMIT
Card Sort AnalysisOwl-Listener/designer-skills2.9k1 repos~287Automated safety check: PassMIT
Sorting Parameter Handlerjeremylongshore/tons-of-skills-marketplace2.8k—~575Automated safety check: PassMIT
Configure Eccxu-xiang/everything-claude-code-zh2k1 repos~2.1kAutomated safety check: PassMIT
Configure Eccxu-xiang/everything-claude-code-zh2k—~1.8kAutomated safety check: PassMIT

Similar skills

  • Sorted

    glebis/claude-skills

    Automate getSorted.de (Sorted) for freelancer invoicing, expense tracking, and German tax submissions (VAT, ZM, annual returns).

    391 GitHub stars~2k tokensUpdated 2 days ago
    Productivity & AutomationAuto-check passed
  • Card Sort Analysis

    Owl-Listener/designer-skills

    Analyse open or closed card sort results into a proposed grouping and label set.

    2.9k GitHub starsUsed in 1 repo~287 tokens
    Frontend & DesignAuto-check passed
  • Sorting Parameter Handler

    jeremylongshore/tons-of-skills-marketplace

    Manage sorting parameter handler operations. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~575 tokensUpdated today
    Backend & APIsAuto-check passed
  • Configure Ecc

    xu-xiang/everything-claude-code-zh

    Everything Claude Code 的交互式安装程序 — 引导用户选择并安装技能和规则到用户级或项目级目录,验证路径,并可选择优化已安装文件。

    2k GitHub starsUsed in 1 repo~2.1k tokens
    Backend & APIsAuto-check passed
  • Configure Ecc

    xu-xiang/everything-claude-code-zh

    Everything Claude Code 的交互式安装程序 —— 引导用户将技能(Skills)和规则(Rules)安装到用户级或项目级目录,验证路径,并在需要时优化已安装的文件。

    2k GitHub stars~1.8k tokensUpdated 7 mo ago
    Backend & APIsAuto-check passed
  • Configure Ecc

    xu-xiang/everything-claude-code-zh

    Everything Claude Code 的交互式安装程序 —— 引导用户选择并将技能(Skills)和规则(Rules)安装到用户级或项目级目录,验证路径,并可选地优化已安装的文件。

    2k GitHub stars~2k tokensUpdated 7 mo ago
    Backend & APIsAuto-check passed

More from affaan-m/ECC

All 683 skills in this repo
  • Skill Stocktake

    affaan-m/ECC

    Audits your installed Claude skills and commands for quality, with a quick mode for recently changed skills and a full mode that evaluates all of them through subagents.

    276k GitHub starsUsed in 5 repos~3.1k tokens
    Auto-check passed
  • Ingests, indexes, searches, edits and monitors video, audio and live streams through the VideoDB Python SDK, returning stream links, clips and timestamps.

    276k GitHub starsUsed in 3 repos~3.5k tokens
    Auto-check: notes
  • Docs Governance

    affaan-m/ECC

    Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references.

    276k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Rules Distillation

    affaan-m/ECC

    Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.

    276k GitHub starsUsed in 2 repos~2.3k tokens
    Auto-check passed
  • Builds DRAFT counterparty agreements from one markdown template and a small JSON spec per party, with clauses picked by the party's role.

    276k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Measures whether agents actually follow a skill, rule or agent definition by generating scenarios at three strictness levels and scoring tool-call traces.

    276k GitHub starsUsed in 1 repo~623 tokens
    Auto-check passed

Questions about Agent Sort

What does Agent Sort do?

通过将技能、命令、规则、钩子和额外内容并行进行仓库感知审查,为特定仓库构建基于证据的 ECC 安装计划,将其分为 DAILY 和 LIBRARY 两类。当 ECC 应精简为项目实际所需而非加载完整包时使用。. Agent Sort is an agent skill from affaan-m/ECC.

How do I install Agent Sort in Claude Code?

Run `npx skills add affaan-m/ECC --skill agent-sort -a claude-code`. Or copy the skill folder (docs/zh-CN/skills/agent-sort in affaan-m/ECC) into .claude/skills/agent-sort in your project. Claude Code loads it when a task matches its description.

How do I install Agent Sort in Codex?

Run `npx skills add affaan-m/ECC --skill agent-sort -a codex`. Or copy the skill folder (docs/zh-CN/skills/agent-sort in affaan-m/ECC) into .agents/skills/agent-sort in your project. Codex loads it when a task matches its description.

Can I use Agent Sort in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add affaan-m/ECC --skill agent-sort -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-sort, .gemini/skills/agent-sort, .github/skills/agent-sort and .opencode/skills/agent-sort in your project.

What does Agent Sort need to run?

Going by SKILL.md and its folder, Agent Sort needs the command-line tools its instructions call (rg, supabase and flutter). Our summary lists: Python 3.

Does Agent Sort access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Sort safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agent Sort use?

Agent Sort is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Sort use?

About 691 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Sort?

Skills that share tags, products or a category with Agent Sort: Sorted (glebis/claude-skills, 391 stars), Card Sort Analysis (Owl-Listener/designer-skills, 2.9k stars), Sorting Parameter Handler (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and Configure Ecc (xu-xiang/everything-claude-code-zh, 2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Sort?

affaan-m (a GitHub user) maintains it in affaan-m/ECC, which has 276,111 GitHub stars. The repository holds 683 skills in this directory. The repository was last updated on October 10, 2026.

Source: affaan-m/ECC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.