JularDepick/AGENTS.md-Best-Practices

Name: JularDepick/AGENTS.md-Best-Practices
Author: JularDepick

Plugin插件 ⭐ 7 MIT Prompts & Skills提示词与技能

A best practice for universal prompts that comply with the AGENTS.md open specification.

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

AGENTS.md-Best-Practices is a universal prompt-engineering best-practices collection that conforms to the AGENTS.md open specification, organized as version 0.2.1 by JularDepick under the MIT license for 2026. The repository splits guidance into domain folders under src/ (such as develop/web-frontend-design and life) and additionally ships a skill/agents-md-best-practices/ bundle whose layout pairs a SKILL.md entry point with an index.yaml manifest and a md/ folder that mirrors the canonical AGENTS.md files under a {primary-category}_{secondary-category}_{author}_AGENTS.md naming convention, enabling progressive disclosure through the SKILL workflow. The project is not a packaged DSH manifest product but a generic best-practices corpus that lists DSH alongside Claude Code, OpenClaw, and OpenCode among its target agent environments.

Typical usage has two equally documented paths: either browse the src/ tree, pick the AGENTS.md (or its optional AGENTS_{xx-YY}.md multilingual variant) that fits the project, drop it into the working directory and ask the local Agent to load it after launch; or install the entire skill/agents-md-best-practices/ pack into the Agent's skills directory and prompt the local Agent to load the skill, letting SKILL.md and index.yaml drive the disclosure of the underlying md/ documents. It is aimed at teams and individual authors who want to codify cross-domain agent collaboration rules and distribute them as reusable skills, and it explicitly welcomes new submissions because the collection list is currently empty.

There are no extra runtime dependencies beyond a local Agent capable of consuming AGENTS.md files or executing the SKILL.md workflow, and the project ships only as documentation plus a packaging skeleton, so users must supply any AGENTS.md entries themselves by following the src/ project structure and naming conventions. First-run caveats include verifying the Agent's skills directory location, confirming support for SKILL.md progressive loading, ensuring index.yaml is recognized, and matching the md/ copy names exactly, since path or naming drift is the most likely cause of load failure given that the curated list is still unpopulated.

AGENTS.md-Best-Practices 是一个遵循 AGENTS.md 开放规范的通用提示工程最佳实践合集，按领域拆分为独立文件夹（如 develop/web-frontend-design、life），并通过 skill/agents-md-best-practices/ 目录将所有 AGENTS.md 封装为以 SKILL.md 为入口、index.yaml 索引、md/ 副本组成的技能包，便于 Agent 通过 SKILL 工作流渐进式加载。项目当前版本 v0.2.1，发布者 JularDepick，采用 MIT 许可证（2026）。集成方式包括两种：一是直接下载对应 AGENTS.md 至项目目录，让本地 Agent 运行后读取；二是将 skill 技能包安装到 Agent 对应的 skills 目录，再提示本地 Agent 加载技能。

典型工作流是按需求挑选 src/ 下领域与作者对应的 AGENTS.md（或其多语言变体 AGENTS_{xx-YY}.md），下载到项目后由本地 Agent 加载；如使用技能路径，则将 skill/agents-md-best-practices/ 整体安装至 Agent 的 skills 目录，由 SKILL.md 与 index.yaml 引导 Agent 渐进式披露 md/ 中的具体文档。合集列表当前为空，欢迎贡献者提交新条目。适合需要为不同领域沉淀 Agent 协作规范、并希望以 SKILL 形式分发的团队与个人作者。

依赖方面项目本身不引入额外运行依赖，仅依赖一个支持 AGENTS.md 加载或 SKILL.md 工作流的本地 Agent 环境；当前合集尚无具体条目，需要社区按 src/ 目录结构与命名规范逐步贡献。在首次使用前请确认 Agent 的 skills 目录位置、SKILL.md 加载方式以及 index.yaml 与 md/ 副本命名（{primary-category}_{secondary-category}_{author}_AGENTS.md）是否被目标 Agent 识别，避免因路径或命名差异导致加载失败。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：AGENTS.md-Best-Practices（JularDepick/AGENTS.md-Best-Practices）
仓库：https://github.com/JularDepick/AGENTS.md-Best-Practices
本站详情页：https://www.yhbd.top/plugins/julardepick-agents-md-best-practices/
本站登记：类型 plugin · 归类 人工精选收录 · 许可证 MIT · ⭐ 7 · 最近提交 2026-09-22 · 未检测到 DSH 插件清单

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 2 warnings2 项注意

Only 7 stars - very few users, little community feedback星标只有 7，几乎没人在用，遇到问题缺少社区反馈
No DSH plugin manifest detected - it may only carry the dsh-plugin topic, so the install method must be confirmed on the spot未检测到 DSH 插件清单：可能只是打了 dsh-plugin 话题，安装方式要现场确认

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add github:JularDepick/AGENTS.md-Best-Practices

把 JularDepick/AGENTS.md-Best-Practices 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

2.8 KB · 缓存于 2026-09-22 19:38:53 · 2.8 KB

AGENTS.md-Best-Practices

[English] [简体中文]

A best practice for universal prompt engineering that complies with the AGENTS.md open specification.

Project Guidelines

Organize AGENTS.md best practices for different domains in separate folders
skill/agents-md-best-practices/ encapsulates all AGENTS.md and uses workflow-generated SKILL for progressive disclosure

Project Structure

AGENTS.md-Best-Practices/
├── src/
│   ├── develop/                    # Primary category
│   │   └── web-frontend-design/    # Secondary category
│   │       └── {author}/           # Author
│   │           ├── AGENTS.md             # Main file (language-agnostic)
│   │           └── AGENTS_{xx-YY}.md     # Optional multilingual version (e.g., zh-CN)
│   └── life/
└── skill/
    └── agents-md-best-practices/   # Complete encapsulation (generated via workflow)
        ├── SKILL.md                # Skill entry point
        ├── index.yaml              # MD document index
        └── md/                     # All AGENTS.md
            └── {primary-category}_{secondary-category}_{author}_AGENTS.md  # AGENTS.md copy

Quick Start

1. As AGENTS.md

Select the appropriate AGENTS.md file based on your needs and project description, download it to your project directory, and prompt the local Agent to load it after running.

2. As SKILL.md

Download and install the skill/agents-md-best-practices/ skill pack to the Agent's corresponding directory, then prompt the local Agent to load the skill after running.

Collection List

No entries yet. Contributions are welcome.

Contribution Guidelines

Welcome to contribute in the following ways:

Submit entries: Create corresponding AGENTS.md files in the src/ directory according to the project structure requirements
Report issues: Submit Issues to report bugs or suggest improvements
Improve documentation: Optimize existing documents or translate multilingual versions
Develop features: Implement new features or optimize workflows

Please ensure you follow the project guidelines and maintain consistent code style.