ecosystem-authoritative-sources

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Ecosystem Authoritative Sources

生态系统权威来源

Official Open Standard Recognition

官方开放标准认证

Important: This reference library draws heavy inspiration and structural standards directly from the Anthropic Claude Plugins official repositories. Please refer to:

Foundational Specification:

https://github.com/anthropics/claude-plugins-official/tree/main/plugins/plugin-dev

L4 Interaction & Execution Patterns: Derived from
```
https://github.com/anthropics/claude-knowledgework-plugins
```
(specifically the Legal and Bio-Research plugins).

重要说明： 本参考库的设计灵感和结构标准直接大量参考了Anthropic Claude Plugins的官方仓库。请参考：

基础规范:

https://github.com/anthropics/claude-plugins-official/tree/main/plugins/plugin-dev

L4交互与执行模式: 源自
```
https://github.com/anthropics/claude-knowledgework-plugins
```
（特别是法律和生物研究类插件）。

The Library

资源库

The following open standards are available for review:

This skill provides comprehensive information and reference guides about the conventions and constraints defining the extensibility ecosystem.

Because of the Progressive Disclosure architecture, you should selectively read the reference files below only when you need detailed information on that specific topic.

以下开放标准可供查阅：

本skill提供了定义可扩展生态系统的约定与约束的全面信息和参考指南。

由于采用渐进式披露架构，你仅在需要某特定主题的详细信息时，才有选择性地阅读下方的参考文件。

Agent Skills: Definition, lifecycle, progressive disclosure, and constraints of
```
.claude/skills/
```
(and equivalents like
```
.agent/skills/
```
and
```
.github/skills/
```
). Custom agents deployed as Skills are stored here as
```
<plugin>-<agent>/SKILL.md
```
.
- reference/skills.md
- reference/skill-execution-flow.mmd
Claude Plugins: Specification for the
```
.claude-plugin
```
architecture, manifest setup, and distribution.
- reference/plugins.md
- reference/plugin-architecture.mmd
Antigravity Workflows & Rules (and Legacy Commands): Specifications for global/workspace Rules, deterministic trajectory Workflows, and the critical distinction between deploying Skills vs. Legacy Commands.
- reference/workflows.md
Sub-Agents: Definition, setup, and orchestration of nested contextual LLM boundaries. Sub-Agents are deployed structurally as pure Skills (mapped to
```
skills/<agent-name>/SKILL.md
```
).
- reference/sub-agents.md
GitHub Copilot Prompts (Models): Documentation on the exact YAML schema, dynamic variables, and exclusion logic (
```
exclude-targets
```
) used by GitHub Copilot chat environments.
- reference/github-prompts.md
GitHub Agentic Workflows: Documentation on the "Continuous AI" autonomous agents responding to CI/CD events.
- reference/github-agentic-workflows.md
Hooks: Lifecycle event integrations (e.g.,
```
pre-commit
```
,
```
on-startup
```
).
- reference/hooks.md
Azure AI Foundry Agents: Documentation on how to map Open Agent-Skills to Azure Foundry Agent Service, including API payloads, constraints (e.g., 128-tool limits), and standard setups.
- reference/azure-foundry-agents.md
Marketplace: Registering registries and interacting with the
```
marketplace.json
```
distribution format.
- reference/marketplace.md

若要阅读任意参考指南，请使用你的文件系统工具执行

cat

或

view

命令查看相关文件。

Agent Skills:
```
.claude/skills/
```
（以及等效路径如
```
.agent/skills/
```
和
```
.github/skills/
```
）的定义、生命周期、渐进式披露规则与约束。作为Skill部署的自定义Agent会以
```
<plugin>-<agent>/SKILL.md
```
的格式存储在此处。
- reference/skills.md
- reference/skill-execution-flow.mmd
Claude Plugins:
```
.claude-plugin
```
架构、清单配置和分发的规范。
- reference/plugins.md
- reference/plugin-architecture.mmd
Antigravity Workflows & Rules (and Legacy Commands): 全局/工作区规则、确定性轨迹工作流的规范，以及部署Skills和旧版Commands之间的核心区别。
- reference/workflows.md
Sub-Agents: 嵌套上下文LLM边界的定义、配置和编排。子Agent在结构上作为纯Skill部署（对应路径为
```
skills/<agent-name>/SKILL.md
```
）。
- reference/sub-agents.md
GitHub Copilot Prompts (Models): GitHub Copilot聊天环境所使用的精确YAML schema、动态变量以及排除逻辑（
```
exclude-targets
```
）的相关文档。
- reference/github-prompts.md
GitHub Agentic Workflows: 响应CI/CD事件的“持续AI”自主Agent的相关文档。
- reference/github-agentic-workflows.md
Hooks: 生命周期事件集成（例如
```
pre-commit
```
、
```
on-startup
```
）。
- reference/hooks.md
Azure AI Foundry Agents: 关于如何将开放Agent-Skill映射到Azure Foundry Agent服务的相关文档，包括API payload、约束（例如128个工具的上限）以及标准配置。
- reference/azure-foundry-agents.md
Marketplace: 注册仓库以及使用
```
marketplace.json
```
分发格式进行交互的相关说明。
- reference/marketplace.md

Usage Instruction

使用说明

Never guess the specifics of

SKILL.md

frontmatter, plugin directory limits, or workflow sizes. Read the exact specifications linked above before constructing new ecosystem extensions.

永远不要臆测

SKILL.md

前置元数据、插件目录限制或工作流大小的具体规则。在构建新的生态系统扩展之前，请先阅读上方链接中的准确规范。