Back to Details

antigravity-skill-orchestrator

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

antigravity-skill-orchestrator

antigravity-skill-orchestrator

Overview

概述

The 
skill-orchestrator
is a meta-skill designed to enhance the AI agent's ability to tackle complex problems. It acts as an intelligent coordinator that first evaluates the complexity of a user's request. Based on that evaluation, it determines if specialized skills are needed. If they are, it selects the right combination of skills, explicitly tracks these combinations using 
@agent-memory-mcp
for future reference, and guides the agent through the execution process. Crucially, it includes strict guardrails to prevent the unnecessary use of specialized skills for simple tasks that can be solved with baseline capabilities.
skill-orchestrator
是一种元技能，旨在提升AI Agent处理复杂问题的能力。它充当智能协调器，首先评估用户请求的复杂度，据此判断是否需要专业技能。如果需要，它会选择合适的技能组合，通过
@agent-memory-mcp
明确跟踪这些组合以便未来参考，并引导Agent完成执行流程。至关重要的是，它包含严格的防护机制，避免在可通过基础能力解决的简单任务中不必要地使用专业技能。

When to Use This Skill

何时使用该技能

  • Use when tackling a complex, multi-step problem that likely requires multiple domains of expertise.
  • Use when you are unsure which specific skills are best suited for a given user request, and need to discover them from the broader ecosystem.
  • Use when the user explicitly asks to "orchestrate", "combine skills", or "use the best tools for the job" on a significant task.
  • Use when you want to look up previously successful combinations of skills for a specific type of problem.
  • 处理需要多领域专业知识的复杂多步骤问题时使用。
  • 不确定哪些特定技能最适合用户请求，需要从更广泛的生态系统中发掘时使用。
  • 用户明确要求在重要任务上“编排”“组合技能”或“使用最佳工具”时使用。
  • 希望查找针对特定类型问题的过往成功技能组合时使用。

Core Concepts

核心概念

Task Evaluation Guardrails

任务评估防护机制

Not every task requires a specialized skill. For straightforward issues (e.g., small CSS fixes, simple script writing, renaming a variable), DO NOT USE specialized skills. Over-engineering simple tasks wastes tokens and time.
Additionally, the orchestrator is strictly forbidden from creating new skills. Its sole purpose is to combine and use existing skills provided by the community or present in the current environment.
Before invoking any skills, evaluate the task:
  1. Is the task simple/contained? Solve it directly using the agent's ordinary file editing, search, and terminal capabilities available in the current environment.
  2. Is the task complex/multi-domain? Only then should you proceed to orchestrate skills.
并非所有任务都需要专业技能。对于简单问题（如小型CSS修复、简单脚本编写、变量重命名），请勿使用专业技能。过度设计简单任务会浪费令牌和时间。
此外，编排器严禁创建新技能。其唯一目的是组合和使用社区提供或当前环境中已有的技能。
在调用任何技能之前，先评估任务：
  1. 任务是否简单/独立？ 直接使用当前环境中Agent具备的常规文件编辑、搜索和终端能力解决。
  2. 任务是否复杂/跨领域？ 只有此时才应进行技能编排。

Skill Selection & Combinations

技能选择与组合

When a task is deemed complex, identify the necessary domains (e.g., frontend, database, deployment). Search available skills in the current environment to find the most relevant ones. If the required skills are not found locally, consult the master skill catalog.
当任务被判定为复杂时，确定所需的领域（如前端、数据库、部署）。在当前环境中搜索可用技能，找到最相关的技能。如果本地找不到所需技能，请查阅主技能目录。

Master Skill Catalog

主技能目录

The Antigravity ecosystem maintains a master catalog of highly curated skills at 
https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/CATALOG.md
. When local skills are insufficient, fetch this catalog to discover appropriate skills across the 9 primary categories:
  • architecture
  • business
  • data-ai
  • development
  • general
  • infrastructure
  • security
  • testing
  • workflow
Antigravity生态系统在
https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/CATALOG.md
维护了一个经过严格筛选的主技能目录。当本地技能不足时，获取该目录以探索9个主要类别中的合适技能：
  • architecture
  • business
  • data-ai
  • development
  • general
  • infrastructure
  • security
  • testing
  • workflow

Memory Integration (
@agent-memory-mcp
)

内存集成（
@agent-memory-mcp
）

To build institutional knowledge, the orchestrator relies on the 
agent-memory-mcp
skill to record and retrieve successful skill combinations.
为了构建机构知识，编排器依赖
agent-memory-mcp
技能来记录和检索成功的技能组合。

Step-by-Step Guide

分步指南

1. Task Evaluation & Guardrail Check

1. 任务评估与防护检查

[Triggered when facing a new user request that might need skills]
  1. Read the user's request.
  2. Ask yourself: "Can I solve this efficiently with just basic file editing and terminal commands?"
  3. If YES: Proceed without invoking specialized skills. Stop the orchestration here.
  4. If NO: Proceed to step 2.
[当遇到可能需要技能的新用户请求时触发]
  1. 阅读用户请求。
  2. 自问：“我能否仅通过基础文件编辑和终端命令高效解决这个问题？”
  3. 如果是：直接处理，不调用专业技能。在此处停止编排。
  4. 如果否：进入步骤2。

2. Retrieve Past Knowledge

2. 检索过往知识

[Triggered if the task is complex]
  1. Use the 
    memory_search
    tool provided by 
    agent-memory-mcp
    to search for similar past tasks.
    • Example query: 
      memory_search({ query: "skill combination for react native and firebase", type: "skill_combination" })
  2. If a working combination exists, read the details using 
    memory_read
    .
  3. If no relevant memory exists, proceed to Step 3.
[当任务被判定为复杂时触发]
  1. 使用
    agent-memory-mcp
    提供的
    memory_search
    工具搜索类似的过往任务。
    • 示例查询：
      memory_search({ query: "skill combination for react native and firebase", type: "skill_combination" })
  2. 如果存在可行的组合，使用
    memory_read
    读取详细信息。
  3. 如果没有相关记忆，进入步骤3。

3. Discover and Select Skills

3. 发现并选择技能

[Triggered if no past knowledge covers this task]
  1. Analyze the core requirements (e.g., "needs a React UI, a Node.js backend, and a PostgreSQL database").
  2. Query the locally available skills using the current environment's skill list or equivalent discovery mechanism to find the best match for each requirement.
  3. If local skills are insufficient, fetch the master catalog with the web or command-line retrieval tools available in the current environment: 
    https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/CATALOG.md
    .
  4. Scan the catalog's 9 main categories to identify the appropriate skills to bring into the current context.
  5. Select the minimal set of skills needed. Do not over-select.
[当过往知识无法覆盖当前任务时触发]
  1. 分析核心需求（如“需要React UI、Node.js后端和PostgreSQL数据库”）。
  2. 使用当前环境的技能列表或等效发现机制查询本地可用技能，找到每个需求的最佳匹配。
  3. 如果本地技能不足，使用当前环境中的网页或命令行检索工具获取主目录：
    https://raw.githubusercontent.com/sickn33/antigravity-awesome-skills/main/CATALOG.md
    。
  4. 浏览目录的9个主要类别，确定要引入当前环境的合适技能。
  5. 选择所需的最少技能集。不要过度选择。

4. Apply Skills and Track the Combination

4. 应用技能并跟踪组合

[Triggered after executing the task using the selected skills]
  1. Assume the task was completed successfully using a new combination of skills (e.g., 
    @react-patterns
    + 
    @nodejs-backend-patterns
    + 
    @postgresql
    ).
  2. Record this combination for future use using 
    memory_write
    from 
    agent-memory-mcp
    .
    • Ensure the type is 
      skill_combination
      .
    • Provide a descriptive key and content detailing why these skills worked well together.
[当使用选定技能完成任务后触发]
  1. 假设使用新的技能组合（如
    @react-patterns
    + 
    @nodejs-backend-patterns
    + 
    @postgresql
    ）成功完成了任务。
  2. 使用
    agent-memory-mcp
    的
    memory_write
    记录该组合以便未来使用。
    • 确保类型为
      skill_combination
      。
    • 提供描述性的键和详细说明这些技能为何能有效配合的内容。

Examples

示例

Example 1: Handling a Simple Task (The Guardrail in Action)

示例1：处理简单任务（防护机制生效）

User Request: "Change the color of the submit button in 
index.css
to blue." Action: The skill orchestrator evaluates the task. It determines this is a "simple/contained" task. It does not invoke specialized skills. It directly edits 
index.css
.
用户请求： 将
index.css
中的提交按钮颜色改为蓝色。 操作： 技能编排器评估任务，判定这是“简单/独立”任务，不调用专业技能，直接编辑
index.css
。

Example 2: Recording a New Skill Combination

示例2：记录新技能组合

javascript
// Using the agent-memory-mcp tool after successfully building a complex feature
memory_write({ 
  key: "combination-ecommerce-checkout", 
  type: "skill_combination", 
  content: "For e-commerce checkouts, using @stripe-integration combined with @react-state-management and @postgresql effectively handles the full flow from UI state to payment processing to order recording.",
  tags: ["ecommerce", "checkout", "stripe", "react"]
})
javascript
// 使用agent-memory-mcp工具成功构建复杂功能后
memory_write({ 
  key: "combination-ecommerce-checkout", 
  type: "skill_combination", 
  content: "For e-commerce checkouts, using @stripe-integration combined with @react-state-management and @postgresql effectively handles the full flow from UI state to payment processing to order recording.",
  tags: ["ecommerce", "checkout", "stripe", "react"]
})

Example 3: Retrieving a Combination

示例3：检索组合

javascript
// At the start of a new e-commerce task
memory_search({ 
  query: "ecommerce checkout", 
  type: "skill_combination" 
})
// Returns the key "combination-ecommerce-checkout", which you then read:
memory_read({ key: "combination-ecommerce-checkout" })
javascript
// 在新的电商任务开始时
memory_search({ 
  query: "ecommerce checkout", 
  type: "skill_combination" 
})
// 返回键"combination-ecommerce-checkout"，随后读取：
memory_read({ key: "combination-ecommerce-checkout" })

Best Practices

最佳实践

  • ✅ Do: Always evaluate task complexity before looking for skills.
  • ✅ Do: Keep the number of orchestrated skills as small as possible.
  • ✅ Do: Use highly descriptive keys when running 
    memory_write
    so they are easy to search later.
  • ❌ Don't: Use this skill for simple bug fixes or UI tweaks.
  • ❌ Don't: Combine skills that have overlapping and conflicting instructions without a clear plan to resolve the conflict.
  • ❌ Don't: Attempt to construct, generate, or create new skills. Only combine what is available.
  • ✅ 应做： 在查找技能前始终评估任务复杂度。
  • ✅ 应做： 尽量减少编排的技能数量。
  • ✅ 应做： 运行
    memory_write
    时使用高度描述性的键，以便后续易于搜索。
  • ❌ 勿做： 将此技能用于简单bug修复或UI微调。
  • ❌ 勿做： 在没有明确解决冲突计划的情况下，组合存在重叠和冲突指令的技能。
  • ❌ 勿做： 尝试构建、生成或创建新技能。仅组合现有可用技能。

Related Skills

相关技能

  • @agent-memory-mcp
    - Essential for this skill to function. Provides the persistent storage for skill combinations.
  • @agent-memory-mcp
    - 此技能运行的必备组件，为技能组合提供持久存储。