技能进化

人工智能 社区

技能解读

当前原文的自动摘译,尚未人工审校。

何时更新技能

当发生以下任何情况时更新技能: 用户以应该概括的方式纠正代理行为。命令失败,应该记住恢复路径。参考链接、命令、组件_type或安装说明已过时。任务路线太宽泛、太狭窄,或者指向了错误的技能。

更新工作流程

先完成用户请求的任务,除非是技能更新的任务。确定应该改变的最小技能。保持每个SKILL.md简洁并以任务为导向。将详细示例或长参考材料移至该技能的references/目录中。添加新技能或任务路由更改时更新AGENTS.md。

命名和布局

使用扁平技能布局:每个技能文件夹必须包含一个带有 frontmatter 的 SKILL.md:使用 author 和 license frontmatter 而不是SKILL.md 文件中的长许可证标头。使用描述任务表面的特定名称。避免隐藏路由信息的包罗万象的文件夹。

品质吧

技能应该告诉客服人员要做什么、接下来要阅读什么以及要验证什么。更喜欢规范的存储库文档而不是复制的长格式解释。保持跨技能链接的相关性和有效性。首次使用时使用“NVIDIA NeMo Agent Toolkit”,然后使用“NeMo Agent Toolkit”或“工具包”。仅将 nat 用于技术标识符,例如 CLI、包名称、Python 命名空间、路径和环境变量。

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
人工智能
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
94 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@NVIDIA · Apache-2.0
上下文用量评级
低消耗
接入复杂程度
即装即用
是否需要外部接口密钥
不需要
兼容的系统
未声明(默认跨平台)
运行环境要求
Python
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
  • 读取环境变量
网络行为
仅限本地
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Skill Evolution

Use this skill before creating, editing, or deciding whether to update any AI coding agent skill in this repository.

## When to Update Skills

Update a skill when any of the following happens:

- A user corrects agent behavior in a way that should generalize.
- A command fails and the recovery path should be remembered.
- A reference link, command, component `_type`, or installation instruction is stale.
- Task routing is too broad, too narrow, or points to the wrong skill.
- A repeated instruction appears in multiple skills and should move to a shared entry point.
- A skill contains too much detail and should move detail into focused references.

Do not update skills for one-off user preferences, temporary local environment quirks, or speculative guidance that was not validated.

## Update Workflow

1. Finish the user's requested task first unless the skill update is the task.
2. Identify the smallest skill that should change.
3. Keep each `SKILL.md` concise and task-oriented.
4. Move detailed examples or long reference material into that skill's `references/` directory.
5. Update `AGENTS.md` when a new skill is added or task routing changes.
6. Run Markdown link checks through pre-commit on the changed skill files.

## Naming and Layout

Use the flat skills layout:

```text
skills/
  nat-installation/
    SKILL.md
    references/
  nat-workflow-creation/
    SKILL.md
    references/
```

Each skill folder must contain one `SKILL.md` with frontmatter:

```yaml
---
name: skill-name
description: Use when ...
author: NVIDIA Corporation and Affiliates
license: Apache-2.0
---
```

Use `author` and `license` frontmatter instead of long license headers in `SKILL.md` files.

Use specific names that describe the task surface. Avoid catch-all folders that hide routing information.

## Quality Bar

- Skills should tell agents what to do, what to read next, and what to validate.
- Prefer canonical repository docs over copied long-form explanations.
- Keep cross-skill links relative and valid.
- Use "NVIDIA NeMo Agent Toolkit" on first prose use, then "NeMo Agent Toolkit" or "the toolkit".
- Use `nat` only for technical identifiers such as the CLI, package name, Python namespace, paths, and environment variables.

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。