Skill 详情
Skill 创建器
Skill Creator · github
交互式创建新 skills,让你可以自行扩展 Claude。
Skill 概览
交互式创建新 skills,让你可以自行扩展 Claude。
Skill 创建器 相关搜索词
本页主要服务搜索 Skill 创建器、下载、安装、README、Skill URL 和使用教程的用户。
资源类型
Anthropic Skill
所属分类
Meta & Tools 元工具、Learning 学习
标签
Skill 创作、元工具
下载的是 EasyGlobe 保存的本地 Markdown skill 文件,可随站点一起部署到 GitHub 和 Cloudflare。
详细 Skill 介绍
Skill 创建器 的定位
Skill 创建器 是一个面向 Meta & Tools 元工具、Learning 学习 场景的 AI Agent skill 资源。根据当前归档内容,它的主要价值是:交互式创建新 skills,让你可以自行扩展 Claude。。用户通常会搜索“Skill 创建器 是什么”“Skill 创建器 怎么安装”“Skill 创建器 怎么使用”“Skill 创建器 下载”以及 Claude Skills、Codex Skills、Gemini Skills、Kimi Skills、GLM Skills 等组合关键词,因此本页把 README、Skill URL、本地下载文件、使用方法和适用平台放在同一个详情页中,方便判断它是否适合自己的工作流。
README 核心说明
A skill for creating new skills and iteratively improving them.
At a high level, the process of creating a skill goes like this:
- Decide what you want the skill to do and roughly how it should do it
- Write a draft of the skill
- Create a few test prompts and run claude-with-access-to-the-skill on them
- Help the user evaluate the results both qualitatively and quantitatively
- While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
- Use the eval-viewer/generate_review.py script to show the user the results for them to look at, and also let them look at the quantitative metrics
- Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
- Repeat until you're satisfied
- Expand the test set and try again at larger scale...
README 能力说明
Based on the user interview, fill in these components:
- **name**: Skill identifier
- **description**: When to trigger, what it does. This is the primary triggering mechanism - include both what the skill does AND specific contexts for when to use it. All "when to use" info goes here, not in the body. Note: currently Claude has a tendency to "undertrigger" skills -- to not use them when they'd be useful. To combat this, please make the skill descriptions a little bit "pushy". So for instance, instead of "How to build a simple fast dashboard to display internal Anthropic data.", you might write "How to build a simple fast dashboard to display internal Anthropic data....
README 使用说明
The skill creator is liable to be used by people across a wide range of familiarity with coding jargon. If you haven't heard (and how could you, it's only very recently that it started), there's a trend now where the power of Claude is inspiring plumbers to open up their terminals, parents and grandparents to google "how to install npm". On the other hand, the bulk of users are probably fairly computer-literate.
So please pay attention to context cues to understand how to phrase your communication! In the default case, just to give you some idea:
- "evaluation" and "benchmark" are borderline, but OK
- for "JSON" and "assertion" you want to see serious cues from the user that they know what those things are before using them without explaining them...
适用场景和工作流价值
从分类和标签看,Skill 创建器 主要覆盖 Meta & Tools 元工具、Learning 学习,关键词包括 Skill 创作、元工具。它适合被整理成团队 SOP、AI Agent 提示词、Claude Skill、Codex Skill 或其他模型平台可复用的操作说明。实际落地时,可以先阅读本页的 README 摘要,确认它解决的问题、输入输出、运行环境和限制条件,再通过 Skill URL 查看原项目的最新说明。对于需要长期复用的场景,本地 Markdown 下载文件可以作为归档版本,便于团队内部评审、二次改写或放入自己的 agent skills 仓库。
安装、使用和平台判断
当前归档中没有发现明确的安装章节。可先通过 Skill URL 打开原始项目,根据项目 README、平台文档或 skill marketplace 页面完成安装;下载按钮提供 EasyGlobe 保存的本地 Markdown 版本。 The skill creator is liable to be used by people across a wide range of familiarity with coding jargon....
安装方式
当前归档中没有发现明确的安装章节。可先通过 Skill URL 打开原始项目,根据项目 README、平台文档或 skill marketplace 页面完成安装;下载按钮提供 EasyGlobe 保存的本地 Markdown 版本。
使用方式
The skill creator is liable to be used by people across a wide range of familiarity with coding jargon. If you haven't heard (and how could you, it's only very recently that it started), there's a trend now where the power of Claude is inspiring plumbers to open up their terminals, parents and grandparents to google "how to install npm". On the other hand, the bulk of users are probably fairly computer-literate.
So please pay attention to context cues to understand how to phrase your communication! In the default case, just to give you some idea:
- "evaluation" and "benchmark" are borderline, but OK
- for "JSON" and "assertion" you want to see serious cues from the user that they know what those things are before using them without explaining them
It's OK to briefly explain terms if you're in doubt, and feel free to clarify terms with a short definition if you're unsure if the user will get it.
---
能力范围
Based on the user interview, fill in these components:
- **name**: Skill identifier
- **description**: When to trigger, what it does. This is the primary triggering mechanism - include both what the skill does AND specific contexts for when to use it. All "when to use" info goes here, not in the body. Note: currently Claude has a tendency to "undertrigger" skills -- to not use them when they'd be useful. To combat this, please make the skill descriptions a little bit "pushy". So for instance, instead of "How to build a simple fast dashboard to display internal Anthropic data.", you might write "How to build a simple fast dashboard to display internal Anthropic data. Make sure to use this skill whenever the user mentions dashboards, data visualization, internal metrics, or wants to display any kind of company data, even if they don't explicitly ask for a 'dashboard.'"
- **compatibility**: Required tools, dependencies (optional, rarely needed)
- **the rest of the skill :)**
支持平台
这个 skill 可以作为以下 AI Agent、模型工作流或团队 SOP 的参考模板使用。
配置与更新
归档中暂未识别到单独的配置章节;如果原项目包含 API key、账号授权、CLI 或插件配置,请以 Skill URL 中的官方说明为准。
README 命令示例
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter (name, description required)
│ └── Markdown instructions
└── Bundled Resources (optional)
├── scripts/ - Executable code for deterministic/repetitive tasks
├── references/ - Docs loaded into context as needed
└── assets/ - Files used in output (templates, icons, fonts) cloud-deploy/
├── SKILL.md (workflow + selection)
└── references/
├── aws.md
├── gcp.md
└── azure.md ## Report structure
ALWAYS use this exact template:
# [Title]
## Executive summary
## Key findings
## Recommendations 标签
常见问题 FAQ
What:Skill 创建器 是什么?
交互式创建新 skills,让你可以自行扩展 Claude。
Who:Skill 创建器 适合谁使用?
适合需要处理 Meta & Tools 元工具、Learning 学习 工作流的团队、运营人员、开发者或 AI Agent。
When:什么时候使用 Skill 创建器?
当任务涉及 Skill 创作、元工具,或需要把对应能力沉淀为 Claude Skills、Codex Skills、Gemini Skills、Kimi Skills、GLM Skills 或团队 SOP 时使用。
如何下载 Skill 创建器?
可以使用页面顶部或 Skill 信息区的“下载 Skill 文件”按钮下载 EasyGlobe 保存的本地 Markdown 文件,文件名为 manual-skill-creator.md。
Skill 创建器 怎么安装?
请查看本页“安装方式”模块;如果归档 README 没有明确安装章节,可以通过 Skill URL 打开原始项目,并按官方 README、平台文档或 marketplace 页面完成安装。
Skill 创建器 怎么使用?
请查看本页“使用方式”“能力范围”和 README 摘要模块。页面会把归档 README 中识别出的使用说明、命令示例和适用工作流整理出来。
Skill 创建器 支持 Claude、Codex、Gemini、Kimi 和 GLM 吗?
本页把它整理为可复用的 AI Agent skill 资料,可作为 Claude Skills、Codex Skills、Gemini Skills、Kimi Skills、GLM Skills、ChatGPT Skills 或团队 SOP 的参考模板;实际可用性以 Skill URL 中的官方说明为准。
Skill 创建器 的 Skill URL 在哪里?
Skill URL 保留在页面左侧的 Skill 信息区,也可以点击页面顶部的“打开原始 Skill”按钮访问原始项目或官方页面。
本地下载文件和 Skill URL 有什么区别?
本地下载文件是 EasyGlobe 保存的 Markdown 版本,便于归档、阅读和复用;Skill URL 指向原始项目、官方文档或 marketplace 页面,适合查看最新说明和官方安装方式。