npx skills add https://github.com/recoupable/setup-artist --skill setup-artist快速搭建完整的艺术家工作区,让智能体能够立即开始工作。
setup-sandbox 技能)orgs/{org}/artists/{artist-slug}/ 路径下,并且包含一个 RECOUP.md 标记文件RECOUP.md 文件包含艺术家的姓名、slug 和 Recoup ID(由 setup-sandbox 创建){artist-slug}/
├── RECOUP.md
├── README.md
├── .env.example
├── .env
├── context/
│ ├── artist.md
│ ├── audience.md
│ ├── era.json
│ ├── tasks.md
│ └── images/
│ └── README.md
├── memory/
│ ├── README.md
│ └── MEMORY.md
├── songs/
│ └── README.md
├── releases/
│ └── README.md
├── content/
│ ├── README.md
│ ├── images/
│ └── videos/
├── config/
│ ├── README.md
│ └── SERVICES.md
├── library/
│ └── README.md
└── apps/
└── README.md
Scaffold a complete artist workspace so agents can start working immediately.
setup-sandbox skill)orgs/{org}/artists/{artist-slug}/ with a RECOUP.md marker fileRECOUP.md file contains the artist's name, slug, and Recoup ID (created by setup-sandbox){artist-slug}/
├── RECOUP.md
├── README.md
├── .env.example
├── .env
├── context/
│ ├── artist.md
│ ├── audience.md
│ ├── era.json
│ ├── tasks.md
│ └── images/
│ └── README.md
├── memory/
│ ├── README.md
│ └── MEMORY.md
├── songs/
│ └── README.md
├── releases/
│ └── README.md
├── content/
│ ├── README.md
│ ├── images/
│ └── videos/
├── config/
│ ├── README.md
│ └── SERVICES.md
├── library/
│ └── README.md
└── apps/
└── README.md
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
RECOUP.md 并创建目录结构导航到艺术家文件夹并读取 RECOUP.md 以获取艺术家的姓名、slug 和 ID:
cd orgs/{org}/artists/{artist-slug}
cat RECOUP.md
创建目录结构:
mkdir -p {context/images,memory,songs,releases,content/images,content/videos,config,library,apps}
RECOUP.md将 status 字段从 not-setup 更新为 active,并将正文替换为简要描述:
---
artistName: {Artist Name}
artistSlug: {artist-slug}
artistId: {uuid-from-recoupable}
status: active
---
# {Artist Name}
将此工作区连接到 Recoupable 平台。完整的目录指南和设置清单请参见 `README.md`。
根据 references/context-files.md 中的模板创建每个文件。核心文件包括:
| 文件 | 操作说明 |
|---|---|
context/artist.md | 填写艺术家身份、品牌、视觉世界、声音、语调。向用户询问详细信息或研究该艺术家。 |
context/audience.md | 填写受众洞察。关注他们为什么听、他们认同什么、他们如何谈论。 |
context/era.json | 设置当前的发行、歌曲、阶段和职业生涯阶段。 |
context/tasks.md | 留空 —— 用户将在任务出现时添加。 |
context/images/README.md | 创建一个说明,解释此文件夹用于存放视觉参考(如面部指南)。 |
创建两个文件:
memory/README.md —— 为智能体提供关于如何使用记忆系统的完整说明,包括范围概念。参见 references/memory-system.md。memory/MEMORY.md —— 几乎为空的起点,包含 frontmatter 和指导性注释(包括范围规则)。记忆系统使用三个范围来防止知识膨胀:
MEMORY.md)MEMORY.md,并标记时代)log/,绝不放入 MEMORY.md)智能体在将反馈保存到长期记忆之前,应向用户询问范围。
服务在 config/ 中跟踪,不在设置时预先填充。创建:
| 文件 | 操作说明 |
|---|---|
config/SERVICES.md | 为智能体提供关于在发现服务时如何添加服务的说明。参见 references/services-guide.md。 |
.env.example | 常见环境变量名称的参考列表(全部注释掉)。参见 references/env-template.md。 |
.env | 带有标题注释的空文件。智能体在连接服务时在此处添加凭据。 |
请勿预先填充服务条目。 服务应在智能体拥有真实信息(如账号、API 密钥、已确认的账户)时添加。旧方法(创建一个包含所有可能服务并设置为 not-setup 的巨大 JSON 文件)只会产生噪音,而非价值。
每个目录都需要一个 README.md 来解释其用途。模板请参见 references/directory-readmes.md。
| 目录 | README 解释... |
|---|---|
songs/ | 歌曲文件夹格式、命名约定、应添加哪些文件 |
releases/ | 发行文件夹格式、RELEASE.md 作为事实来源 |
content/ | 生成的内容输出 —— 图像和视频 |
config/ | 每位艺术家的配置、服务和共享的自动化工具 |
library/ | 深度参考文档、研究报告 |
apps/ | 艺术家特定的应用程序(非共享工具) |
在艺术家根目录创建 README.md,包含:
模板请参见 references/root-readme.md。
如果您拥有关于该艺术家的信息(来自用户、研究或 Recoup 平台):
context/artist.md 中的身份/品牌信息context/audience.md 中的受众洞察context/era.json 中设置当前的发行阶段请勿捏造信息。 对于任何未知信息,请使用占位符。
git add -A
git commit -m "setup: create {artist-name} artist workspace"
git push origin main
lowercase-kebab-case(例如 gatsby-grace,a-thing-called-love)songs/a-thing-called-love/a-thing-called-love.mp3)content/videos/shortform/)。{placeholder} 语法 —— 这比空白字段更好。not-setup 和 null 的文件不是占位符 —— 而是杂乱信息。服务、账户和配置应在它们成为现实时添加。songs/ 中,发行通过 slug 引用它们。内容存放在 content/ 中,不复制到其他地方。每周安装量
1.1K
代码仓库
首次出现
2026年2月18日
安全审计
安装于
openclaw1.1K
opencode1.1K
codex1.1K
gemini-cli1.1K
github-copilot1.1K
amp1.1K
RECOUP.md and create the directory structureRECOUP.md to get the artist's name, slug, and ID:cd orgs/{org}/artists/{artist-slug}
cat RECOUP.md
2. Create the directory structure:
mkdir -p {context/images,memory,songs,releases,content/images,content/videos,config,library,apps}
RECOUP.mdUpdate the status field from not-setup to active and replace the body with a brief description:
---
artistName: {Artist Name}
artistSlug: {artist-slug}
artistId: {uuid-from-recoupable}
status: active
---
# {Artist Name}
Connects this workspace to the Recoupable platform. See `README.md` for the full directory guide and setup checklist.
Create each file from the templates in references/context-files.md. The essential files:
| File | What to do |
|---|---|
context/artist.md | Fill with artist identity, brand, visual world, voice, tone. Ask the user for details or research the artist. |
context/audience.md | Fill with audience insights. Focus on WHY they listen, what they relate to, how they talk. |
context/era.json | Set the current release, songs, phase, and career stage. |
context/tasks.md | Leave blank — the user will add tasks as they come up. |
context/images/README.md | Create with a note explaining this holds visual references like face guides. |
Create two files:
memory/README.md — Full instructions for agents on how to use the memory system, including the scope concept. See references/memory-system.md.memory/MEMORY.md — Nearly empty starting point with frontmatter and guidelines comment (including scope rules).The memory system uses three scopes to prevent knowledge bloat:
MEMORY.md)MEMORY.md, tagged with era)log/ only, never MEMORY.md)Agents should ask the user about scope before saving feedback to long-term memory.
Services are tracked in config/, not pre-filled at setup. Create:
| File | What to do |
|---|---|
config/SERVICES.md | Instructions for agents on how to add services as they're discovered. See references/services-guide.md. |
.env.example | Reference list of common env var names (all commented out). See references/env-template.md. |
.env | Empty file with a header comment. Agents add credentials here as services are connected. |
Do NOT pre-fill service entries. Services are added when the agent has real information — a handle, an API key, a confirmed account. The old approach of creating a massive JSON file with every possible service set to not-setup creates noise, not value.
Each directory needs a README.md explaining its purpose. See references/directory-readmes.md for templates.
| Directory | README explains... |
|---|---|
songs/ | Song folder format, naming conventions, what files to add |
releases/ | Release folder format, RELEASE.md as source of truth |
content/ | Generated content output — images and videos |
config/ | Per-artist config, services, and shared automation tools |
library/ | Deep-dive reference docs, research, reports |
apps/ | Artist-specific applications (not shared tools) |
Create README.md at the artist root with:
See references/root-readme.md for the template.
If you have information about the artist (from the user, from research, or from the Recoup platform):
context/artist.md with as much identity/brand info as possiblecontext/audience.md with audience insightscontext/era.json with the current release phaseDon't fabricate information. Leave placeholders for anything you don't know.
git add -A
git commit -m "setup: create {artist-name} artist workspace"
git push origin main
lowercase-kebab-case (e.g. gatsby-grace, a-thing-called-love)songs/a-thing-called-love/a-thing-called-love.mp3)content/videos/shortform/) as they run.{placeholder} syntax for unknown values — it's better than blank fields.not-setup and null isn't a placeholder — it's clutter. Services, accounts, and configs should be added when they're real.songs/, releases reference them by slug. Content goes in content/, not copied elsewhere.Weekly Installs
1.1K
Repository
First Seen
Feb 18, 2026
Security Audits
Installed on
openclaw1.1K
opencode1.1K
codex1.1K
gemini-cli1.1K
github-copilot1.1K
amp1.1K
React 组合模式指南:Vercel 组件架构最佳实践,提升代码可维护性
103,800 周安装