Atlas Cloud logo

Atlas Cloud

Community
infometa
atlas-cloud

How to use the Atlas Cloud connector tools (atlas_*) correctly: find a model in the live catalog, read its schema and price, submit image / video / audio / transcription jobs, handle the server's quote-and-confirm step, poll results, upload local files, and deliver outputs. Use whenever an atlas_* tool is about to be called or the user asks to generate images, video, voice or music with Atlas Cloud.

Overview

Publisherinfometa
Repositoryworkbuddyskills
Skill nameatlas-cloud
Stars
376
Forks
124
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by infometa on GitHub. Read the source before you install it.

Installation

Install the Atlas Cloud AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/infometa/workbuddyskills/tree/main/connectors/atlas-cloud/skills/atlas-cloud
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/infometa/workbuddyskills.git /tmp/workbuddyskills
mkdir -p .claude/skills
cp -r /tmp/workbuddyskills/connectors/atlas-cloud/skills/atlas-cloud .claude/skills/atlas-cloud
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Atlas Cloud in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Atlas Cloud on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Atlas Cloud is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Atlas Cloud 连接器使用指南

Atlas Cloud 连接器通过一个统一接口提供三百多个生成模型(图像、视频、语音、音乐、转写)。 用户通过账号授权连接,生成费用记在用户自己的 Atlas 账户上。

工具一览

工具用途是否计费
atlas_list_models按类型列出模型否
atlas_search_docs按关键词搜模型和文档否
atlas_get_model_info查单个模型的参数 schema、枚举值、默认值、定价否
atlas_get_model_costs生成前估算这一次的费用否
atlas_get_upload_url换上传票据,把本地文件变成公网 URL否
atlas_generate_image / atlas_generate_video / atlas_generate_audio提交生成任务是
atlas_transcribe_audio音频转文字是
atlas_quick_generate一步出结果,适合简单单张图是
atlas_get_prediction查询异步任务状态和结果否
atlas_list_predictions列最近的任务,找回丢失的任务 ID否
atlas_get_balance / atlas_get_model_usage查余额和用量否

所有操作都走这些工具。不要用 curl 直接调 Atlas 的 REST API:这里是账号授权连接, 环境里没有 API Key,直接调只会 401。唯一的例外是上传(见下文)。

1. 模型和参数一律现查

模型目录经常变。每次生成前:

  1. 用 atlas_search_docs 或 atlas_list_models 找候选模型
  2. 用 atlas_get_model_info 取该模型的参数 schema、枚举值、默认值和定价
  3. 严格按 schema 构造参数

不要凭记忆写模型 ID 或参数名。常见错误:模型要 ratio 却传了 aspect_ratio, 要 image 却传了 image_url。schema 里没有的参数就是不存在。

2. 提交前报价

提交计费任务前,用 atlas_get_model_costs 估算费用并告诉用户。 能力相当的模型价差可能很大(视频每秒单价能差三倍以上),先比价再推荐。

3. 幂等键与服务端确认

五个计费工具都要求 idempotency_key(一个 UUID):

  • 每次新的生成都换一个新的 key;只有重试完全相同的请求才复用旧 key。

调用后可能拿到的不是任务 ID,而是一份报价和一个 confirmation_token。 这表示服务端没有提交、没有扣费,在等用户确认。这不是失败:

  1. 把报价原样告诉用户,停下等回复。
  2. 用户明确同意后,用同一个 idempotency_key、一字未改的参数、加上 confirmation_token 再调一次。
  3. 换了 key 或改了参数,令牌就失效,会再被拦一次。不要反复换 key 重试。

视频任务按秒计费,服务端算不出精确价时一律转确认,金额再小也一样。

4. 轮询与结果

提交成功后拿到 prediction ID,用 atlas_get_prediction 轮询。

  • 返回成功状态之前,不要说任务完成,也不要给出任何产物链接。
  • failed 是终点,再轮询也不会变。把 error 原文告诉用户,建议换一个能力相当的模型或原样重提。 No available upstream channel / Upstream access denied 是上游路由问题,换模型能绕开。
  • 提交时的金额是预估;失败的任务不计费。确认成功之前说"预计 $X",不要说"已扣费"。
  • 找不到之前的任务 ID 时,用 atlas_list_predictions 找回。

5. 上传本地文件

远程服务读不到用户本机的文件,本地路径直接填进生成参数一定失败。

  1. 调 atlas_get_upload_url,拿到 upload_url、expires_at、max_bytes 和 curl_example。

  2. 按 curl_example 把文件 POST 上去,文件名(带扩展名)放在 X-Atlas-Filename 头里:

    bash
    curl -sS -X POST "<upload_url>" \
      -H "Content-Type: application/octet-stream" \
      -H "X-Atlas-Filename: product.jpg" \
      --data-binary @"/path/to/product.jpg"
  3. 响应里的 url 就是公网地址,填进 image_url 或音频参数。

  • 票据已带身份,这条 curl 不需要任何 key。
  • 一个 upload_url 在有效期内(约 10 分钟)可传多个文件。上传不计费。
  • 超过 max_bytes(默认 32MB)会被拒,请用户提供公网链接。
  • curl 失败或响应里没有 url,如实说没传上去,不要写成"已上传"。

6. 交付

  • 远端 URL 原样复制,不要编造、拼接或改写。
  • 图片用 ![描述](URL),视频音频用带说明的链接,让界面有机会渲染预览。
  • 同时注明完整模型 ID(如 bytedance/seedream-v5.0-lite)和费用。
  • 需要把产物存到本地时,下载失败(502、超时、空文件)要如实说,并给出远端链接。 产出文件存在海外对象存储,国内网络直连有时不通,换网络或代理通常能解决。

7. 授权与失败

  • 看不到 atlas_* 工具,只说明它们还没载入,不说明授权有问题。只有真正调用失败才能判定不可用。
  • 调用失败时如实转述错误原文,不要模拟结果,不要换别的通道顶替。
  • 不要替用户生成涉及真实人物肖像、他人版权角色或违规内容的素材。

Frequently asked questions

What does the Atlas Cloud AI skill do?

How to use the Atlas Cloud connector tools (atlas_*) correctly: find a model in the live catalog, read its schema and price, submit image / video / audio / transcription jobs, handle the server's quote-and-confirm step, poll results, upload local files, and deliver outputs. Use whenever an atlas_* tool is about to be called or the user asks to generate images, video, voice or music with Atlas Cloud.

Why use Atlas Cloud on TypingMind?

Because you install it once and use it with any model. Atlas Cloud is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Atlas Cloud in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/infometa/workbuddyskills/tree/main/connectors/atlas-cloud/skills/atlas-cloud. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Atlas Cloud?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Atlas Cloud?

As many as you like. As long as a model supports skills, you can use Atlas Cloud with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Atlas Cloud AI skill free?

It is published on GitHub by infometa. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇