Agent skill

Atlas Cloud

by calesthio in calesthio/OpenMontage

Generate or edit images and videos through the Atlas Cloud gateway.

AGPL-3.0Auto-check passedMedia & Creative

Install Atlas Cloud

skills CLI
$ npx skills add calesthio/OpenMontage --skill atlas-cloud -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install calesthio/OpenMontage atlas-cloud --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/calesthio/OpenMontage.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/atlas-cloud .claude/skills/atlas-cloud && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
atlas-cloud
GitHub stars
66k
Token cost
~1.2k tokens
SKILL.md length
443 words
Files
1
Skills in repo
41
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Generate or edit images and videos through the Atlas Cloud gateway.

  • Works in 5 steps: Read tool.get_info()["model_catalog"];… → Select an exact model id and operation… → Announce the Atlas tool, provider, exact… → …
  • Atlas-hosted Seedance 2.5/2.0
  • SKILL.md covers Preflight every paid call, Video routes, Image routes and Result and failure contract
  • Needs ATLASCLOUD_API_KEY and ATLAS_CLOUD_API_KEY

What it does

Atlas Cloud is an agent skill from calesthio/OpenMontage. Generate or edit images and videos through the Atlas Cloud gateway. Use for Atlas-hosted Seedance 2.5/2.0, Gemini Omni Flash, MiniMax H3, Seedream 5.0, GPT Image 2, Nano Banana 2, or when one ATLASCLOUDAPIKEY should access multiple media model families.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Media & Creative, covering Image generation, AI video generation and Image editing. It works with Seedance, MiniMax and Google Gemini. The repository describes itself as: World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant… The licence is AGPL-3.0.

When your agent uses it

  • Atlas-hosted Seedance 2.5/2.0
  • Gemini Omni Flash
  • One ATLASCLOUDAPIKEY should access multiple media model families

Example prompts

  • “/atlas-cloud”

Requirements

  • Python 3
  • A credential in ATLASCLOUD_API_KEY
  • A credential in ATLAS_CLOUD_API_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read tool.get_info()["model_catalog"]; do not infer availability from a
  2. Select an exact model id and operation supported by that catalog.
  3. Announce the Atlas tool, provider, exact model, request count, and estimated
  4. Use local-path inputs when convenient. The tool uploads them through Atlas.
  5. Save outputs inside the active projects// tree and inspect them.

What it can do on your machine

Read from SKILL.md and the folder at commit 9327439. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ATLASCLOUD_API_KEY
    • ATLAS_CLOUD_API_KEY
    • ATLAS_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Atlas Cloud loads about 1.2k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 443 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from calesthio/OpenMontage at commit 9327439, republished under its AGPL-3.0 licence (© calesthio). 443 words, ~1,152 tokens.

Download SKILL.mdSave it as .claude/skills/atlas-cloud/SKILL.md (or your agent's skills folder).
name
atlas-cloud
description
Generate or edit images and videos through the Atlas Cloud gateway. Use for Atlas-hosted Seedance 2.5/2.0, Gemini Omni Flash, MiniMax H3, Seedream 5.0, GPT Image 2, Nano Banana 2, or when one ATLASCLOUD_API_KEY should access multiple media model families.

Atlas Cloud

Route complete productions through image_selector or video_selector. Call atlas_image or atlas_video directly when the user names Atlas Cloud or an exact Atlas model. Never substitute a direct vendor endpoint for an Atlas request.

Set ATLASCLOUD_API_KEY. The aliases ATLAS_CLOUD_API_KEY and ATLAS_API_KEY are accepted for compatibility.

Preflight every paid call

  1. Read tool.get_info()["model_catalog"]; do not infer availability from a search collection or invent a task suffix.
  2. Select an exact model id and operation supported by that catalog.
  3. Announce the Atlas tool, provider, exact model, request count, and estimated cost before submitting.
  4. Use local-path inputs when convenient. The tool uploads them through Atlas.
  5. Save outputs inside the active projects/<project-id>/ tree and inspect them.

Video routes

FamilyOperationsExact route notes
Seedance 2.5text, image, referencebytedance/seedance-2.5/{text,image,reference}-to-video; image mode uses image plus optional last_image; reference mode accepts up to 30 images, 10 videos, and 10 audios (including audio-only); 4–30s; $0.134/s
Seedance 2.0text, image, referencebytedance/seedance-2.0/{text,image,reference}-to-video; 4–15s; $0.112/s
Gemini Omni Flashtext, image, reference, video editStandard routes use google/gemini-omni-flash/...; developer routes exist for text/image/reference only. Standard image mode uses one image; standard reference uses images; developer reference requires one video_clips object.
MiniMax H3text, image, referenceminimax/h3/{text,image,reference}-to-video; image mode supports optional end_image; reference mode requires refers objects; 4–15s; 768P/2K; $0.10/s

Use canonical OpenMontage fields:

python
tool.execute({
    "prompt": "...",
    "model": "minimax/h3/reference-to-video",
    "operation": "reference_to_video",
    "duration": 10,
    "resolution": "2K",
    "reference_images": ["projects/demo/character.png"],
    "reference_audios": ["projects/demo/performance.wav"],
    "output_path": "projects/demo/h3.mp4",
})

For Gemini developer reference video, pass video_clips objects with url, start, and ends. For H3, callers may pass normalized reference_images, reference_videos, and reference_audios; the tool converts them to refers.

Do not silently clamp duration, resolution, or ratio. Invalid values must fail before billing with the supported choices in the error.

Show full SKILL.md (176 more words)Show less

Image routes

FamilyOperationsExact route notes
Seedream 5.0 Progenerate, edit, decomposebytedance/seedream-v5.0-pro/text-to-image, /edit, /layer-decomposition; edit accepts up to 10 images; sizes use WIDTH*HEIGHT
Seedream 5.0 Liteeditbytedance/seedream-v5.0-lite/edit; no live Lite text-to-image sibling is assumed; accepts up to 14 images
GPT Image 2generate, editopenai/gpt-image-2/text-to-image, /edit; sizes use WIDTHxHEIGHT; edit accepts up to 10 images
Nano Banana 2generate, editgoogle/nano-banana-2/text-to-image, /edit; uses aspect ratio plus 1k/2k/4k resolution; edit accepts up to 14 images

Set generation_mode to generate, edit, or decompose. Source images can be supplied as image_path, image_paths, image_url, or image_urls.

python
tool.execute({
    "prompt": "Replace the packaging with matte cobalt glass; preserve the logo",
    "model": "google/nano-banana-2/edit",
    "generation_mode": "edit",
    "image_paths": ["projects/campaign/source.png"],
    "resolution": "2k",
    "output_path": "projects/campaign/revised.png",
})

Result and failure contract

Both tools submit to Atlas, poll the returned prediction id, download every output, and return ToolResult provenance containing the provider, exact model, prediction id, submitted parameters, source URL, artifact paths, and estimated cost. A missing key, unsupported route, invalid enum, missing media input, failed prediction, timeout, or download failure must return a failed result without switching providers.

Confirm current pricing and schemas from the machine-readable model page (Accept: text/markdown) immediately before quoting or spending on a batch.

© calesthio, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/atlas-cloud of calesthio/OpenMontage.

Open the folder on GitHubat commit 9327439

Compare with similar skills

Atlas Cloud next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Atlas Cloud compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Atlas Cloud this skillcalesthio/OpenMontage66k—~1.2kAutomated safety check: PassAGPL-3.0
HiggsfieldOSideMedia/higgsfield-ai-prompt-skill713—~9.1kAutomated safety check: PassMIT
Editorial Collage MotionPluviobyte/rnskill1.6k—~1.2kAutomated safety check: PassCustom licence
Higgsfield ModelsOSideMedia/higgsfield-ai-prompt-skill713—~7kAutomated safety check: PassMIT
Seedance Storyboard Generatorliangdabiao/Seedance2-Storyboard-Generator2.6k—~2.2kAutomated safety check: PassNone
Imagesmixs/visual-skills494—~2.1kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Higgsfield

    OSideMedia/higgsfield-ai-prompt-skill

    A skill your agent uses whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano…

    713 GitHub stars~9.1k tokensUpdated 13 days ago
    Media & CreativeAuto-check passed
  • Editorial Collage Motion

    Pluviobyte/rnskill

    将参考图或简要描述解码为可编辑的半色调纸张拼贴规范,默认使用 Codex 内置 imagegen 生成品牌一致的静帧和透明图层,再用本地 FFmpeg 或 HyperFrames 制作“从空背景逐件组装”的确定性动态视频。用户提到半色调拼贴、纸张拼贴、剪纸拼贴、编辑式拼贴、杂志拼贴、复古印刷拼贴、拼贴动效、拼贴动画、剪纸动画、纸片组装、逐层组装、从无到有、元素飞入拼装、定格拼贴、定格动画、Arc…

    1.6k GitHub stars~1.2k tokensUpdated 19 days ago
    Media & CreativeAuto-check passed
  • Higgsfield Models

    OSideMedia/higgsfield-ai-prompt-skill

    A skill your agent uses when the user asks which model to use, wants to compare models, or needs guidance on selecting between Kling, Wan (incl.

    713 GitHub stars~7k tokensUpdated 13 days ago
    Media & CreativeAuto-check passed
  • Seedance Storyboard Generator

    liangdabiao/Seedance2-Storyboard-Generator

    专业的Seedance 2.0平台AI视频脚本和分镜生成器。当用户要求:(1) 将文章/故事转换为视频脚本,(2) 生成Seedance 2.0分镜提示词,(3) 规划多集AI视频系列,(4) 为GPT-Image-2、Seedream、Nano Banana…

    2.6k GitHub stars~2.2k tokensUpdated 19 days ago
    Media & CreativeAuto-check passed
  • Image

    smixs/visual-skills

    Image prompting skill for Nano Banana (NBP/NB2) and GPT Image 2.5 (Flare/Sunburst).

    494 GitHub stars~2.1k tokensUpdated 23 days ago
    Media & CreativeAuto-check passed
  • Video

    Nexus-JPF/note-companion

    When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks.

    870 GitHub starsUsed in 3 repos~3.6k tokens
    Media & CreativeAuto-check passed

More from calesthio/OpenMontage

All 41 skills in this repo
  • Video Understand

    calesthio/OpenMontage

    Understand video content locally using ffmpeg frame extraction and Whisper transcription.

    66k GitHub stars~841 tokensUpdated 6 days ago
    Auto-check passed
  • Avatar Video

    calesthio/OpenMontage

    Create AI avatar videos with precise control over avatars, voices, scripts, scenes, and backgrounds using HeyGen's v2 API.

    66k GitHub stars~1.6k tokensUpdated 6 days ago
    Auto-check passed
  • D3 Viz

    calesthio/OpenMontage

    Creating interactive data visualisations using d3.js. An agent skill from calesthio/OpenMontage.

    66k GitHub starsUsed in 3 repos~5.4k tokens
    Auto-check passed
  • Create Video

    calesthio/OpenMontage

    Create videos from a text prompt using HeyGen's Video Agent.

    66k GitHub stars~1.3k tokensUpdated 6 days ago
    Auto-check passed
  • Threejs World Generation

    calesthio/OpenMontage

    Build deterministic, editable, free-viewpoint Three.js worlds from text or structured briefs.

    66k GitHub stars~2k tokensUpdated 6 days ago
    Auto-check passed
  • Video Edit

    calesthio/OpenMontage

    Edit videos locally using ffmpeg. An agent skill from calesthio/OpenMontage.

    66k GitHub stars~855 tokensUpdated 6 days ago
    Auto-check: notes

Questions about Atlas Cloud

What does Atlas Cloud do?

Generate or edit images and videos through the Atlas Cloud gateway. Atlas Cloud is an agent skill from calesthio/OpenMontage. Generate or edit images and videos through the Atlas Cloud gateway.

When should I use Atlas Cloud?

Atlas Cloud fits situations like: atlas-hosted Seedance 2.5/2.0; gemini Omni Flash; one ATLASCLOUDAPIKEY should access multiple media model families.

How do I install Atlas Cloud in Claude Code?

Run `npx skills add calesthio/OpenMontage --skill atlas-cloud -a claude-code`. Or copy the skill folder (.agents/skills/atlas-cloud in calesthio/OpenMontage) into .claude/skills/atlas-cloud in your project. Claude Code loads it when a task matches its description.

How do I install Atlas Cloud in Codex?

Run `npx skills add calesthio/OpenMontage --skill atlas-cloud -a codex`. Or copy the skill folder (.agents/skills/atlas-cloud in calesthio/OpenMontage) into .agents/skills/atlas-cloud in your project. Codex loads it when a task matches its description.

Can I use Atlas Cloud in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add calesthio/OpenMontage --skill atlas-cloud -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/atlas-cloud, .gemini/skills/atlas-cloud, .github/skills/atlas-cloud and .opencode/skills/atlas-cloud in your project.

What does Atlas Cloud need to run?

Going by SKILL.md and its folder, Atlas Cloud needs credentials named ATLASCLOUD_API_KEY, ATLAS_CLOUD_API_KEY and ATLAS_API_KEY. Our summary lists: Python 3; A credential in ATLASCLOUD_API_KEY; A credential in ATLAS_CLOUD_API_KEY.

Does Atlas Cloud access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Atlas Cloud safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Atlas Cloud use?

Atlas Cloud is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Atlas Cloud use?

About 1.2k tokens (SKILL.md is roughly 4.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Atlas Cloud?

Skills that share tags, products or a category with Atlas Cloud: Higgsfield (OSideMedia/higgsfield-ai-prompt-skill, 713 stars), Editorial Collage Motion (Pluviobyte/rnskill, 1.6k stars), Higgsfield Models (OSideMedia/higgsfield-ai-prompt-skill, 713 stars) and Seedance Storyboard Generator (liangdabiao/Seedance2-Storyboard-Generator, 2.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Atlas Cloud?

calesthio (a GitHub user) maintains it in calesthio/OpenMontage, which has 65,930 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 3, 2026.

Source: calesthio/OpenMontage on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.