Agent skill

Atlas Video Gen

Generate one Veo 3.1 Lite video through Atlas Cloud. An agent skill from aAAaqwq/AGI-Super-Team.

Install Atlas Video Gen

skills CLI

$ npx skills add aAAaqwq/AGI-Super-Team --skill atlas-video-gen -a claude-code

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

GitHub CLI

$ gh skill install aAAaqwq/AGI-Super-Team atlas-video-gen --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/aAAaqwq/AGI-Super-Team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/atlas-video-gen .claude/skills/atlas-video-gen && 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/

Paste into Claude Code

Install the "atlas-video-gen" agent skill from https://github.com/aAAaqwq/AGI-Super-Team/tree/main/skills/atlas-video-gen into .claude/skills/atlas-video-gen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "atlas-video-gen", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/aAAaqwq/AGI-Super-Team/tree/main/skills/atlas-video-gen

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add aAAaqwq/AGI-Super-Team --skill atlas-video-gen -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install aAAaqwq/AGI-Super-Team atlas-video-gen --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/atlas-video-gen .agents/skills/atlas-video-gen && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "atlas-video-gen" agent skill from https://github.com/aAAaqwq/AGI-Super-Team/tree/main/skills/atlas-video-gen into .agents/skills/atlas-video-gen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "atlas-video-gen", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add aAAaqwq/AGI-Super-Team --skill atlas-video-gen -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install aAAaqwq/AGI-Super-Team atlas-video-gen --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/atlas-video-gen .cursor/skills/atlas-video-gen && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "atlas-video-gen" agent skill from https://github.com/aAAaqwq/AGI-Super-Team/tree/main/skills/atlas-video-gen into .cursor/skills/atlas-video-gen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "atlas-video-gen", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/aAAaqwq/AGI-Super-Team.git --path skills/atlas-video-gen

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add aAAaqwq/AGI-Super-Team --skill atlas-video-gen -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install aAAaqwq/AGI-Super-Team atlas-video-gen --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/atlas-video-gen .gemini/skills/atlas-video-gen && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "atlas-video-gen" agent skill from https://github.com/aAAaqwq/AGI-Super-Team/tree/main/skills/atlas-video-gen into .gemini/skills/atlas-video-gen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "atlas-video-gen", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install aAAaqwq/AGI-Super-Team atlas-video-gen

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add aAAaqwq/AGI-Super-Team --skill atlas-video-gen -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/atlas-video-gen .github/skills/atlas-video-gen && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "atlas-video-gen" agent skill from https://github.com/aAAaqwq/AGI-Super-Team/tree/main/skills/atlas-video-gen into .github/skills/atlas-video-gen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "atlas-video-gen", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add aAAaqwq/AGI-Super-Team --skill atlas-video-gen -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install aAAaqwq/AGI-Super-Team atlas-video-gen --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/aAAaqwq/AGI-Super-Team.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/atlas-video-gen .opencode/skills/atlas-video-gen && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "atlas-video-gen" agent skill from https://github.com/aAAaqwq/AGI-Super-Team/tree/main/skills/atlas-video-gen into .opencode/skills/atlas-video-gen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "atlas-video-gen", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: atlas-video-gen
GitHub stars: 105
Token cost: ~890 tokens
SKILL.md length: 379 words
Files: 3 (incl. scripts)
Skills in repo: 167
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Generate one Veo 3.1 Lite video through Atlas Cloud. An agent skill from aAAaqwq/AGI-Super-Team.

Works in 6 steps: Turn the request into a concise English… → Preview the helper command without --yes. → Obtain explicit human approval for the… → …
Text-to-video needs an Atlas route
SKILL.md covers Prerequisites, Safety Boundary, Usage and Supported Inputs, plus 4 more sections
Runs Python scripts from its folder; calls python; reaches api.atlascloud.ai; needs ATLASCLOUD_API_KEY

What it does

Atlas Video Gen is an agent skill from aAAaqwq/AGI-Super-Team. Generate one Veo 3.1 Lite video through Atlas Cloud. Use when text-to-video needs an Atlas route, explicit paid-request confirmation, bounded polling, and a local MP4.

Its SKILL.md is about 890 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/generate_video.py` and `scripts/test_generate_video.py`).

It sits in Media & Creative, covering AI video generation. It works with Google Veo. The repository describes itself as: An installable, cross-framework AI organization: C-suite agents, expert subagents, curated skills, independent review, and one-command setup across 18 AI client/runtime adapters. The licence is MIT.

When your agent uses it

Text-to-video needs an Atlas route
Explicit paid-request confirmation
Bounded polling

Example prompts

“/atlas-video-gen”

Requirements

Python 3
A credential in ATLASCLOUD_API_KEY

Workflow steps

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

Turn the request into a concise English video prompt with subject motion,
Preview the helper command without --yes.
Obtain explicit human approval for the displayed model and parameters.
Run once with --yes.
Wait for terminal prediction status and report the saved MP4 path.
On an ambiguous submission or failure, do not resubmit automatically.

What it can do on your machine

Read from SKILL.md and the folder at commit 7cefd81. 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
Ships 2 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- api.atlascloud.ai
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
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Atlas Video Gen loads about 890 tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 379 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~46
When it runs · the whole SKILL.md, loaded when a task matches: ~890

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); the scripts in this folder are not scanned.

SKILL.md

The full file from aAAaqwq/AGI-Super-Team at commit 7cefd81, republished under its MIT licence (© aAAaqwq). 379 words, ~890 tokens.

Download SKILL.mdSave it as .claude/skills/atlas-video-gen/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: atlas-video-gen
description: Generate one Veo 3.1 Lite video through Atlas Cloud. Use when text-to-video needs an Atlas route, explicit paid-request confirmation, bounded polling, and a local MP4.

Atlas Cloud Video Generation

Generate one text-to-video clip with Atlas Cloud's google/veo3.1-lite/text-to-video model. This is an opt-in workflow and does not replace any other video provider.

Prerequisites

Python 3.10 or newer; the helper uses only the standard library.
An Atlas Cloud API key in ATLASCLOUD_API_KEY.
Outbound HTTPS access to api.atlascloud.ai and the returned output URL.

Set the key in the environment. Never put it in a prompt, command argument, source file, or log.

bash

export ATLASCLOUD_API_KEY="..."

Safety Boundary

Running a generation request may incur charges. The helper prints the exact request plan and exits without network access unless --yes is present.

The generation POST is sent exactly once and is never retried. Only prediction and output GET requests use bounded retries for transient failures. If the submission result is unclear, stop and inspect the Atlas Cloud console instead of running the command again.

Usage

Preview the request first:

bash

python skills/atlas-video-gen/scripts/generate_video.py \
  "A slow aerial orbit around a lighthouse at sunrise" \
  --output lighthouse.mp4

After reviewing the plan, confirm one paid submission:

bash

python skills/atlas-video-gen/scripts/generate_video.py \
  "A slow aerial orbit around a lighthouse at sunrise" \
  --output lighthouse.mp4 \
  --duration 4 \
  --ratio 16:9 \
  --resolution 720p \
  --yes

Use --json for a machine-readable result. The default timeout is 10 minutes, and --poll-interval controls prediction polling frequency.

Supported Inputs

Option	Values	Default
`--duration`	`4`, `6`, `8`	`8`
`--ratio`	`16:9`, `9:16`	`16:9`
`--resolution`	`720p`, `1080p`	`720p`
`--seed`	integer; `-1` requests a random seed	`-1`

Atlas Cloud's current schema requires an 8-second duration for 1080p output. The helper validates that rule before submitting.

Show full SKILL.md (164 more words)Show less

Workflow

Turn the request into a concise English video prompt with subject motion, camera movement, setting, lighting, and audio cues when relevant.
Preview the helper command without --yes.
Obtain explicit human approval for the displayed model and parameters.
Run once with --yes.
Wait for terminal prediction status and report the saved MP4 path.
On an ambiguous submission or failure, do not resubmit automatically.

Limitations

This helper supports text-to-video only. Use a separate image-to-video skill when a start or end frame is required.
Model availability and accepted parameters can change. If Atlas Cloud rejects a previously valid request, check the live model catalog and schema before changing the helper.
Generated media remains subject to Atlas Cloud and model content policies.

Test Evidence

Run the focused standard-library tests with:

bash

python -m unittest -v skills/atlas-video-gen/scripts/test_generate_video.py

The tests cover schema-aligned payloads, the single-POST boundary, wrapped and flat API responses, preview mode, and the 1080p duration constraint.

API References

Model catalog: https://api.atlascloud.ai/api/v1/models
Submit: POST https://api.atlascloud.ai/api/v1/model/generateVideo
Poll: GET https://api.atlascloud.ai/api/v1/model/prediction/{id}

Files

SKILL.md and 2 other files (scripts) in skills/atlas-video-gen of aAAaqwq/AGI-Super-Team.

SKILL.md
scripts/generate_video.py
scripts/test_generate_video.py

Open the folder on GitHubat commit 7cefd81

Compare with similar skills

Atlas Video Gen 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 Video Gen compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Atlas Video Gen this skillaAAaqwq/AGI-Super-Team	105	—	~890	Automated safety check: Pass	MIT	2 days ago
Veo Usecnemri/google-genai-skills	127	—	~625	Automated safety check: Pass	MIT	8 mo ago
Veo Buildcnemri/google-genai-skills	127	—	~513	Automated safety check: Pass	MIT	8 mo ago
Video Gen UsageOtoDock/oto-dock	190	—	~1.4k	Automated safety check: Pass	Custom licence	3 days ago
Capcutsocial-media-skills/skills	134	—	~2k	Automated safety check: Pass	MIT	9 days ago
Klingsocial-media-skills/skills	134	—	~1.3k	Automated safety check: Pass	MIT	9 days ago

Similar skills

Veo Use
cnemri/google-genai-skills
Create and edit videos using Google's Veo 2 and Veo 3 models.
127 GitHub stars~625 tokensUpdated 8 mo ago
Media & CreativeAuto-check passed
Veo Build
cnemri/google-genai-skills
Create and edit videos using Google's Veo 2 and Veo 3 models.
127 GitHub stars~513 tokensUpdated 8 mo ago
Media & CreativeAuto-check passed
Video Gen Usage
OtoDock/oto-dock
Generate AI videos, transitions between clips, and AI video edits.
190 GitHub stars~1.4k tokensUpdated 3 days ago
Media & CreativeAuto-check passed
Capcut
social-media-skills/skills
The CapCut craft skill — edit short-form social video (TikTok, Reels, Shorts) fast and safely: retention-paced cuts, auto-captions, beat-synced sound, exports.
134 GitHub stars~2k tokensUpdated 9 days ago
Media & CreativeAuto-check passed
Kling
social-media-skills/skills
The generative-video producer for native 4K, multi-shot storyboarding, and motion-transfer (Kling-led).
134 GitHub stars~1.3k tokensUpdated 9 days ago
Media & CreativeAuto-check passed
Runway
social-media-skills/skills
Prompt and direct Runway (Gen-4.5, Aleph) — the control-grade generative video tool for camera moves, character consistency, and edit-grade shots.
134 GitHub stars~1.3k tokensUpdated 9 days ago
Media & CreativeAuto-check passed

Questions about Atlas Video Gen

What does Atlas Video Gen do?

Generate one Veo 3.1 Lite video through Atlas Cloud. An agent skill from aAAaqwq/AGI-Super-Team. Atlas Video Gen is an agent skill from aAAaqwq/AGI-Super-Team.1 Lite video through Atlas Cloud.

When should I use Atlas Video Gen?

Atlas Video Gen fits situations like: text-to-video needs an Atlas route; explicit paid-request confirmation; bounded polling.

How do I install Atlas Video Gen in Claude Code?

Run `npx skills add aAAaqwq/AGI-Super-Team --skill atlas-video-gen -a claude-code`. Or copy the skill folder (skills/atlas-video-gen in aAAaqwq/AGI-Super-Team) into .claude/skills/atlas-video-gen in your project. Claude Code loads it when a task matches its description.

How do I install Atlas Video Gen in Codex?

Run `npx skills add aAAaqwq/AGI-Super-Team --skill atlas-video-gen -a codex`. Or copy the skill folder (skills/atlas-video-gen in aAAaqwq/AGI-Super-Team) into .agents/skills/atlas-video-gen in your project. Codex loads it when a task matches its description.

Can I use Atlas Video Gen 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 aAAaqwq/AGI-Super-Team --skill atlas-video-gen -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-video-gen, .gemini/skills/atlas-video-gen, .github/skills/atlas-video-gen and .opencode/skills/atlas-video-gen in your project.

What does Atlas Video Gen need to run?

Going by SKILL.md and its folder, Atlas Video Gen needs Python for the scripts in its folder, the command-line tools its instructions call (python) and credentials named ATLASCLOUD_API_KEY. Our summary lists: Python 3; A credential in ATLASCLOUD_API_KEY.

Does Atlas Video Gen access the network?

SKILL.md names 1 domain. In commands or code: api.atlascloud.ai; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Atlas Video Gen 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Atlas Video Gen use?

Atlas Video Gen is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Atlas Video Gen use?

About 890 tokens (SKILL.md is roughly 3.6k 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 Video Gen?

Skills that share tags, products or a category with Atlas Video Gen: Veo Use (cnemri/google-genai-skills, 127 stars), Veo Build (cnemri/google-genai-skills, 127 stars), Video Gen Usage (OtoDock/oto-dock, 190 stars) and Capcut (social-media-skills/skills, 134 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Atlas Video Gen?

aAAaqwq (a GitHub user) maintains it in aAAaqwq/AGI-Super-Team, which has 105 GitHub stars. The repository holds 167 skills in this directory. The repository was last updated on October 8, 2026.

Source: aAAaqwq/AGI-Super-Team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Atlas Video Gen

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Atlas Cloud Video Generation

Prerequisites

Safety Boundary

Usage

Supported Inputs

Workflow

Limitations

Test Evidence

API References

Files

Compare with similar skills

Similar skills

More from aAAaqwq/AGI-Super-Team

Related

Questions about Atlas Video Gen