Find Atlas Cloud image and video models, check their current input requirements and prices, and submit one confirmed generation request. The skill checks progress at fixed intervals with a maximum number of checks and returns generated media URLs.
Discover Atlas Cloud image and video models, inspect their live schemas, and submit one confirmed media generation request with bounded GET polling. Use when integrating Atlas Cloud media APIs or generating images and videos without hard-coding stale model parameters.
Review the instructions the agent will receive before you install.
Use the bundled scripts/atlas_media.py CLI to discover current Atlas Cloud models, inspect a model's live request schema, and run asynchronous image or video generation.
Set the API key in the environment. Never pass it as a CLI argument or commit it to a repository.
export ATLASCLOUD_API_KEY="your-api-key"
ATLASCLOUD_BASE_URL may point to a compatible deployment. It defaults to https://api.atlascloud.ai.
python3 scripts/atlas_media.py models --type Image --query flux
python3 scripts/atlas_media.py models --type Video --query seedance
Treat model availability and prices as live data. Run discovery immediately before choosing a model.
python3 scripts/atlas_media.py describe black-forest-labs/flux-schnell
The command resolves the model's current schema URL and reports the required fields, property definitions, submission endpoint, result endpoint, and catalog price data. Build the payload from this output instead of copying an old example.
{
"prompt": "A clean product photograph on a neutral background",
"size": "1024*1024",
"num_images": 1
}
Do not include model; the CLI inserts the selected model ID after validation.
python3 scripts/atlas_media.py generate \
black-forest-labs/flux-schnell \
--params-file request.json \
--confirm-paid
The --confirm-paid flag is mandatory. The CLI sends exactly one generation POST and does not retry it. It polls only the schema-defined GET result endpoint, with a fixed interval and maximum poll count.
Use stdin when a temporary file is unnecessary:
printf '%s' '{"prompt":"A geometric app icon"}' | \
python3 scripts/atlas_media.py generate \
black-forest-labs/flux-schnell \
--params-file - \
--confirm-paid
Commands write structured JSON to stdout. Successful generation output includes the prediction ID, final status, generated URLs, model ID, and the endpoints resolved from the live schema.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Handle ActiveCampaign contact and marketing tasks through Rube MCP, a connection for agent tools. Find or create contacts, manage tags and subscriptions, enroll contacts in existing automated workflows, and create follow-up tasks.
Research competitors’ live Meta and Google ads to identify opening hooks, offers, calls to action, and landing pages. Receive a sourced creative brief and up to three test ideas adapted to your product.
Add website or app tracking, then use command-line tools to review traffic, signups, drop-off, and returning users across projects. Run A/B tests, which compare alternative headlines or buttons, and inspect results to guide changes.
Establish rules for when an AI agent should recall past context and save lasting decisions, corrections, preferences, and failures. Works with Markdown files or memory services, preserving decision history and surfacing conflicting records.
Audit local AI coding-agent sessions with agenttrace to identify spending, token use, tool failures, and operational problems. Produce readable or structured reports and define pass-or-fail thresholds for automated continuous integration checks.
Audit saved agent sessions for access to private files and evidence that secret values entered an agent's context. Get findings without displaying secrets, identify keys needing rotation, and inspect Claude Code or Codex sessions in a local report.