Stats
Actions
Tags
From omni
Manages Omni batch jobs for media/content processing: estimate costs, create time-based/chat-targeted/media redownload jobs, list/monitor status, cancel. For bulk syncs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/omni:omni-batchThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
```bash
omni batch estimate --instance <id> --type time_based_batch --days 7 --content-types audio,image --json
omni batch estimate --instance <id> --type targeted_chat_sync --chat <chatId> --limit 200 --json
# Time-window job
omni batch create --instance <id> --type time_based_batch --days 30 --content-types audio,video --limit 500 --json
# Chat-targeted job
omni batch create --instance <id> --type targeted_chat_sync --chat <chatId> --limit 200 --json
# Media redownload
omni batch create --instance <id> --type media_redownload --days 14 --content-types image,document --force --json
omni batch list --instance <id> --status running,failed --limit 50 --json
omni batch status <jobId> --json
omni batch status <jobId> --watch --interval 2000 --json
omni batch cancel <jobId> --json
targeted_chat_sync, time_based_batch, media_redownload.--no-confirm in non-interactive scripts.npx claudepluginhub automagik-dev/omni --plugin omniProcesses thousands of documents asynchronously using Google's Gemini Batch API at 50% lower cost. Enforces correct API patterns to avoid silent failures.
Manages Omni automations via bash CLI: create/read/update/delete, enable/disable, test/execute with event payloads, inspect logs. For event-driven automation workflows.
High-volume, asynchronous offline inference via Together AI's Batch API. Prepares JSONL inputs, uploads files, creates jobs, polls status, and downloads outputs for bulk classification, synthetic data generation, and dataset transformations.