Agent skill · ma08
sora
Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI\u2019s video API using the bundled CLI (`scripts/sora.py`), including requests like \u201cgenerate AI video,\u201d \u201cSora,\u201d \u201cvideo remix,\u201d \u201cdownload video/thumbnail/spritesheet,\u201d and batch video generation; requires `OPENAI_API_KEY` and Sora API access.
What it needs
About 5k tokens when loaded.
What this skill does
Sora Video Generation Skill Creates or manages short video clips for the current project (product demos, marketing spots, cinematic shots, UI mocks). Defaults to sora-2 and a structured prompt augmentation workflow, and prefers the bundled CLI for deterministic runs. Note: $sora is a skill tag in prompts, not a shell command. When to use Generate a new video clip from a prompt Remix an existing video by ID Poll status, list jobs, or download assets (video/thumbnail/spritesheet) Batch runs (many prompts or variants) Decision tree (create vs remix vs status/download vs batch) If the user has a video id and wants a change → remix If the user has a video id and wants status or assets → status/poll/download If the user needs many prompts/assets → create-batch If the user asks for two versions with a small change (same shot, different subject/detail) → create the base, then remix for the variation Otherwise → create (or create-and-poll if they need a ready asset in one step) Workflow 1. Decide intent: create vs remix vs status/download vs batch. 2. Collect inputs: prompt, model, size, seconds, and any input reference image. 3. If batch: write a temporary JSONL under tmp/ (one job per line), run once, then delete the JSONL. 4. Prefer CLI augmentation flags (--use-case, --scene, --camera, etc.) instead of pre-writing a structured prompt. If you already produced a structured prompt file, pass --no-augment to avoid double-wrapping. 5. Run the bundled CLI (scripts/sora.py) with sensible defaults (see references/cli.md). For long prompts, prefer --prompt-file to avoid shell-escaping issues; pair with --no-augment if the prompt is already structured. 6. For async jobs, poll until complete (or use create-and-poll). 7. Download assets (video/thumbnail/spritesheet) and save locally. 8. Remove intermediate files created during invocation (for example prompt.txt, remixjob.json, temp JSONL). If the sandbox blocks rm, skip cleanup or truncate the files without surfacing an error. 9. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills ma08/sora