Skill · em Criar imagem, vídeo e arte

sora

Use when the user asks to generate, remix, poll, list, download, or delete Sora videos via OpenAI’s video API using the bundled CLI (`scripts/sora.py`), including requests like “generate AI video,” “Sora,” “video remix,” “download video/thumbnail/spritesheet,” and batch video generation; requires…

Procedência

Antes de instalar

14 arquivos · 89,1 KB · inclui 1 script que executa: scripts/sora.py

Instalar na sua CLI

O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.

Claude Code

Neste projeto: instala em .claude/skills/sora/.

d=".claude/skills/sora"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/video/sora"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/agents/openai.yaml" "$u/agents/openai.yaml" \
  -o "$d/assets/sora-small.svg" "$u/assets/sora-small.svg" \
  -o "$d/assets/sora.png" "$u/assets/sora.png" \
  -o "$d/LICENSE.txt" "$u/LICENSE.txt" \
  -o "$d/references/cinematic-shots.md" "$u/references/cinematic-shots.md" \
  -o "$d/references/cli.md" "$u/references/cli.md" \
  -o "$d/references/codex-network.md" "$u/references/codex-network.md" \
  -o "$d/references/prompting.md" "$u/references/prompting.md" \
  -o "$d/references/sample-prompts.md" "$u/references/sample-prompts.md" \
  -o "$d/references/social-ads.md" "$u/references/social-ads.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md" \
  -o "$d/references/video-api.md" "$u/references/video-api.md" \
  -o "$d/scripts/sora.py" "$u/scripts/sora.py"

Global: instala em ~/.claude/skills/sora/.

d="$HOME/.claude/skills/sora"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/video/sora"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/agents/openai.yaml" "$u/agents/openai.yaml" \
  -o "$d/assets/sora-small.svg" "$u/assets/sora-small.svg" \
  -o "$d/assets/sora.png" "$u/assets/sora.png" \
  -o "$d/LICENSE.txt" "$u/LICENSE.txt" \
  -o "$d/references/cinematic-shots.md" "$u/references/cinematic-shots.md" \
  -o "$d/references/cli.md" "$u/references/cli.md" \
  -o "$d/references/codex-network.md" "$u/references/codex-network.md" \
  -o "$d/references/prompting.md" "$u/references/prompting.md" \
  -o "$d/references/sample-prompts.md" "$u/references/sample-prompts.md" \
  -o "$d/references/social-ads.md" "$u/references/social-ads.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md" \
  -o "$d/references/video-api.md" "$u/references/video-api.md" \
  -o "$d/scripts/sora.py" "$u/scripts/sora.py"

Codex

Neste projeto: instala em .agents/skills/sora/.

d=".agents/skills/sora"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/video/sora"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/agents/openai.yaml" "$u/agents/openai.yaml" \
  -o "$d/assets/sora-small.svg" "$u/assets/sora-small.svg" \
  -o "$d/assets/sora.png" "$u/assets/sora.png" \
  -o "$d/LICENSE.txt" "$u/LICENSE.txt" \
  -o "$d/references/cinematic-shots.md" "$u/references/cinematic-shots.md" \
  -o "$d/references/cli.md" "$u/references/cli.md" \
  -o "$d/references/codex-network.md" "$u/references/codex-network.md" \
  -o "$d/references/prompting.md" "$u/references/prompting.md" \
  -o "$d/references/sample-prompts.md" "$u/references/sample-prompts.md" \
  -o "$d/references/social-ads.md" "$u/references/social-ads.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md" \
  -o "$d/references/video-api.md" "$u/references/video-api.md" \
  -o "$d/scripts/sora.py" "$u/scripts/sora.py"

Global: instala em ~/.agents/skills/sora/.

d="$HOME/.agents/skills/sora"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/video/sora"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/agents/openai.yaml" "$u/agents/openai.yaml" \
  -o "$d/assets/sora-small.svg" "$u/assets/sora-small.svg" \
  -o "$d/assets/sora.png" "$u/assets/sora.png" \
  -o "$d/LICENSE.txt" "$u/LICENSE.txt" \
  -o "$d/references/cinematic-shots.md" "$u/references/cinematic-shots.md" \
  -o "$d/references/cli.md" "$u/references/cli.md" \
  -o "$d/references/codex-network.md" "$u/references/codex-network.md" \
  -o "$d/references/prompting.md" "$u/references/prompting.md" \
  -o "$d/references/sample-prompts.md" "$u/references/sample-prompts.md" \
  -o "$d/references/social-ads.md" "$u/references/social-ads.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md" \
  -o "$d/references/video-api.md" "$u/references/video-api.md" \
  -o "$d/scripts/sora.py" "$u/scripts/sora.py"

Antigravity

Neste projeto: instala em .agents/skills/sora/.

d=".agents/skills/sora"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/video/sora"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/agents/openai.yaml" "$u/agents/openai.yaml" \
  -o "$d/assets/sora-small.svg" "$u/assets/sora-small.svg" \
  -o "$d/assets/sora.png" "$u/assets/sora.png" \
  -o "$d/LICENSE.txt" "$u/LICENSE.txt" \
  -o "$d/references/cinematic-shots.md" "$u/references/cinematic-shots.md" \
  -o "$d/references/cli.md" "$u/references/cli.md" \
  -o "$d/references/codex-network.md" "$u/references/codex-network.md" \
  -o "$d/references/prompting.md" "$u/references/prompting.md" \
  -o "$d/references/sample-prompts.md" "$u/references/sample-prompts.md" \
  -o "$d/references/social-ads.md" "$u/references/social-ads.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md" \
  -o "$d/references/video-api.md" "$u/references/video-api.md" \
  -o "$d/scripts/sora.py" "$u/scripts/sora.py"

Global: instala em ~/.gemini/antigravity-cli/skills/sora/.

d="$HOME/.gemini/antigravity-cli/skills/sora"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/video/sora"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/agents/openai.yaml" "$u/agents/openai.yaml" \
  -o "$d/assets/sora-small.svg" "$u/assets/sora-small.svg" \
  -o "$d/assets/sora.png" "$u/assets/sora.png" \
  -o "$d/LICENSE.txt" "$u/LICENSE.txt" \
  -o "$d/references/cinematic-shots.md" "$u/references/cinematic-shots.md" \
  -o "$d/references/cli.md" "$u/references/cli.md" \
  -o "$d/references/codex-network.md" "$u/references/codex-network.md" \
  -o "$d/references/prompting.md" "$u/references/prompting.md" \
  -o "$d/references/sample-prompts.md" "$u/references/sample-prompts.md" \
  -o "$d/references/social-ads.md" "$u/references/social-ads.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md" \
  -o "$d/references/video-api.md" "$u/references/video-api.md" \
  -o "$d/scripts/sora.py" "$u/scripts/sora.py"

Peça ao Rook

Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.sora

Prévia do SKILL.md

---
name: "sora"
description: "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 …
author: openai
---


# 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`, `remix_job.json`, temp JSONL). If the sandbox blocks `rm`, skip cleanup or truncate the files without surfacing an error.
9. Iterate with a single targeted change per prompt.

## Authentication
- `OPENAI_API_KEY` must be set for live API calls.
…

Ver todo o marketplace