npx skills add https://github.com/openai/skills --skill sora为当前项目创建或管理 Sora 视频任务(产品演示、营销短片、电影镜头、社交媒体剪辑、UI 模拟)。默认使用 sora-2 模型,并进行结构化提示增强,推荐使用捆绑的 CLI 以实现确定性运行。注意:$sora 是提示中的技能标签,而非 shell 命令。
create-characterextendeditstatus、poll 或 广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
downloadcreate-batch(本地扇出,非 Batch API)references/video-api.md 中描述的官方 Batch API 流程create(或者如果他们需要一步获取就绪的资源,则使用 create-and-poll)--use-case、--scene、--camera 等),而不是手动编写冗长的结构化提示。如果已有结构化提示文件,请传递 --no-augment。scripts/sora.py)。对于长提示,优先使用 --prompt-file 以避免 shell 转义问题。create-and-poll)。create 调用中引用它们。edit;如果他们希望镜头在时间上延续,优先使用 extend。OPENAI_API_KEY。如果缺少密钥,请向用户提供以下步骤:
OPENAI_API_KEY 设置为环境变量。sora-2(更高保真度请使用 sora-2-pro)。1280x720。4 秒(允许值:"4"、"8"、"12"、"16"、"20")。1920x1080 和 1080x1920 需要 sora-2-pro 模型。openai 包)。如果高级 SDK 助手滞后于最新的 Sora 指南,请在官方 SDK 内部使用低级别的 client.post/get/delete,而不是独立的 HTTP 代码。OPENAI_API_KEY。UV_CACHE_DIR=/tmp/uv-cache。input_reference 对象使用 file_id 或 image_url;上传的文件路径使用 multipart 格式。scripts/sora.py 中的 create-batch 是本地并发队列,而非官方 Batch API。scripts/sora.py,除非用户要求。Audio: 和 Dialogue: 行中明确指定,并保持简短。sora-2 和 sora-2-pro。seconds 参数设置,目前支持 4、8、12、16 和 20。2-4 秒、16:9 或 9:16 比例、720p-1080p 分辨率的非人类 MP4 短视频。20 秒,每个源视频最多可扩展六次,总长度最长可达 120 秒。POST /v1/videos,使用 JSON 请求体而非 multipart 上传。references/video-api.md)。将提示重新格式化为结构化的、面向生产的规范。仅将隐含的细节显式化;不要发明新的创意要求。
模板(仅包含相关行):
Use case: <片段将用于何处>
Primary request: <用户的主要提示>
Scene/background: <地点、时间、氛围>
Subject: <主要主体>
Action: <单一清晰的动作>
Camera: <镜头类型、角度、运动>
Lighting/mood: <灯光 + 氛围>
Color palette: <3-5 个色彩锚点>
Style/format: <电影/动画/格式提示>
Timing/beats: <计数或节拍>
Audio: <环境音/音乐/画外音(如请求)>
Text (verbatim): "<确切文本>"
Dialogue:
<对话>
- Speaker: "简短台词。"
</对话>
Constraints: <必须保持/必须避免>
Avoid: <负面约束>
增强规则:
--no-augment 以避免工具重新包装它。Use case: product teaser
Primary request: a close-up of a matte black camera on a pedestal
Action: slow 30-degree orbit over 4 seconds
Camera: 85mm, shallow depth of field, gentle handheld drift
Lighting/mood: soft key light, subtle rim, premium studio feel
Constraints: no logos, no text
Primary request: same shot and framing, switch palette to teal/sand/rust with warmer backlight
Constraints: keep the subject and camera move unchanged
Primary request: Mossy, a moss-covered teapot mascot, hurries through a lantern-lit market at dusk
Camera: cinematic tracking shot, 35mm, shoulder height
Lighting/mood: warm dusk practicals, soft haze
Constraints: keep Mossy’s silhouette and moss texture consistent across the shot
edit;对于时间线延续,优先使用 extend。当请求针对特定工件时,请使用这些模块。它们提供针对性的模板和默认值。
references/cinematic-shots.mdreferences/social-ads.mdreferences/cli.mdreferences/video-api.mdreferences/prompting.mdreferences/sample-prompts.mdreferences/troubleshooting.mdreferences/codex-network.mdreferences/cli.md :如何通过 scripts/sora.py 运行 create/edit/extend/create-character/poll/download/local-queue 流程。references/video-api.md :API 级别的旋钮(模型、尺寸、时长、角色、编辑、扩展、官方 Batch API)。references/prompting.md :提示结构、角色连续性、编辑和扩展指导。references/sample-prompts.md :复制/粘贴的提示配方(仅示例;无额外理论)。references/cinematic-shots.md :电影镜头的模板。references/social-ads.md :简短社交媒体广告节拍的模板。references/troubleshooting.md :常见错误及修复方法。references/codex-network.md :网络/审批故障排除。每周安装量
470
仓库
GitHub 星标数
15.3K
首次出现
Jan 28, 2026
安全审计
安装于
codex422
opencode409
gemini-cli396
github-copilot389
cursor381
kimi-cli372
Creates or manages Sora video jobs for the current project (product demos, marketing spots, cinematic shots, social clips, UI mocks). Defaults to sora-2 with structured prompt augmentation and prefers the bundled CLI for deterministic runs. Note: $sora is a skill tag in prompts, not a shell command.
create-characterextendeditstatus, poll, or downloadcreate-batch (local fan-out, not the Batch API)references/video-api.mdcreate (or create-and-poll if they need a ready asset in one step)--use-case, --scene, --camera, etc.) instead of hand-writing a long structured prompt. If you already have a structured prompt file, pass --no-augment.scripts/sora.py) with sensible defaults. For long prompts, prefer --prompt-file to avoid shell-escaping issues.create-and-poll).create calls.OPENAI_API_KEY must be set for live API calls.If the key is missing, give the user these steps:
OPENAI_API_KEY as an environment variable in their system.sora-2 (use sora-2-pro for higher fidelity).1280x720.4 (allowed: "4", "8", "12", "16", "20").sora-2-pro is required for 1920x1080 and .sora-2 and sora-2-pro.seconds parameter and currently supports 4, 8, 12, 16, and 20.2-4 second non-human MP4s in 16:9 or , at -.Reformat prompts into a structured, production-oriented spec. Only make implicit details explicit; do not invent new creative requirements.
Template (include only relevant lines):
Use case: <where the clip will be used>
Primary request: <user's main prompt>
Scene/background: <location, time of day, atmosphere>
Subject: <main subject>
Action: <single clear action>
Camera: <shot type, angle, motion>
Lighting/mood: <lighting + mood>
Color palette: <3-5 color anchors>
Style/format: <film/animation/format cues>
Timing/beats: <counts or beats>
Audio: <ambient cue / music / voiceover if requested>
Text (verbatim): "<exact text>"
Dialogue:
<dialogue>
- Speaker: "Short line."
</dialogue>
Constraints: <must keep/must avoid>
Avoid: <negative constraints>
Augmentation rules:
--no-augment to avoid the tool re-wrapping it.Use case: product teaser
Primary request: a close-up of a matte black camera on a pedestal
Action: slow 30-degree orbit over 4 seconds
Camera: 85mm, shallow depth of field, gentle handheld drift
Lighting/mood: soft key light, subtle rim, premium studio feel
Constraints: no logos, no text
Primary request: same shot and framing, switch palette to teal/sand/rust with warmer backlight
Constraints: keep the subject and camera move unchanged
Primary request: Mossy, a moss-covered teapot mascot, hurries through a lantern-lit market at dusk
Camera: cinematic tracking shot, 35mm, shoulder height
Lighting/mood: warm dusk practicals, soft haze
Constraints: keep Mossy’s silhouette and moss texture consistent across the shot
edit for targeted changes and extend for timeline continuation.Use these modules when the request is for a specific artifact. They provide targeted templates and defaults.
references/cinematic-shots.mdreferences/social-ads.mdreferences/cli.mdreferences/video-api.mdreferences/prompting.mdreferences/sample-prompts.mdreferences/troubleshooting.mdreferences/codex-network.mdreferences/cli.md : how to run create/edit/extend/create-character/poll/download/local-queue flows via scripts/sora.py.references/video-api.md : API-level knobs (models, sizes, duration, characters, edits, extensions, official Batch API).references/prompting.md : prompt structure, character continuity, editing, and extension guidance.references/sample-prompts.md : copy/paste prompt recipes (examples only; no extra theory).references/cinematic-shots.md : templates for filmic shots.references/social-ads.md : templates for short social ad beats.Weekly Installs
470
Repository
GitHub Stars
15.3K
First Seen
Jan 28, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
codex422
opencode409
gemini-cli396
github-copilot389
cursor381
kimi-cli372
AI Elements:基于shadcn/ui的AI原生应用组件库,快速构建对话界面
54,900 周安装
edit; if they want the shot to continue in time, prefer extend.1080x1920openai package). If high-level SDK helpers lag the latest Sora guide, use low-level client.post/get/delete inside the official SDK rather than standalone HTTP code.OPENAI_API_KEY before any live API call.UV_CACHE_DIR=/tmp/uv-cache.input_reference objects use either file_id or image_url; uploaded file paths use multipart.create-batch in scripts/sora.py is a local concurrent queue, not the official Batch API.scripts/sora.py unless the user asks.Audio: and Dialogue: lines and keep it short.9:16720p1080p20 seconds each, up to six times per source video, for a maximum total length of 120 seconds.POST /v1/videos only, with JSON bodies rather than multipart uploads.references/video-api.md for the supported sizes).references/troubleshooting.mdreferences/codex-network.md : network/approval troubleshooting.