
seedance-submitter
Use when preparing, submitting, polling, or debugging Seedance 2.0 or 2.5 video generation jobs from prompts, opening/ending frames, multimodal references, storyboard images, UGC scripts, or voiceover copy. Use for selecting an unambiguous scene endpoint, uploading references, composing submit flags, submitting through PostPlus Cloud, polling predictions, and handing off local render paths.
- Installs
- 806
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/postplusai/postplus-skills --skill seedance-submitter- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads seedance-submitter automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Seedance Submitter
Use When
- Preparing, validating, submitting, polling, or debugging Seedance 2.0/2.5 jobs through PostPlus Cloud.
Do Not Use When
- Required inputs are missing and guessing would change the result.
- Task class, hook logic, storyboard, or reference policy is still unresolved.
Use
video-generationandvideo-request-architectfirst.
Execution Boundary
- This runner validates, submits, and polls normalized Seedance requests. It must not make creative strategy, task-classification, or reference-policy decisions.
- Interpret
sd2as Seedance 2.0 Mini (video-seedance-2-mini-*), the current default tier, unless the user names another model. Standard/fast remain available explicitly; use them when reference video/audio is required. - Seedance 2.5 has four deliberately separate scene endpoints. Never convert one
scene into another merely because an image is present:
video-seedance-2-5-text: prompt only; no media inputs.video-seedance-2-5-first-frame: exactly one--first-frame; the output starts from that frame, so this is not a feature-only reference.video-seedance-2-5-first-last-frame: exactly one--first-frameand one--last-frame; the provider contract fixes ratio toadaptiveand duration to-1.video-seedance-2-5-reference: one or more repeatable--reference-image,--reference-video, or--reference-audio; these guide features/style/content and are not opening or ending frames.
- For 2.0, standard/fast
-textendpoints accept image/video/audio references; mini-textaccepts images only. Every-imageendpoint takes one--imagefirst frame and no reference slots. - Released endpoint keys and their option enums (resolution, aspect ratio,
duration bounds) are discovered from
postplus media schema --json; they are not hard-coded here. - Set
durationwithin the endpoint's published bounds (see schema). For edit targets that fall between viable values, pick the nearest validdurationand settargetEditDurationSeconds. - When
targetEditDurationSeconds < duration, includetimeline.activePerformanceEndSecondsandtimeline.tailStrategy. - If the target script or beat plan exceeds the endpoint's maximum duration, split into independent submit-ready segments. Do not submit one oversized request.
- For 2.5 reference
editorextend, supply a reference video and use the exact schema constraints (aspect_ratio=adaptive,duration=-1). The CLI and Web boundary reject unsupported combinations before provider submission and billing.
Source And Request
- Lock media, script, duration, output root, source basis, and whether the user wants submission or commands only.
promptPlan.*,timeline.*, andtargetEditDurationSecondsare authoring vocabulary, not Seedance request fields. Submit with the endpoint's CLI flags from the flat provider contract discovered frompostplus media schema --json(--prompt, legacy 2.0--image, 2.5--first-frame/--last-frame,--duration,--resolution,--aspect-ratio,--generate-audio,--output-format,--omni-reference-task-type, and the repeatable--reference-image/--reference-video/--reference-audio— reference flags only on the endpoints that publish those slots); the CLI rejects any flag outside the selected endpoint's contract. Compose the storyline/audio plan and anytimeline.activePerformanceEndSeconds/timeline.tailStrategyinstruction into the single--promptnarrative, then map the supported render bucket to--duration; timeline authoring fields have no separate flags or request fields, and there is no request-JSON envelope to author.- Bind references explicitly: say what
[image 1],[image 2],[audio 1], or[video 1]controls. Do not rely onsame as previous,content above, or unbound local handles in final requests. - Upload local reference media to hosted storage with
postplus media-file upload --skill seedance-submitter --input-file <file> --mime <mime> --output <upload.json>, then passoutput.mediaReference— a persistentpostplus-media://reference that never expires — into the Seedance media flags (for example--reference-image <output.mediaReference>). The hosted boundary exchanges it for a fresh signed URL at provider send time, so upload once and reuse the same reference across later submissions.output.data.download_urlis a signed URL that expires; preferoutput.mediaReference. - Do not claim that uploading through PostPlus hosted storage automatically
grants Moyu real-person exemption. Automatic Moyu asset-library escalation is
enabled only for the enterprise Seedance 2.0
first_framepath with real end-to-end evidence.reference_imageremained privacy-blocked in a recorded run afterasset://rewrite, and no paid Seedance 2.5 exemption smoke has been approved; both paths fail with the provider's typed policy boundary.
Review And Handoff
- Before submission, verify validation passed, every segment is self-contained, references are bound, required media exists, source basis is explicit, and the output path is durable.
- Seedance 2.5 support is contract-verified by official/live provider material and local submit/poll/result/billing mocks. Until an approved paid smoke checks the MP4, actual duration, resolution, audio track, and settlement, do not label those output properties artifact-proven.
- If a render is pending, return the segment id, manifest path, the
output.data.idgeneration handle, the poll commandpostplus media poll --handle <output.data.id>, and expected localrenders/output path. The poll command waits in-command (re-checks every 8s for up to 45s per invocation;--wait-seconds 0= single check): rerun the same command while the render stays pending instead of re-submitting or writing a tighter retry loop. - Save a finished render to disk with
postplus media-file download --url <fresh-output-url> --output-file <renders/...>(or--reference <postplus-media://...>for media that lives in hosted storage); provider output URLs are temporary, so download while fresh.
Stop Conditions
- Stop when required user intent, source evidence, or owned input artifacts are missing and guessing would change the result.
- If an owned CLI or script command fails, report the exact error and stop. Do not bypass the failure with metadata-only answers, readiness probing, local payload rewrites, fallback providers, or unpublished tools.
Public Command Boundary
- Choose the smallest matching command or workflow from the user input and run it directly.
- Readiness diagnostics:
postplus doctor --skill seedance-submitter. - Poll a pending render:
postplus media poll --handle <output.data.id>(waits in-command up to 45s per invocation; rerun while pending). - Use
postplus media schema --jsononly when constructing or repairing an unknown request shape. - Run the hosted submit with the generated command below; do not call provider APIs directly.
postplus media create video-seedance-2-fast-image \
--prompt <prompt> \
--image <image> \
--output <result.json>
- If the CLI returns a quote-confirmation challenge, run
postplus quote confirm --json --challenge-file <challenge.json>and retry with the returned token.
FAQ
What does the seedance-submitter skill do?
Use when preparing, submitting, polling, or debugging Seedance 2.0 or 2.5 video generation jobs from prompts, opening/ending frames, multimodal references, storyboard images, UGC scripts, or voiceover copy. Use for selecting an unambiguous scene endpoint, uploading references, composing submit flags, submitting through PostPlus Cloud, polling predictions, and handing off local render paths.
How do I install seedance-submitter?
Run npx skills add https://github.com/postplusai/postplus-skills --skill seedance-submitter in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/seedance-submitter/ (personal) or .claude/skills/seedance-submitter/ (project).
Which AI agents can use seedance-submitter?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is seedance-submitter safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains seedance-submitter?
It is published by postplusai in postplusai/postplus-skills. It has 806 recorded installs.
More from postplusai/postplus-skills
audio-transcription
postplusai/postplus-skills
Transcribe local or remote audio into text and timestamps. Convert an existing timed transcript locally into SRT or ASS without another transcription job.
video-transcription
postplusai/postplus-skills
Transcribe speech in local or remote videos with timestamps. Convert existing timed transcripts locally into SRT or ASS; use media-analysis for visual understanding.
google-trends-research
postplusai/postplus-skills
Research Google Trends keyword momentum, regional interest, and related queries. Use search-interest evidence without treating it as sales or total demand.
facebook-research
postplusai/postplus-skills
Research public Facebook pages, groups, posts, reels, comments, ads, events, marketplace listings, and profiles for audience or competitor evidence.
youtube-research
postplusai/postplus-skills
Research public YouTube channels, video metrics, and comment samples; obtain downloadable video records when requested. Use for content and audience evidence.
video-analysis
postplusai/postplus-skills
Analyze local or remote social videos through PostPlus, especially for TikTok/Reels shot beats, timelines, voiceover or on-screen text capture, creative strategy, and natural Markdown outputs. Use this when you need video-level analysis beyond metadata and want results linked back to source metadata.
Popular media & creative skills
hyperframes
heygen-com/hyperframes
Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.
media-use
heygen-com/hyperframes
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.
hyperframes-registry
heygen-com/hyperframes
About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.
hyperframes-creative
heygen-com/hyperframes
Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.
ai-video-generation
101-skills/superpowers
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse
ai-image-generation
101-skills/superpowers
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image