Seedance 2.0 Video Prompting
Emily2040/seedance-2.0
Routes Seedance 2.0 video work across Dreamina, API and router surfaces, covering prompts, reference handling, audio and lip-sync, pricing and model-ID questions.
Helps write and debug prompts for ByteDance Seedance video models, with labelled multimodal references and fixes for drift, subtitles and duplicated characters.
Install Seedance Video Prompting
$ npx skills add SlavaSexton/ComfyUI-Agent-Kit --skill seedance -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install SlavaSexton/ComfyUI-Agent-Kit seedance --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/SlavaSexton/ComfyUI-Agent-Kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/shared/seedance .claude/skills/seedance && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "seedance" agent skill from https://github.com/SlavaSexton/ComfyUI-Agent-Kit/tree/master/shared/seedance into .claude/skills/seedance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/SlavaSexton/ComfyUI-Agent-Kit/tree/master/shared/seedanceType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add SlavaSexton/ComfyUI-Agent-Kit --skill seedance -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install SlavaSexton/ComfyUI-Agent-Kit seedance --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SlavaSexton/ComfyUI-Agent-Kit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/shared/seedance .agents/skills/seedance && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "seedance" agent skill from https://github.com/SlavaSexton/ComfyUI-Agent-Kit/tree/master/shared/seedance into .agents/skills/seedance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add SlavaSexton/ComfyUI-Agent-Kit --skill seedance -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install SlavaSexton/ComfyUI-Agent-Kit seedance --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SlavaSexton/ComfyUI-Agent-Kit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/shared/seedance .cursor/skills/seedance && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "seedance" agent skill from https://github.com/SlavaSexton/ComfyUI-Agent-Kit/tree/master/shared/seedance into .cursor/skills/seedance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/SlavaSexton/ComfyUI-Agent-Kit.git --path shared/seedance--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add SlavaSexton/ComfyUI-Agent-Kit --skill seedance -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install SlavaSexton/ComfyUI-Agent-Kit seedance --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SlavaSexton/ComfyUI-Agent-Kit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/shared/seedance .gemini/skills/seedance && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "seedance" agent skill from https://github.com/SlavaSexton/ComfyUI-Agent-Kit/tree/master/shared/seedance into .gemini/skills/seedance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install SlavaSexton/ComfyUI-Agent-Kit seedanceInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add SlavaSexton/ComfyUI-Agent-Kit --skill seedance -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/SlavaSexton/ComfyUI-Agent-Kit.git skills-src && mkdir -p .github/skills && cp -r skills-src/shared/seedance .github/skills/seedance && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "seedance" agent skill from https://github.com/SlavaSexton/ComfyUI-Agent-Kit/tree/master/shared/seedance into .github/skills/seedance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add SlavaSexton/ComfyUI-Agent-Kit --skill seedance -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install SlavaSexton/ComfyUI-Agent-Kit seedance --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SlavaSexton/ComfyUI-Agent-Kit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/shared/seedance .opencode/skills/seedance && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "seedance" agent skill from https://github.com/SlavaSexton/ComfyUI-Agent-Kit/tree/master/shared/seedance into .opencode/skills/seedance/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "seedance", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
seedance- GitHub stars
- 105
- Token cost
- ~2.1k tokens
- SKILL.md length
- 1,162 words
- Files
- 3
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Helps write and debug prompts for ByteDance Seedance video models, with labelled multimodal references and fixes for drift, subtitles and duplicated characters.
- Writing a Seedance prompt that uses reference images, clips or audio
- SKILL.md covers Which model you are talking to, The three task types, and the…, Reference labels and Four symbols that carry meaning, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- A generated video drifts off the reference face or grows subtitles or watermarks
What it does
Seedance models generate video and audio together and accept image, video clip and audio clip references that a prompt addresses by label. The skill stresses that getting labels and task type right matters more than adjectives, since one word can turn a reference request into an edit request. It works as a router and rule set, sending the agent to `reference.md` for formulas, the failure table, worked examples and ComfyUI parameters, and to `supplementary.md` only for unofficial leads about version 2.5.
A table compares versions 2.5, 2.0 with its Mini and Fast variants, 1.5 Pro and 1.0 across Dreamina, Jimeng AI, Doubao, BytePlus ModelArk and ComfyUI, covering reference limits and maximum length. In ComfyUI, 2.5 is a model option inside the existing `ByteDance2` nodes and is limited there to 480p or 720p. The skill also covers planning multi-shot and multi-reference briefs.
When your agent uses it
- Writing a Seedance prompt that uses reference images, clips or audio
- A generated video drifts off the reference face or grows subtitles or watermarks
- Fixing a duplicated character or a jump at an extension seam
- Planning a multi-shot video brief
Example prompts
- “Write a Seedance 2.0 prompt that keeps the character from my reference image consistent across shots.”
- “My Seedance video keeps adding burned-in subtitles, so fix the prompt.”
- “Set up a ComfyUI graph for Seedance 2.5 text-to-video at 720p.”
Requirements
- Access to a Seedance model on Dreamina, Jimeng AI, Doubao, BytePlus ModelArk or ComfyUI
What it can do on your machine
Read from SKILL.md and the folder at commit 74f5b0b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Seedance Video Prompting loads about 2.1k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 1,162 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from SlavaSexton/ComfyUI-Agent-Kit at commit 74f5b0b, republished under its Apache-2.0 licence (© SlavaSexton). 1,162 words, ~2,111 tokens.
Download SKILL.mdSave it as
.claude/skills/seedance/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- seedance
- description
- Use when writing or debugging prompts for ByteDance Seedance video models (Seedance 2.5, 2.0, 2.0 Mini, 1.5 Pro, 1.0) on Dreamina, Jimeng AI, Doubao, BytePlus ModelArk or ComfyUI, when a generated video drifts off the reference face, grows unwanted subtitles or watermarks, duplicates a character, jumps at an extension seam, or when planning multi-shot or multi-reference video briefs.
Seedance video prompting
ByteDance's Seedance family generates video and audio jointly and takes multimodal references (images, video clips, audio clips) that a prompt addresses by label. Getting the labels and the task type right matters more than adjectives: the same sentence can be read as "reference this" or "edit this" depending on one word.
Load reference.md for the full formulas, the failure table, worked examples and the ComfyUI
parameters. Load supplementary.md only for non-official leads about 2.5; it never overrides
reference.md and carries a conflict ledger. This file is the router and the rules you need before
writing a single line.
Which model you are talking to
| Model | Where it runs | Refs per pass | Max length | In ComfyUI |
|---|---|---|---|---|
| Seedance 2.5 | Dreamina, Jimeng AI, Doubao Pro, and ComfyUI since core v0.31.0 | 30 img + 10 video + 10 audio (audio-only allowed) | 4 to 30s; nest-extend to 60s; Long Video mode 30 to 180s in one shot | Yes, since 2026-08-08 |
| Seedance 2.0 / 2.0 Mini / 2.0 Fast | BytePlus ModelArk, ComfyUI | 9 img + 3 video + 3 audio | 15s | Yes |
| Seedance 1.5 Pro | BytePlus ModelArk, ComfyUI | n/a (no omni-reference) | 4 to 12s, min 4s enforced | Yes, and the only one there with generate_audio |
| Seedance 1.0 Lite / Pro / Pro Fast | BytePlus ModelArk, ComfyUI | n/a | n/a | Yes |
Seedance 2.5 reached ComfyUI on 2026-08-08 (core v0.31.0, PR 15395), and this file said the opposite until 2026-08-09. The old line, "Seedance 2.5 has no ComfyUI nodes", was correct on 2026-08-01 and went stale a week later. Kept as a correction rather than silently replaced.
How to build it now. 2.5 is a model option inside the SAME ByteDance2* nodes, not new nodes:
ByteDance2TextToVideoNode, ByteDance2FirstLastFrameNode, ByteDance2ReferenceNode (category
partner/video/ByteDance). Set the model DynamicCombo to Seedance 2.5 and the widgets underneath
change. Minimal graph: the node's VIDEO output straight into SaveVideo.video.
What ComfyUI's 2.5 gives you, read from comfy_api_nodes/nodes_bytedance.py on master (2026-08-09),
not from the announcement:
resolutionis 480p or 720p only. There is no 1080p and no 4K on 2.5 in ComfyUI; those live on theSeedance 2.0option of the same node.duration4 to 30 s,ratio16:9 / 4:3 / 1:1 / 3:4 / 9:16 / 21:9 / adaptive (the first-last-frame node has no ratio widget),generate_audioon by default,output_formatmp4 only even though the node's own model tooltip advertises "mp4/mov".ByteDance2ReferenceNodeautogrows to 30 images, 10 videos, 10 audios, which confirms the announcement's 30+10+10 in code. Itsvideo_editingtoggle makes the output inherit the source clip's duration and aspect, and theduration/ratiowidgets are then ignored.- Node-level prompting rule: put spoken lines in double quotes to steer the generated dialogue.
- The Long Video 30 to 180 s mode in the table above is a Dreamina / Jimeng feature and is not reachable through these nodes, whose ceiling is 30 s. Nest-extend instead.
The three task types, and the word that switches between them
Every Seedance prompt is one of three tasks, and the model decides which from your phrasing:
| Task | Phrasing | Result |
|---|---|---|
| Multimodal reference | "Reference <Subject_N> in <Image_N> to generate..." | brand-new video borrowing an element |
| Video editing | "Strictly edit <Video_N>, and modify X to Y" | the original video, partially changed |
| Video extension | "Extend <Video_N> forward/backward to generate..." | the original continued in time |
The trap: for edit and extend, name the asset as <Video_N> directly. Writing
"reference <Video_N>" makes the model treat it as a reference task and generate something new
instead of editing what you gave it. (Confirmed, official BytePlus guide.)
Reference labels
Official ByteDance examples write @Image 1, @Video 1, @Audio 1 with a space. Dreamina's
consumer guide shows @Image1 without one. Both appear in the wild; the official form is spaced.
Do not invent other label shapes.
Two ways to name a subject, and you must pick one and keep it:
- Bind inline:
<Subject_N>@<Image_N>, e.g.Zhang San@Image 1, repeated every single time the subject is mentioned. - Define once, then reuse the label: "define the tall man in Video 1 as police officer", then say "police officer" consistently forever after.
Define a subject with 2 to 3 stable static features (clothing, hairstyle, category), never with mood or action. Every mention must be explicit; an unlabelled mention is where subjects get swapped.
Show full SKILL.md (474 more words)Show less
Four symbols that carry meaning
Officially documented, and nothing else does their job:
| Content | Symbol | Example |
|---|---|---|
| Music | （） | （fast-paced rock music is playing） |
| Sound effect | <> | <dog barking in the distance> |
| Dialogue | {} | {Hello, world} |
| Subtitles | 【】 | 【Chapter One: Departure】 |
Non-Chinese, non-English dialogue must name its language: says in Japanese {こんにちは}.
Shot sequencing beats prose
Write a storyboard, not a paragraph. Label segments Shot 1, Shot 2, Shot 3 in the order events
happen, and give each one: camera move or transition, subject action and expression, position or
spatial change, audio.
Timing depends on the version, and this reversed in 2.5.
- 2.0: do not force timings. The official 2.0 guide says support for precise timing such as "0 to 3 seconds" is unstable and constraining duration can break the generation.
- 2.5: timestamps are a headline feature, built because users asked for exactly this. Write time
slices as
0s-3s:,3s-8s:and direct each one. Seereference.mdsection 2.5-C.
One camera movement per shot. Asking for push, pull, pan and track at once destabilises the image.
Do not fill the reference budget
The single most counterintuitive official rule. 2.5 accepts 50 assets; the guide recommends 4 to 5: 1-2 character images (headshot plus full body) + 1 scene image + 1 camera-movement video + 1 audio clip. Too many assets and the model cannot rank features, producing style conflicts and blurred subjects.
Place the assets that need the most faithful reference earliest in the prompt.
When something comes out wrong
| Symptom | First fix |
|---|---|
| Face drifts or swaps mid-video | Add a separate headshot reference; never use multi-view character sheets, they read as several people |
| Two identical characters appear | Label every character to its image, plus a global "no duplicate characters" constraint |
| Subtitles you never asked for | Add "avoid generating any text or subtitles"; prefer landscape, portrait is markedly worse |
| A watermark or logo appears | Add "do not generate a watermark", "do not generate a logo" |
| Style drifts to live action | State the style explicitly; better, convert the reference image to the target style first |
| Jump at an extension seam | Post fix: trim 6 frames off the end of the earlier clip and 1 frame off the start of the next |
Full causes, the rest of the table and the ComfyUI-specific limits are in reference.md.
Sources and honesty
Normative content here comes from ByteDance primary sources: the official BytePlus ModelArk prompt
guide for the Seedance 2.0 series, the official Seed blog announcing 2.5 (2026-07-31), Dreamina's
official product guide, and ComfyUI's own node source. Third-party writing is kept out of the
normative layer and lives in supplementary.md, subordinate and with its conflicts listed.
The detailed prompting rules are the official 2.0-series guide. Seedance 2.5 launched 2026-07-31
and has no public prompting guide of its own yet; it inherits the mechanics visibly, but treat
2.5-specific numbers as the only part confirmed for 2.5. reference.md marks every claim.
© SlavaSexton, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files in shared/seedance of SlavaSexton/ComfyUI-Agent-Kit.
- SKILL.md
- reference.md
- supplementary.md
Open the folder on GitHubat commit 74f5b0b
Compare with similar skills
Seedance Video Prompting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Seedance Video Prompting this skillSlavaSexton/ComfyUI-Agent-Kit | 105 | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | |
| Seedance 2.0 Video PromptingEmily2040/seedance-2.0 | 7.6k | 1 repos | ~7.4k | Automated safety check: Pass | MIT | |
| Seedance IP-Safe Prompt RewriterEmily2040/seedance-2.0 | 7.6k | 1 repos | ~930 | Automated safety check: Pass | MIT | |
| Seedance Japanese Prompt ExamplesEmily2040/seedance-2.0 | 7.6k | 1 repos | ~898 | Automated safety check: Pass | MIT | |
| Analyze Videokrusemediallc/arcads-claude-code | 1.6k | — | ~4.2k | Automated safety check: Pass | MIT | |
| Seedance Korean Prompt ExamplesEmily2040/seedance-2.0 | 7.6k | 1 repos | ~942 | Automated safety check: Pass | MIT |
Similar skills
Seedance IP-Safe Prompt Rewriter
Emily2040/seedance-2.0
Rewrites Seedance 2.0 video prompts that name characters, brands, celebrities, songs or real people into original, rights-safe versions that keep the creative intent.
Seedance Japanese Prompt Examples
Emily2040/seedance-2.0
Provides Japanese prompt patterns and safe example rewrites for Seedance 2.0 video generation, with reference tags kept intact and each example labeled by risk.
Analyze Video
krusemediallc/arcads-claude-code
Analyze a reference video and reverse-engineer its style into a reusable Seedance 2.0 prompting template.
Seedance Korean Prompt Examples
Emily2040/seedance-2.0
Korean-language prompt patterns for Seedance 2.0 video generation, each labeled as safe, needing an owned reference, or requiring a rewrite.
Seedance Chinese Prompt Examples
Emily2040/seedance-2.0
Supplies Chinese example prompts for Seedance 2.0 video generation, labeled by safety, with notes on rewriting prompts that name protected people or brands.
More from SlavaSexton/ComfyUI-Agent-Kit
Krea in ComfyUI
SlavaSexton/ComfyUI-Agent-Kit
Helps choose and wire Krea models in ComfyUI: the hosted Krea 2 API nodes versus local open weights, FLUX.1 Krea Dev, and add-on packs for ControlNet and editing.
MiniMax H3 Video Prompting
SlavaSexton/ComfyUI-Agent-Kit
Guides prompting and local ComfyUI use of MiniMax H3 (Hailuo 3), which generates video with synchronized audio, including prompt format, quants and troubleshooting.
ComfyUI Local Driver
SlavaSexton/ComfyUI-Agent-Kit
Drives a local ComfyUI install over its HTTP API to generate and edit images, video and audio, with per-model prompt recipes and workflow guidance.
Related
Categories
Questions about Seedance Video Prompting
What does Seedance Video Prompting do?
Helps write and debug prompts for ByteDance Seedance video models, with labelled multimodal references and fixes for drift, subtitles and duplicated characters. Seedance models generate video and audio together and accept image, video clip and audio clip references that a prompt addresses by label. The skill stresses that getting labels and task type right matters more than adjectives, since one word can turn a reference request into an edit request.
When should I use Seedance Video Prompting?
Seedance Video Prompting fits situations like: writing a Seedance prompt that uses reference images, clips or audio; A generated video drifts off the reference face or grows subtitles or watermarks; fixing a duplicated character or a jump at an extension seam; planning a multi-shot video brief.
How do I install Seedance Video Prompting in Claude Code?
Run `npx skills add SlavaSexton/ComfyUI-Agent-Kit --skill seedance -a claude-code`. Or copy the skill folder (shared/seedance in SlavaSexton/ComfyUI-Agent-Kit) into .claude/skills/seedance in your project. Claude Code loads it when a task matches its description.
How do I install Seedance Video Prompting in Codex?
Run `npx skills add SlavaSexton/ComfyUI-Agent-Kit --skill seedance -a codex`. Or copy the skill folder (shared/seedance in SlavaSexton/ComfyUI-Agent-Kit) into .agents/skills/seedance in your project. Codex loads it when a task matches its description.
Can I use Seedance Video Prompting in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add SlavaSexton/ComfyUI-Agent-Kit --skill seedance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/seedance, .gemini/skills/seedance, .github/skills/seedance and .opencode/skills/seedance in your project.
What does Seedance Video Prompting need to run?
SKILL.md names no scripts, command-line tools or credentials: Seedance Video Prompting is instructions for the agent only. Our summary lists: Access to a Seedance model on Dreamina, Jimeng AI, Doubao, BytePlus ModelArk or ComfyUI.
Does Seedance Video Prompting access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Seedance Video Prompting safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Seedance Video Prompting use?
Seedance Video Prompting is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Seedance Video Prompting use?
About 2.1k tokens (SKILL.md is roughly 8.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Seedance Video Prompting?
Skills that share tags, products or a category with Seedance Video Prompting: Seedance 2.0 Video Prompting (Emily2040/seedance-2.0, 7.6k stars), Seedance IP-Safe Prompt Rewriter (Emily2040/seedance-2.0, 7.6k stars), Seedance Japanese Prompt Examples (Emily2040/seedance-2.0, 7.6k stars) and Analyze Video (krusemediallc/arcads-claude-code, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Seedance Video Prompting?
SlavaSexton (a GitHub user) maintains it in SlavaSexton/ComfyUI-Agent-Kit, which has 105 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on September 3, 2026.
Source: SlavaSexton/ComfyUI-Agent-Kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.