seedance-2.0 is an agent-driven production pipeline for creating AI films from text, images, videos, and references, including audio and platform-specific workflows. Filmmakers and creators use it to plan scenes and generate coherent prompts for Seedance-related tools, while the catalogue contains skills from that workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Emily2040/seedance-2.0 --skill seedance-prompt-shortgit clone --depth 1 https://github.com/Emily2040/seedance-2.0Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/emily2040/seedance-2.0/seedance-prompt-short)<a href="https://agentmods.dev/skills/emily2040/seedance-2.0/seedance-prompt-short"><img src="https://agentmods.dev/badge/skills/emily2040/seedance-2.0/seedance-prompt-short/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/emily2040/seedance-2.0/seedance-prompt-short"><img src="https://agentmods.dev/badge/skills/emily2040/seedance-2.0/seedance-prompt-short.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.01261 |
| Opus 5.5 | $0.00019 | $0.00504 |
| Sonnet 5.5 | $0.00009 | $0.00252 |
| Haiku 4.5 | $0.00005 | $0.00126 |
Grade A, and why
seedance-prompt-short scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seedance-prompt-short
Before producing prompt text, a prompt-ready block, a rewrite, an example, or a compiled clip, load the Director's Read, classify the brief, and complete its canonical narrative or non-narrative record. Translate that record into visible or audible carriers and keep its internal labels out of final generation prose.
Compress Seedance prompts without losing the production signal. A short prompt still needs mode, subject, action, camera, light, sound when useful, and constraints. Remove filler before removing physical details.
Load the Director's Read before compression, even when the requested output is only one line. Briefs with a dramatic story turn complete its ten-field narrative record first. Observation/performance without that turn and utility briefs use its two-line non-narrative intent and refusal without fabricated drama; short output must still preserve the requested expression or rhythm. Short means compressed output, not skipped judgment.
When sequence state is present, compression must preserve continuity locks, exact reference tags, actual opening state, current clip action, endpoint, completed beat exclusions, and reserved future beats. Do not compress away the words that keep a continuation from replaying completed action or leaking future action.
The moderation pre-screen runs on the compressed prompt too: compression that drops a clarifying word can expose a cue, and a short prompt is refused as readily as a long one. Never write an involuntary outcome as the endpoint; the model stages accidents as intentions. The short route still builds the shot table for any storyboard or multi-person clip and may deliver the prompt alone, but a cell it cannot fill is a question it must ask before delivering. Compression never removes a lock line, a stated position or a feeling word, never turns a literal action back into an idiom, and never replaces idle business with a freeze; see direct-for-the-model.
Storyboard clips keep their structure when compressed: numbered shots in event order, the cut written in words, no absolute seconds inside a block on Seedance 2.0. The shot-count ladder from multishot-grammar shrinks to one line per rung and one finished prompt at the chosen rung; when the user has fixed the count, state its rung in one line and write it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +6 lines b343aba1f8e8
- 1mo ago Changed 645e1a50cb4b
- 1mo ago First seen · 65 lines · 47 tokens per session scan A 3225ea5b3dd3
seedance-prompt-short is a skill published in the GitHub repository Emily2040/seedance-2.0 (7,955 stars, last pushed 25d ago), licensed MIT. It adds 47 tokens to every session and 1,261 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
seedance-prompt-short
This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.
seedance-prompt-short
This skill should be used when the user asks for a compact Seedance 2.0 prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language.
seedance-prompt-short
This skill should be used when the user asks for a compact Seedance 2.x prompt, short Chinese prompt, prompt compression, 30-100 word output, or removal of unnecessary prompt language. Reference tokens must come from the active structured surface contract or the user's exact supplied tags.
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
seedance-examples-zh
This skill should be used when the user asks for Chinese Seedance 2.0 examples, Chinese prompt patterns, example rewrites, or safe versions of working Chinese video-generation prompts.
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.