Analyze Video
krusemediallc/arcads-claude-code
Analyze a reference video and reverse-engineer its style into a reusable Seedance 2.0 prompting template.
Agent skill
Universal Video Prompt Spec
by AtlasCloudAI in AtlasCloudAI/awesome-seedance-2.5-prompts-skills
Writes one model-agnostic video prompt spec, then compiles it for whichever video model you can call, rewriting vague intent into results you can check in the output.
Install Universal Video Prompt Spec
$ npx skills add AtlasCloudAI/awesome-seedance-2.5-prompts-skills --skill universal-video-prompt-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install AtlasCloudAI/awesome-seedance-2.5-prompts-skills universal-video-prompt-skill --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/AtlasCloudAI/awesome-seedance-2.5-prompts-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/universal-video-prompt-skill .claude/skills/universal-video-prompt-skill && 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 "universal-video-prompt-skill" agent skill from https://github.com/AtlasCloudAI/awesome-seedance-2.5-prompts-skills/tree/main/skills/universal-video-prompt-skill into .claude/skills/universal-video-prompt-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "universal-video-prompt-skill", 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/AtlasCloudAI/awesome-seedance-2.5-prompts-skills/tree/main/skills/universal-video-prompt-skillType 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 AtlasCloudAI/awesome-seedance-2.5-prompts-skills --skill universal-video-prompt-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install AtlasCloudAI/awesome-seedance-2.5-prompts-skills universal-video-prompt-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AtlasCloudAI/awesome-seedance-2.5-prompts-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/universal-video-prompt-skill .agents/skills/universal-video-prompt-skill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "universal-video-prompt-skill" agent skill from https://github.com/AtlasCloudAI/awesome-seedance-2.5-prompts-skills/tree/main/skills/universal-video-prompt-skill into .agents/skills/universal-video-prompt-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "universal-video-prompt-skill", 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 AtlasCloudAI/awesome-seedance-2.5-prompts-skills --skill universal-video-prompt-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install AtlasCloudAI/awesome-seedance-2.5-prompts-skills universal-video-prompt-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AtlasCloudAI/awesome-seedance-2.5-prompts-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/universal-video-prompt-skill .cursor/skills/universal-video-prompt-skill && 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 "universal-video-prompt-skill" agent skill from https://github.com/AtlasCloudAI/awesome-seedance-2.5-prompts-skills/tree/main/skills/universal-video-prompt-skill into .cursor/skills/universal-video-prompt-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "universal-video-prompt-skill", 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/AtlasCloudAI/awesome-seedance-2.5-prompts-skills.git --path skills/universal-video-prompt-skill--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 AtlasCloudAI/awesome-seedance-2.5-prompts-skills --skill universal-video-prompt-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install AtlasCloudAI/awesome-seedance-2.5-prompts-skills universal-video-prompt-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AtlasCloudAI/awesome-seedance-2.5-prompts-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/universal-video-prompt-skill .gemini/skills/universal-video-prompt-skill && 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 "universal-video-prompt-skill" agent skill from https://github.com/AtlasCloudAI/awesome-seedance-2.5-prompts-skills/tree/main/skills/universal-video-prompt-skill into .gemini/skills/universal-video-prompt-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "universal-video-prompt-skill", 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 AtlasCloudAI/awesome-seedance-2.5-prompts-skills universal-video-prompt-skillInstalls 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 AtlasCloudAI/awesome-seedance-2.5-prompts-skills --skill universal-video-prompt-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/AtlasCloudAI/awesome-seedance-2.5-prompts-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/universal-video-prompt-skill .github/skills/universal-video-prompt-skill && 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 "universal-video-prompt-skill" agent skill from https://github.com/AtlasCloudAI/awesome-seedance-2.5-prompts-skills/tree/main/skills/universal-video-prompt-skill into .github/skills/universal-video-prompt-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "universal-video-prompt-skill", 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 AtlasCloudAI/awesome-seedance-2.5-prompts-skills --skill universal-video-prompt-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install AtlasCloudAI/awesome-seedance-2.5-prompts-skills universal-video-prompt-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/AtlasCloudAI/awesome-seedance-2.5-prompts-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/universal-video-prompt-skill .opencode/skills/universal-video-prompt-skill && 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 "universal-video-prompt-skill" agent skill from https://github.com/AtlasCloudAI/awesome-seedance-2.5-prompts-skills/tree/main/skills/universal-video-prompt-skill into .opencode/skills/universal-video-prompt-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "universal-video-prompt-skill", 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
universal-video-prompt-skill- GitHub stars
- 234
- Token cost
- ~2.6k tokens
- SKILL.md length
- 1,399 words
- Files
- 17 (incl. references)
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Writes one model-agnostic video prompt spec, then compiles it for whichever video model you can call, rewriting vague intent into results you can check in the output.
- Works in 6 steps: Two axes govern every line you write → Write the spec → Choose time granularity before writing… → …
- Reusing one video brief across several generation providers
- SKILL.md covers Language route, 1. Two axes govern every line…, 2. Write the spec and 3. Choose time granularity…, plus 5 more sections
- Calls make
What it does
The skill separates a spec, the decisions a prompt encodes, from the dialect each video model expects. Every line is judged on two axes. Scope puts it in a bucket: global (film type, scene, style, camera principle), locks (identity, reference roles, audio source, supporting cast, negatives) or time (stage events and end states). Verifiability means it must be checkable afterward, so words like tense or fast-paced become observable cues such as gaze, breathing and hands, or a time budget per stage.
Other conventions include saying what each reference image controls and what not to take from it, and repeating the few costliest locks at the end of the prompt. English requests follow the main file, while Chinese requests start from a Chinese workflow file and matching reference files. References cover checklists, execution, film-type DNA, model profiles, portability and spec format, with a cross-model example. The excerpt stops partway through writing the spec.
When your agent uses it
- Reusing one video brief across several generation providers
- Building a comparison matrix of how different video models handle the same spec
- Continuing prompt work when the target video model is not yet available
- Turning vague style words into observable details a model can follow
Example prompts
- “Write a model-agnostic spec for a thirty-second product teaser, then compile it for two video models.”
- “Rewrite 'make it tense and fast-paced' as observable cues with a time budget per stage.”
- “Take this storyboard brief and list which lines are global, locks and timed beats.”
- “Compare how my spec would change for model A and model B using the model profiles.”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
- Two axes govern every line you write
- Write the spec
- Choose time granularity before writing bucket 3
- Compile the spec to a target model
- Transitions
- Review
What it can do on your machine
Read from SKILL.md and the folder at commit 852d044. 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
Shell commands in SKILL.md call:
make
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
Universal Video Prompt Spec loads about 2.6k tokens when it runs, and up to ~30k if it reads all its reference files. Until then it costs about 80 tokens; SKILL.md has 1,399 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,399 words (~2,650 tokens).
“Write the spec once. Compile it per model. A spec is not a prompt: it is the decisions a prompt encodes, kept separate from the dialect that expresses them.”
- name
- universal-video-prompt-skill
Files
SKILL.md and 16 other files (references) in skills/universal-video-prompt-skill of AtlasCloudAI/awesome-seedance-2.5-prompts-skills.
- SKILL.md
- examples/cross-model/model-profiles.md
- references/checklist.md
- references/checklist.zh-CN.md
- references/execution.md
- references/execution.zh-CN.md
- references/film-type-dna.md
- references/film-type-dna.zh-CN.md
- references/model-profile-schema.md
- references/model-profile-schema.zh-CN.md
- references/portability.md
- references/portability.zh-CN.md
- references/spec-format.md
- references/spec-format.zh-CN.md
- references/verifiability.md
- references/verifiability.zh-CN.md
- references/workflow.zh-CN.md
Open the folder on GitHubat commit 852d044
Compare with similar skills
Universal Video Prompt Spec 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 |
|---|---|---|---|---|---|---|
| Universal Video Prompt Spec this skillAtlasCloudAI/awesome-seedance-2.5-prompts-skills | 234 | — | ~2.6k | Automated safety check: Pass | Custom licence | |
| Analyze Videokrusemediallc/arcads-claude-code | 1.6k | — | ~4.2k | Automated safety check: Pass | MIT | |
| 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 | |
| Seedance Korean Prompt ExamplesEmily2040/seedance-2.0 | 7.6k | 1 repos | ~942 | Automated safety check: Pass | MIT |
Similar skills
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.
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.
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.
AIGC Video Production Workflow
renmu2017/Hell-Grind-AIGC-Skill
Model-agnostic workflow for AI image and video projects: prompt writing, tracking of assets and shots, continuity checks and diagnosis of failed generations.
More from AtlasCloudAI/awesome-seedance-2.5-prompts-skills
Seedance 2.5 Video Planner
AtlasCloudAI/awesome-seedance-2.5-prompts-skills
Plans and generates controllable Seedance videos by choosing a creative route first, from text prompts and storyboards to keyframe pairs, extensions and edits.
Related
Categories
Questions about Universal Video Prompt Spec
What does Universal Video Prompt Spec do?
Writes one model-agnostic video prompt spec, then compiles it for whichever video model you can call, rewriting vague intent into results you can check in the output. The skill separates a spec, the decisions a prompt encodes, from the dialect each video model expects. Every line is judged on two axes.
When should I use Universal Video Prompt Spec?
Universal Video Prompt Spec fits situations like: reusing one video brief across several generation providers; building a comparison matrix of how different video models handle the same spec; continuing prompt work when the target video model is not yet available; turning vague style words into observable details a model can follow.
How do I install Universal Video Prompt Spec in Claude Code?
Run `npx skills add AtlasCloudAI/awesome-seedance-2.5-prompts-skills --skill universal-video-prompt-skill -a claude-code`. Or copy the skill folder (skills/universal-video-prompt-skill in AtlasCloudAI/awesome-seedance-2.5-prompts-skills) into .claude/skills/universal-video-prompt-skill in your project. Claude Code loads it when a task matches its description.
How do I install Universal Video Prompt Spec in Codex?
Run `npx skills add AtlasCloudAI/awesome-seedance-2.5-prompts-skills --skill universal-video-prompt-skill -a codex`. Or copy the skill folder (skills/universal-video-prompt-skill in AtlasCloudAI/awesome-seedance-2.5-prompts-skills) into .agents/skills/universal-video-prompt-skill in your project. Codex loads it when a task matches its description.
Can I use Universal Video Prompt Spec 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 AtlasCloudAI/awesome-seedance-2.5-prompts-skills --skill universal-video-prompt-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/universal-video-prompt-skill, .gemini/skills/universal-video-prompt-skill, .github/skills/universal-video-prompt-skill and .opencode/skills/universal-video-prompt-skill in your project.
What does Universal Video Prompt Spec need to run?
Going by SKILL.md and its folder, Universal Video Prompt Spec needs the command-line tools its instructions call (make).
Does Universal Video Prompt Spec 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 Universal Video Prompt Spec 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 Universal Video Prompt Spec use?
Universal Video Prompt Spec has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Universal Video Prompt Spec use?
About 2.6k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 27k tokens, read only when the agent opens those files.
What are the alternatives to Universal Video Prompt Spec?
Skills that share tags, products or a category with Universal Video Prompt Spec: Analyze Video (krusemediallc/arcads-claude-code, 1.6k stars), Seedance 2.0 Video Prompting (Emily2040/seedance-2.0, 7.6k stars), Seedance IP-Safe Prompt Rewriter (Emily2040/seedance-2.0, 7.6k stars) and Seedance Japanese Prompt Examples (Emily2040/seedance-2.0, 7.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Universal Video Prompt Spec?
AtlasCloudAI (a GitHub organization) maintains it in AtlasCloudAI/awesome-seedance-2.5-prompts-skills, which has 234 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 11, 2026.
Source: AtlasCloudAI/awesome-seedance-2.5-prompts-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.