Vibe Creating Skill

An open-source AI video-prompt skill — for Seedance, Sora, Kling, Veo & more

Turn a rough idea into a model-ready text-to-video prompt. Let creation return to expression.

English · 中文

Vibe Creating is an open-source, bilingual prompt-engineering skill that rewrites a rough idea, story, feeling, or over-specified shot script into a clean, model-friendly text-to-video prompt — and first judges whether your input even suits this style. It follows the open Agent Skills standard (a single SKILL.md), so it runs in Claude Code, Codex, OpenClaw, Hermes, and any agent on the same standard — or as a rule (Cursor) or system prompt (GPT, Gemini, any LLM). It works with any text-to-video model, and you can run many of them through one API on Atlas Cloud — Seedance 2.0, Kling, Veo, Hailuo, Wan, Vidu, Gemini Omni, and Grok Imagine, among others.

✨ What is Vibe Creating?

As text-to-video models get smarter, prompting gets simpler. Instead of over-specifying focal lengths, shot numbers, and frame-by-frame scripts, you focus on telling the story and trust the model to find the right shots, light, and rhythm.

Vibe Creating is that paradigm — introduced by ByteDance / Volcengine alongside the Seedance 2.0 video-generation model. This repo turns its methodology into a reusable AI video prompt skill:

• 🎯 Focus on Story — describe the situation, the texture of the air, the flow of emotion; let the model interpret.
• 🤝 Trust the Model — drop low-value technical parameters; keep and translate the shot intent.
• 🧭 Judgment-first — it decides whether your input even suits this style before rewriting, so it never flattens a precise shot list you actually wanted.

It is not a "make everything shorter" tool. Read the full philosophy for the idea behind it.

🧠 How it works

The skill is judgment-first: it scores your input on three axes — Scenario × Expression × Information — picks the lightest action that fits, and always replies in the same four-part format.

Input  (idea · scene · script)
  │
  ├─ Suits Vibe Creating? ───── no ─────▶ keep as-is  (explain the mismatch)
  │     │ yes
  ├─ Enough info? (4 layers) ── no ─────▶ ask first   (1–3 short questions)
  │     │ yes
  └─ How polished already?
        ├─ strong      ─▶ pass-through
        ├─ near / messy ─▶ light cleanup
        └─ execution    ─▶ direct rewrite  (strip params, translate intent)
                                │
                                ▼
        Four-part output:  Judgment · Action · Result · Notes

The four layers it checks for: visual anchor (the main subject), action / state (what's happening), local tonality (one mood word), and video theme (use case + visual style).

And every response comes back in that same fixed four-part format:

Judgment — does it suit Vibe Creating, is it already usable, is the info enough Action — one of pass-through / light cleanup / direct rewrite / ask first / keep as-is / optional VC version Result — the rewritten prompt, the kept text, or a clarifying question Notes (if any) — what technical control was stripped, what constraints were kept

For example — You: Express the feeling of freedom. Skill: Judgment: suits VC, but too abstract to render — no visual anchor. Action: ask first — "Who is free, and where? A child in open fields, a diver, a city rooftop at dawn? Any style — photoreal, anime, ink-wash?"

📦 Install

The skill is one portable SKILL.md folder. Pick whichever option fits your setup.

Option 1 — One-liner (recommended). Auto-detects your installed agents and copies the skill into each:

npx github:Alisa0808/vibe-creating-skill

Add --all for every known agent, name agents explicitly (… claude codex), or target any folder with --dir <path>.

Option 2 — Clone and copy. Same file, different home per agent:

git clone https://github.com/Alisa0808/vibe-creating-skill.git
cp -r vibe-creating-skill/skills/vibe-creating-prompt <your-agent-skills-dir>/

Option 3 — Cursor or any other LLM. Paste the body of the skill file (or its Chinese edition) as a rule (Cursor) or as the system prompt / custom instructions (GPT, Gemini, a local model, etc.).

Then restart your agent and describe what you want to film — e.g. "a basketball kid hits a buzzer-beater three."

🎬 Before & after

Real test cases from the original handbook — the same scene, a regular prompt vs. a Vibe Creating prompt, with the clip each one generated (videos from Volcengine's Seedance 2.0). See all eight in the worked test cases, and browse the example gallery for dozens more prompts.

Case 2 · near-VC input → light cleanup

▶ Press play to watch, with sound.

Case 3 · execution shot-script → direct rewrite

▶ Press play to watch, with sound.

Case 4 · heavy precision control → rewrite, with disclosure

▶ Press play to watch, with sound.

🚀 Generate it

Vibe Creating writes the prompt — to turn it into an actual clip, send the rewritten prompt to any text-to-video model. The quickest path is Atlas Cloud, one unified API for Seedance 2.0, Kling, Veo, Hailuo, Wan, Vidu, Gemini Omni, Grok Imagine, and more.

Let your agent do it end-to-end — add the official skill or MCP, then ask it to rewrite and generate:

# Skill
npx skills add AtlasCloudAI/atlas-cloud-skills
# …or MCP (Claude Code / Codex / Cursor / …)
claude mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="…"   # get one at atlascloud.ai/console/api-keys

"Rewrite this with Vibe Creating, then generate it with Seedance."

Or call the API directly:

curl -X POST https://api.atlascloud.ai/api/v1/model/generateVideo \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"bytedance/seedance-2.0/text-to-video","prompt":"<your Vibe Creating prompt>","ratio":"16:9"}'

Atlas Cloud skill · MCP server · browse models · get an API key

Disclosure: this repo is maintained by folks at Atlas Cloud. The skill itself is model- and provider-agnostic — any text-to-video API works.

🚫 When NOT to use it

Vibe Creating is for atmosphere, emotion, narrative, and visual exploration. For precise word-for-word dialogue sync, strict shot-by-shot execution, UI demos, or step-by-step tutorials, traditional precise prompting is the better tool — and the skill will tell you so rather than force a rewrite.

❓ FAQ

Vibe Creating is a prompt-writing paradigm for AI video generation: instead of over-specifying camera parameters and shot-by-shot scripts, you describe the story and feeling and trust the model to interpret it. This repo packages that approach as a reusable prompt skill that rewrites your input into a model-friendly text-to-video prompt.

Cover four layers without naming them: a visual anchor (the main subject), an action or state (what's happening), a local tonality (one mood word), and a video theme (use case + visual style). Keep the story; drop low-value technical parameters. The skill does this for you and asks for whatever layer is missing.

Any text-to-video model — it was distilled from Seedance 2.0, and the same prompts work well with Sora, Kling, Veo, Runway, Pika, and Hailuo. The output is plain natural-language description, not model-specific syntax.

Any agent that supports the open Agent Skills (SKILL.md) standard — Claude Code, Codex, OpenClaw, Hermes, and others. For tools that use their own rules format (e.g. Cursor) or any plain LLM, paste the skill as a rule / system prompt.

Vibe Creating is not "longer" or "shorter" — it's the right information. It removes ineffective technical noise and keeps the story, emotion, and key imagery, so the model locks onto your intent. It also refuses to rewrite inputs that genuinely need precise control (dialogue sync, UI demos), instead of forcing every prompt into one style.

No. It's an independent, faithful open-source port of a publicly-shared methodology. See Attribution & license and the NOTICE file.

🤝 Contributing

Translations, new gallery prompts, and refinements welcome — see the contributing guide.

📄 Attribution & license

The Vibe Creating paradigm, the original skill draft, and the example prompts originate from ByteDance / Volcengine (created with Seedance 2.0). This repository is an independent, faithful English/bilingual port of that publicly-shared methodology, not an official product. Original sources (in Chinese): Practice Handbook · Prompt Skill draft. See the NOTICE file for full attribution.

Code and documentation in this repo are released under the MIT License. The underlying paradigm and any trademarks remain with their original owners.