メニュー
This skill should be used when the user asks for a Seedance 2.0 template, genre recipe, product ad, lifestyle video, drama scene, music video, landscape shot, commercial, animation scene, or reusable production pattern.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Conecta una máquina nueva (Mac, Linux, Windows/WSL) a tu stack de Claude Code corriendo en un EC2 vía SSH + Tailscale + tmux persistente. Te guía paso a paso: detecta tu OS, instala Tailscale, configura SSH keys, crea aliases, verifica la conexión. Una vez configurado, el comando "ec2" desde cualquier terminal te conecta a Claude Code remoto exactamente igual que si estuviera local. Funciona incluso si tu Mac se cae o cambias de WiFi (tmux mantiene la sesión viva en EC2). Incluye runbook de persistencia server-side que DETECTA el patrón de la máquina (systemd system-level vs user-level + lingering) en vez de asumir, idempotente y multi-proyecto.
This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface - Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seedance route, or fal - including text/image/video/reference-to-video prompts, first/last frame, dialogue, lip-sync and audio, IP-safe rewrites, API, pricing and model-ID questions, and zh/ja/ko/es/ru prompt work. Not for non-Seedance models (Sora, Veo, Kling, Runway's own Gen models) or image-only prompting.
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.
This skill should be used when the user asks for Seedance 2.0 audio, dialogue, lip-sync, music, sound effects, ambience, beat-sync, audio-reference mapping, desync troubleshooting, or sound-driven visual timing.
This skill should be used when the user asks for camera movement, shot scale, lens feel, framing, one-take direction, dolly, pan, tilt, push-in, handheld, aerial, macro, or camera-transfer guidance for Seedance 2.0.
This skill should be used when the user asks for character consistency, character tags, identity lock, multi-character blocking, wardrobe continuity, hand safety, expression control, or likeness-sensitive character guidance.
| name | seedance-recipes |
| description | This skill should be used when the user asks for a Seedance 2.0 template, genre recipe, product ad, lifestyle video, drama scene, music video, landscape shot, commercial, animation scene, or reusable production pattern. |
| license | MIT |
| user-invocable | true |
| tags | ["templates","genres","recipes","seedance-20"] |
| metadata | {"version":"5.5.2","updated":"2026-06-12","parent":"seedance-20","author":"Iamemily2050 (@iamemily2050)","repository":"https://github.com/Emily2040/seedance-2.0","openclaw":{"emoji":"🎬","homepage":"https://github.com/Emily2040/seedance-2.0"}} |
Use recipes as starting patterns, not rigid prompt templates. Pick the recipe that matches the user's outcome, then customize subject, action, camera, lighting, audio, and constraints. Recipes should preserve the one-beat discipline of a short clip.
Load [ref:genre-guides] for genre patterns, [ref:examples-by-mode] when the user needs copy-ready examples, [ref:shot-list-continuity] for professional multi-shot sequences or commercials, and [ref:multilingual-community-examples] when the recipe should reflect Chinese/Russian/Japanese/Korean/Spanish community-style structures.
A recipe is a head start, never a mold. The user wants the confidence of a proven shape with their own story inside it. Bend the recipe to the story every time; a user who feels templated has been failed even if the output is competent.
| Family | Best use | Core pattern |
|---|---|---|
| Product | Ads, ecommerce, hero shots, material reveals. | product anchor + one material change + controlled camera + logo preservation |
| Lifestyle | Human use, food, travel, social clips. | simple action + lived environment + handheld or natural light + ambient sound |
| Drama | Emotion, dialogue, short narrative beats. | character tag + gesture + motivated camera + silence or sparse sound |
| Music video | Beat sync, dance, stylized edits. | rhythm reference + visible beat changes + light pulses + clear character blocking |
| Landscape | Establishing shots, nature, atmosphere. | slow camera + weather motion + layered depth + natural sound |
| Commercial | Brand-safe polish and function. | problem/use/result beat + precise product constraint + clean light |
| Animation | Original characters and stylized motion. | medium + shape language + palette + elastic or weighted motion |
| VFX | Transformations, particles, weather, energy. | source + material behavior + interaction + dissipation endpoint |
| First/last frame | In-between transitions, product state changes, character pose targets. | first frame + last frame + continuous transition + identity locks |
| Commercial campaign | 6/10/15/30s variants, vertical/social cutdowns, textless/localized masters. | hook + product proof + end state + cutdown matrix + delivery notes |
| Short drama (短剧) | Fast-cut vertical mini-drama beats: setup, reversal, cliffhanger. | two or three labeled shots + one emotional reversal + held reaction close + cut on the sting |
| Talking head (口播) | Presenter, explainer, livestream-style pitch to camera. | locked medium close-up + short quoted lines + minimal head motion + caption-safe framing + room tone |
| Home / space tour | Walkthrough of a room, venue, or property. | single continuous take + steady forward path + light changes per zone + ambient sound only |
Product I2V: [Image1] is the product reference; preserve logo, label, shape, and materials exactly. [One material or light change]. Camera: [single move]. Lighting: [physical source]. Sound: [ambient/SFX].
Drama T2V: Character A [visible emotional action] in [specific setting]. Camera: [motivated framing]. Lighting: [motivated source]. Sound: [ambient or short dialogue]. End state: [changed expression/action].
Reference Motion: [Video1] provides only [camera/action/timing] reference; do not transfer identity, costume, logo, or environment. New subject: [authorized/original subject]. [Action and endpoint].
First/Last Frame: [Image1] is the first frame. [Image2] is the last frame. Preserve [identity/product/scene anchors]. Generate a continuous transition from [start state] to [end state]. Camera: [locked or one controlled move]. Sound: [ambient/SFX].
Animation: Original [character archetype] [action] in [environment]. Style: [medium, line quality, texture, palette]. Motion: [rhythm]. Camera and sound: [simple support].
If a user gives many goals, choose the recipe that protects the most fragile requirement. Product identity beats camera spectacle; lip-sync beats large head motion; character consistency beats complex choreography; first/last-frame target accuracy beats extra style changes; safety and authorization beat style mimicry.
Return one selected recipe, why it fits, the customized prompt skeleton, compact final prompt, and campaign/delivery notes when relevant.
