一套完整的视频导演工作流

SKILL前端设计
前端设计 未标注权限 许可证不明确
安装这个技能

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, fal, or third-party provider/router surfaces such as EvoLink, OpenRouter, Kie.ai, PiAPI, LaoZhang, Runware, ModelsLab, AI/ML API, MuAPI, SeeGen, and Segmind - 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.

一句话选型结论

按资料字段整理

一套完整的视频导演工作流是前端设计类的 Agent Skill,安装方式未标注,权限级别未标注,许可证不明确,有可直接复制的安装命令。技能本质是给模型读的说明书,效果取决于模型与客户端;装完先用一个小任务验证,再放进正式流程。

分类前端设计 安装方式未标注 权限级别未标注权限 许可证许可证不明确
累计安装 未标注 本周 未标注
GitHub 星标 未标注 仓库 未标注
下载量 未标注 技能市场下载数
权限级别 未标注权限 安装前请确认风险范围
许可证 许可证不明确 未说明

安装

未标注
在支持 Skills 的客户端里执行,装完问一句「你有哪些技能」验证
skillhub install user_bcde01df/validata-skills
  1. 1
    确认客户端支持

    确认你的客户端支持 Skills(Claude、Codex、Cursor 等),并升级到较新的版本。

  2. 2
    拿到技能文件

    执行上面的命令安装;也可以把仓库里的 SKILL.md 手动放进客户端的 skills 目录。

  3. 3
    刷新技能列表

    重新打开客户端,或刷新技能列表,让新放进来的技能被加载。

  4. 4
    验证是否生效

    问一句「你有哪些技能」,确认列表里出现它,再拿一个小任务试跑。

技能档案

前端设计
字段来自技能仓库与公开索引,中文说明由本站标注
作者 / 维护方user_bcde01df仓库 未标注 · 版本 未标注
宿主客户端未标注技能可被这些客户端加载
安装方式未标注安装包 community
权限级别未标注权限安装前请确认风险范围
许可证未说明许可证不明确,商用前请自行确认条款
仓库可用性available技能仓库当前是否可访问
最近核验未标注上游最后核验时间 · 数据更新 1791728374
正文体量12.6 KBSKILL.md 原文大小,越大说明说明书写得越细

典型使用场景

3 类
按分类整理的常见用法,具体以 SKILL.md 为准
出页面与组件

按描述生成页面结构和组件草稿。

调整样式与布局

改间距、配色与响应式布局。

生成设计说明

把设计稿整理成开发能接的说明。

选择建议

装之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 有可直接复制的安装命令,不用自己翻文档找入口。

先想清楚的地方

  • 没有标注权限级别,实际能做什么要装好后确认。
  • 许可证不明确,商用或二次分发前先到仓库确认条款。
  • 没有做站内核验,内容以作者仓库为准。
  • 技能只是说明书,实际效果取决于模型与客户端,装完先用小任务试一遍。

更适合

  • 需要在前端设计场景里给模型补一套做法的人。
  • 愿意先读一遍 SKILL.md、确认它会让模型做什么的人。

不太适合

  • 对许可证要求很严、必须明确可商用的人。
  • 只想装完就自动变强、不打算看说明书的人。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
技能权限级别安装方式累计安装宿主客户端安装命令
一套完整的视频导演工作流当前 未标注权限 未标注 未标注 未标注 有
前端设计 只读 GitHub 仓库 882.3 万 Codex、Claude、Cursor 有
Vercel 组合模式 联网访问 GitHub 仓库 385.9 万 Codex、Claude、Cursor 有
Vercel React native skills 前端 只读 GitHub 仓库 246.9 万 Codex、Claude、Cursor 有
adapt 搜索 浏览器控制 GitHub 仓库 202.7 万 Codex、Claude、Cursor 有
使用我的浏览器 浏览器控制 GitHub 仓库 184.8 万 Codex、Claude、Cursor 有

SKILL.md 全文

12.6 KB
模型实际读到的说明书原文,来自技能仓库

seedance-20

Seedance 2.0 operating loop for agent-directed video work. Use this root skill to route, check facts, protect references, and keep prompts compact before loading specialized sub-skills.

Soul

This skill exists so that a person who arrives with a feeling leaves with a film. Three principles govern everything below:

  1. Hear the intent behind the words. Users describe outcomes ("make it feel like home"), not parameters. Every gate and sub-skill translates feeling into craft; none of them may hand the translation work back to the user.
  2. Keep the story alive. Hold a story state across the conversation: subject, mode, look, references, decided constraints, and what failed before. Every skill reads it before asking anything and updates it after acting. A user should never have to repeat a decision, and a new request inherits the world already built.
  3. Evolve with the user. Speak plainly to a beginner and in director language to a professional - and notice when the same user grows from one into the other across a project. The register adapts; the standards never do.

Fast Lane

Most requests are one short clip from someone who just wants to see their idea. Do not run the full gate loop on them. Take the fast path when the request is a single standalone clip, from a non-expert, with no IP/likeness/brand/real-person or safety flag and no platform-fact question (API, pricing, model ID, limits, region):

  1. Go straight to [skill:seedance-interview-short] - or write the brief immediately if the idea is already clear - then [skill:seedance-prompt-short].
  2. Apply craft inline from memory: one visible beat, one motivated camera move, one motivated light source, sound intent, and the directing coherence rule (name one intention; make camera, light, and performance serve it). Load [ref:directing-engine], [ref:capability-map], [ref:allocation-model], and the source or professional gates only when something actually invokes them.
  3. Treat it as one clip: do not ask sequence or continuation questions yet. Raise "should this be a series, part two, or longer" only after the first draft, or when the user says continue, extend, next part, or longer.
  4. Keep the single-clip prompt compact (about 40-110 words) unless the active surface is a verified stricter API, and keep director language (blocking, directorial voice, shot contracts) inside the internal brief - speak to the user in plain words.

Leave the fast lane the instant the request earns a gate: IP/likeness/brand/safety risk goes to the safety gate (step 9); a platform-fact question loads the source gate; a film, client, or delivery request loads the professional gate; a long story, connected clips, or continuation goes to the Sequence Gate. When in doubt about safety, leave the fast lane. The Operating Loop below is the full procedure - the fast lane is the default for the common case, and every gate it skips stays one signal away.

Operating Loop

  1. Intake: identify the user's goal, production phase, target surface, mode, duration, aspect ratio, references, audio needs, deliverables, and safety/IP risks. If intake surfaces a clear safety, IP, likeness, or evasion risk, jump straight to the safety gate (step 9) before any planning.
  2. Source gate: before platform claims, load [ref:api-status] and [ref:source-registry]. For Runway, Volcengine, fal, provider/router, or China-facing surface specifics, also load [ref:platform-surface-matrix].
  3. Professional gate: if the user asks for film, ad, campaign, client, delivery, localization, color, sound, subtitle, post, QC, or multi-shot work, load [ref:pro-filmmaking-standards] before drafting.
  4. Sequence Gate: classify the request as standalone_clip or sequence_project before the Mode Gate. Use sequence_project for long stories, connected clips, continuation/extend/next-part requests, dense action/dialogue scenes, campaigns, or any idea whose beats cannot clearly fit inside one verified active-surface generation. For sequence work, load [skill:seedance-sequence], [ref:sequence-project-state], [ref:continuation-handoff], and [ref:prompt-compiler]; for continuation, repair-tail, or re-anchor requests, also load [skill:seedance-continuation].
  5. Mode gate: choose T2V, I2V, V2V, R2V, FLF2V, edit, native extend when verified for that surface, or troubleshoot before writing prose.

Mode availability is surface-specific: edit and extend exist on Dreamina and Ark routes; fal has no dedicated extend endpoint - to continue a clip on fal, prefer reference-to-video with the previous clip as a video reference (keeps motion and audio context), and chain image-to-video from its last frame as the fallback. Provider/router surfaces can rename the same job type, hide fields, or expose only selected modes; recheck their current docs before implementation.

  1. Capability check: when planning any shot, mode, or budget, load [ref:capability-map] to design into model strengths and around known limits, and [ref:allocation-model] to decide where the prompt spends its fidelity budget before drafting.
  2. Reference map: assign every asset one primary role: identity, first frame, last frame, product, environment, motion, camera, timing, audio, or style. State what must not transfer.
  3. Multilingual gate: if the prompt uses Chinese, Russian, Japanese, Korean, Spanish, or code-mixed wording, load [ref:multilingual-community-examples] and preserve reference tags exactly. For native Chinese, Japanese, or Korean example-driven requests, route to [skill:seedance-examples-zh], [skill:seedance-examples-ja], or [skill:seedance-examples-ko].
  4. Safety gate: route IP, likeness, voice, brand, real-person, graphic, or evasion-like wording through [skill:seedance-copyright] or [skill:seedance-filter].
  5. Direction: before drafting any scene, name one intention and make camera, lens, light, blocking, performance, and sound serve it instead of picking a "cinematic look" - apply this coherence rule inline. Load [ref:directing-engine] only when scenes need distinct treatment, one directorial voice must hold across many clips, or the right setup is genuinely unclear.
  6. Prompt build: route to [skill:seedance-interview], [skill:seedance-prompt], [skill:seedance-prompt-short], [skill:seedance-sequence], [skill:seedance-continuation], or a domain skill for camera, motion, lighting, audio, characters, VFX, style, recipes, or pipeline.
  7. Quality pass: run anti-slop and the directing coherence test, then check one visible beat, one primary camera move, physical motivated light, sound intent, continuity anchors, constraints, delivery caveats, and source-date caveats.
  8. Repair loop: when a take returns, triage it with [ref:retake-protocol] (keep / fix in post / edit / re-roll / rewrite, one variable per retake, inside an attempt budget); if it fails outright, diagnose root cause before adding adjectives via [skill:seedance-troubleshoot].

Sequence Gate

For a sequence project, do not write Clip 01 until these are known: story objective, final story outcome, ordered major beats grouped into scenes, active surface or conservative surface assumption, clip budget, current clip narrative job and felt intent, and current clip completed endpoint.

Do not write a continuation prompt until the previous accepted clip or its actual final frame has been reviewed and its observed end state recorded.

Sequence invariants:

  • every sequence prompt has project_id and clip_id lineage;
  • accepted observed state overrides planned state;
  • rejected footage is excluded from canon and cannot become a continuation source;
  • future prompts remain provisional until the preceding accepted take is reviewed;
  • exact reference tags survive every clip unchanged;
  • seamless continuation stays inside a scene; a scene boundary opens from canonical references and resets extension_depth;
  • completed beats cannot replay and reserved future beats cannot leak early;
  • continuity state must be updated after each accepted take;
  • final Seedance prompts remain natural language unless the user explicitly asks for structured output.

Load Map

Situation Load
Vague idea or missing brief [skill:seedance-interview] or [skill:seedance-interview-short]
Long story, connected clips, campaign sequence, dense action/dialogue scene, or a prompt that needs several generations [skill:seedance-sequence], [ref:sequence-project-state], [ref:prompt-compiler]
Continue, extend, next part, repair tail, bridge known states, or re-anchor drift from accepted footage [skill:seedance-continuation], [ref:continuation-handoff], [ref:continuity-qc]
Review a generated take and update canon before the next prompt [ref:retake-protocol], [ref:sequence-project-state], [ref:continuation-handoff]
First multi-clip project, or how the sequence loop actually runs end to end [ref:sequence-worked-trace]
Dense animation storyboard or multi-shot prompt [ref:dense-storyboard-mode], [ref:multishot-grammar], [ref:2d-anime-grammar]
Production prompt [skill:seedance-prompt], [ref:quick-ref], [ref:prompt-examples]
Planning any shot, mode, or budget [ref:capability-map]
Where the prompt spends fidelity: identity vs motion vs scene density [ref:allocation-model], [ref:intent-vs-precision]
Multi-shot prompt, cuts inside one clip, or shots-per-duration budget [ref:multishot-grammar]
2D, anime, or cel-style motion [ref:2d-anime-grammar], [skill:seedance-style]
Professional film, commercial, campaign, or delivery workflow [ref:pro-filmmaking-standards], [ref:shot-list-continuity], [ref:delivery-qc]
Compact prompt or Chinese compression [skill:seedance-prompt-short], language vocab reference
Choosing the right camera, light, blocking, performance, and voice for a scene, keeping every choice motivated, or holding one directorial style across a long story [ref:directing-engine]
Camera, lens, blocking, shot contract [skill:seedance-camera], [ref:cinematography-shot-language]
Image reference / first frame [ref:i2v-guide], [ref:reference-workflow]
First and last frame [ref:first-last-frame-guide]
API, Runway, Volcengine, fal, provider/router surfaces, China-facing surfaces, workflow, pricing, model IDs [skill:seedance-pipeline], [ref:api-workflow], [ref:model-name-map]
Color, ACES, HDR/SDR, aspect ratio, subtitles, audio post, or QC [ref:color-pipeline-aces], [ref:aspect-ratio-delivery], [ref:subtitles-localization], [ref:audio-post-delivery], [ref:delivery-qc]
Genre template, examples, or a worked directing example in a specific genre [skill:seedance-recipes], [ref:examples-by-mode], [ref:genre-guides], [ref:directing-engine-genre-library]
Chinese examples or safe Chinese rewrites [skill:seedance-examples-zh], [skill:seedance-vocab-zh], [ref:vocab/zh]
Japanese examples or safe Japanese rewrites [skill:seedance-examples-ja], [skill:seedance-vocab-ja], [ref:vocab/ja]
Korean examples or safe Korean rewrites [skill:seedance-examples-ko], [skill:seedance-vocab-ko], [ref:vocab/ko]
Russian/Spanish or mixed-language examples [skill:seedance-vocab-ru], [skill:seedance-vocab-es], [ref:multilingual-community-examples]
Slop-heavy or filter-tripping English wording [skill:seedance-vocab-en], [skill:seedance-antislop]
Bad result [skill:seedance-troubleshoot]
A take came back: keep, fix in post, edit, re-roll, or rewrite [ref:retake-protocol]
Why a rule works, or a novel case no rule covers [ref:model-mechanics]

Preserve reference tags exactly, keep prompts short, and never convert field-observed community tricks into official platform guarantees. For professional filmmaker requests, deliver the workflow object the role needs: shot list, shot contract, continuity ledger, prompt, post handoff, localization plan, or QC checklist.

常见问题

5 问
答案由本站依据条目字段整理
一套完整的视频导演工作流怎么安装?

在支持 Skills 的客户端里执行:skillhub install user_bcde01df/validata-skills。安装方式为未标注。装完刷新技能列表或重开客户端。

一套完整的视频导演工作流支持哪些客户端?

资料没有标注宿主客户端,但只要客户端支持 Skills(Claude、Codex、Cursor 等),一般都能加载。

一套完整的视频导演工作流权限高吗,安全吗?

权限级别为未标注权限。安装前先看它会读取或写入哪些内容。

一套完整的视频导演工作流收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于技能本身和所用的模型或客户端,正式使用前按作者说明确认。

一套完整的视频导演工作流用什么许可证?

许可证标注为 未说明(许可证不明确)。商用或二次分发前请到仓库确认条款原文。

热门专题

按场景挑技能
全部专题 →

技能内容以作者仓库为准;分类、权限级别与许可证状态的中文说明为中文整理,最近核验 未标注。