Seedance Storyboard in Shanghai Animation Style
liangdabiao/smy-seedance-storyboard
Turns a story, novel or myth into a retro hand-drawn animation style short-drama script, episode breakdown, asset prompts and Seedance 2.0 storyboard prompts.
Routes story-to-video work through slash commands for character cards, scene images, storyboards, video prompts and posters, with prompt QC and draft, lock and commit states.
SKILL.md written in Chinese; this summary is our English description.
Install AI Visual Director
$ npx skills add jijiutong/ai-visual-director --skill ai-visual-director -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jijiutong/ai-visual-director ai-visual-director --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ai-visual-director" agent skill from https://github.com/jijiutong/ai-visual-director/tree/main into .claude/skills/ai-visual-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-visual-director", 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.
$ npx skills add jijiutong/ai-visual-director --skill ai-visual-director -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jijiutong/ai-visual-director ai-visual-director --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ai-visual-director" agent skill from https://github.com/jijiutong/ai-visual-director/tree/main into .agents/skills/ai-visual-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-visual-director", 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 jijiutong/ai-visual-director --skill ai-visual-director -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jijiutong/ai-visual-director ai-visual-director --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ai-visual-director" agent skill from https://github.com/jijiutong/ai-visual-director/tree/main into .cursor/skills/ai-visual-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-visual-director", 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.
$ npx skills add jijiutong/ai-visual-director --skill ai-visual-director -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jijiutong/ai-visual-director ai-visual-director --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ai-visual-director" agent skill from https://github.com/jijiutong/ai-visual-director/tree/main into .gemini/skills/ai-visual-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-visual-director", 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 jijiutong/ai-visual-director ai-visual-directorInstalls 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 jijiutong/ai-visual-director --skill ai-visual-director -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ai-visual-director" agent skill from https://github.com/jijiutong/ai-visual-director/tree/main into .github/skills/ai-visual-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-visual-director", 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 jijiutong/ai-visual-director --skill ai-visual-director -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jijiutong/ai-visual-director ai-visual-director --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ai-visual-director" agent skill from https://github.com/jijiutong/ai-visual-director/tree/main into .opencode/skills/ai-visual-director/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-visual-director", 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
ai-visual-director- GitHub stars
- 176
- Token cost
- ~1k tokens
- SKILL.md length
- 220 words
- Files
- 215 (incl. scripts)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Routes story-to-video work through slash commands for character cards, scene images, storyboards, video prompts and posters, with prompt QC and draft, lock and commit states.
- Turning a story or script into a storyboard and video prompts
- SKILL.md covers 触发条件, 默认行为, 命令路由 and 主执行链, plus 6 more sections
- Making a character card or scene card that stays consistent across shots
- Producing a poster or cover visual from a story
What it does
This is the master routing skill of a larger Chinese-language visual production toolkit. It turns stories, scripts, novel excerpts or storyboard ideas into an executable visual plan using commands such as `/create`, `/source`, `/storyboard`, `/character`, `/scene`, `/video`, `/style` and `/poster`, also available under an `/avd/` namespace. If a user only pastes a story or asks for a one-click result, it defaults to `/create standard`.
Each command routes to a sub-skill file that must be read before any asset is produced, together with templates and rule files for format, numbering, quality checks and character and scene consistency. Output starts in a `draft` state and is written to project state only after you confirm, moving through draft, locked and committed with the `/lock` and `/commit` commands. Further commands handle dialogue, sound and status checks. The excerpt is truncated.
When your agent uses it
- Turning a story or script into a storyboard and video prompts
- Making a character card or scene card that stays consistent across shots
- Producing a poster or cover visual from a story
- Checking video prompts for quality before sending them to a video model
Example prompts
- “/create standard: here is my short story about a lighthouse keeper and a lost whale.”
- “Make a character card for the lighthouse keeper that I can reuse across scenes.”
- “Write video prompts for scene one and run the prompt QC check.”
Requirements
- API settings copied from `api-config.template.env` for image or video generation
What it can do on your machine
Read from SKILL.md and the folder at commit b47f664. 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
Ships 1 file in scripts/, which the agent can run.
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
AI Visual Director loads about 1k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 220 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); the scripts in this folder are not scanned.
SKILL.md
The full file from jijiutong/ai-visual-director at commit b47f664, republished under its MIT licence (© jijiutong). 220 words, ~1,049 tokens.
Download SKILL.mdSave it as
.claude/skills/ai-visual-director/SKILL.md (or your agent's skills folder). This skill also uses 214 other files; get the full folder from GitHub.- name
- ai-visual-director
- description
- AI视觉导演主控路由。用于 /create /avd/create 故事到视频、角色卡、场景图、故事板、分镜图、视频 Prompt、海报、Prompt QC、状态锁定和子技能分发。普通故事默认 /create standard。
AI Visual Director — 主控路由
这是给 agent 执行用的主 Skill，不是产品 README。README 负责介绍、安装和能力展示；本文件只定义触发、路由、必读文件和执行约束。
触发条件
当用户提出以下任一需求时，使用本 Skill：
- 把故事、剧本、小说片段、分镜想法转成可执行视觉方案
- 生成角色卡、场景图、故事板、分镜图、视频 Prompt、海报或执行包
- 使用
/create/source/storyboard/character/scene/video/style/poster - 使用
/avd/*命名空间命令 - 要求进行角色一致性、场景一致性、参考图锚定、视频平台适配或 Prompt QC
默认行为
如果用户只粘贴故事或说“一键生成/直接出/auto”，默认路由到：
/create standard默认输出状态为 draft。只有用户明确确认、锁定或提交时，才写回项目状态：
draft -> locked -> committed命令路由
| 用户意图 | 路由 | 必读文件 |
|---|---|---|
| 一键故事到视频包 | /create 或 /avd/create | sub-skills/create/SKILL.md |
| 读取 Obsidian/Markdown/粘贴/批处理 | /source 或 /avd/source | sub-skills/source/SKILL.md |
| 角色外观、表情、服装、DNA、一致性 | /character 或 /avd/character | sub-skills/character/SKILL.md |
| 场景空间、光照、材质、地理关系 | /scene 或 /avd/scene | sub-skills/scene/SKILL.md |
| 故事板、分镜图、镜头设计、全案板 | /storyboard 或 /avd/storyboard | sub-skills/storyboard/SKILL.md |
| 视频 Prompt、首尾帧、平台参数、拆段 | /video 或 /avd/video | sub-skills/video/SKILL.md |
| 风格浏览、融合、迁移、导演方法参考 | /style 或 /avd/style | sub-skills/style/SKILL.md |
| 独立海报、封面、营销视觉 | /poster 或 /avd/poster | sub-skills/poster/SKILL.md |
| 台词、字幕、口型节奏 | /dialogue | engines/dialogue-engine.md |
| 环境音、拟音、音乐、混响 | /sound | engines/sound-engine.md |
| 锁定、提交、解锁、检查状态 | /lock /commit /unlock /check | engines/state-commit.md |
先读路由目标文件，再按该文件继续读取模板、规则和引擎。不要只凭本文件生成最终资产。
/create 不替代 /storyboard、/character、/scene；它只在一键总编排中按模式调度三条核心资产子链。
/storyboard 核心资产：故事板
/character 核心资产：角色卡
/scene 核心资产：场景图主执行链
/create 是默认总编排链，按需调度角色、场景、分镜和视频模块。具体步骤以 sub-skills/create/SKILL.md 的执行链路为权威，本文件只列主控边界：
engines/command-gate.md
-> sub-skills/create/SKILL.md
-> rules/format-contract.md
-> rules/prompt-qc.md
-> rules/final-video-qc.md
-> engines/state-commit.md必须遵守
- 输出资产前必须读取对应子 Skill 和模板文件。
- 格式边界以
rules/format-contract.md为准。 - 编号体系以
rules/numbering.md为准。 - 视频负面词和质量检查以
rules/qc.md、rules/final-video-qc.md、rules/prompt-qc.md为准。 - 角色一致性以
rules/character-consistency.md为准。 - 场景一致性以
rules/scene-consistency.md为准。 - 默认参数以
rules/one-click-defaults.md和api-config.template.env为准。 - 用户没有确认时，不写回
state/主状态；允许在输出中生成 draft 状态块或执行清单。
模板读取规则
| 输出类型 | 必读模板 |
|---|---|
| 角色卡 | templates/character-sheet.md |
| 场景图 | templates/scene-card.md |
| 全案板 | templates/full-board.md |
| 分镜图 | templates/quick-board.md |
| 海报 | templates/poster.md |
| 台词脚本 | templates/dialogue-script.md |
| 声音设计 | templates/sound-design-sheet.md |
模板是输出结构的权威源。模板内已有的模块数、参数数、版式编号和禁止项，不要在本文件重复维护。
能力分层
| 层级 | 内容 | 默认策略 |
|---|---|---|
| A 稳定治理层 | command-gate、format-contract、lock-state、prompt-qc、auto-repair | 所有命令必走 |
| B 资产生产层 | character、scene、storyboard、video、dialogue、sound、poster | 按用户意图调用 |
| C 导演增强层 | shot-budget、video-director、motion-physics、emotion-curve、color-narrative | project/standard/full 默认可用 |
| D 探索发散层 | fusion、multi-version、style-migration、director-imitation、series、mood-slider | 用户明确要求才启用 |
写回策略
| 状态 | 触发 | 行为 |
|---|---|---|
draft | 默认生成 | 只输出草稿、状态块或执行清单，不改 state/ 主状态文件 |
locked | 用户确认锁定 | 写入 state/lock-state.md，禁止自动覆盖 |
committed | 用户确认提交 | 写回 state/variable-registry.md、state/asset-map.md、state/project-graph.md 等持久状态 |
涉及状态变更时，先读 engines/state-commit.md 和相关 state/*.md。
禁止事项
- 禁止把 README 的安装说明、营销文案、能力展示复制进本文件。
- 禁止不读子 Skill 或模板，直接凭记忆输出角色卡、场景图、故事板或视频 Prompt。
- 禁止把全案板和分镜图混为同一种输出；先用
rules/format-contract.md判断output_type。 - 禁止默认开启 D 类探索能力，除非用户明确要求发散、多版本、融合、迁移或导演模仿。
- 禁止在用户未确认时覆盖已 locked/committed 的状态。
- 禁止输出未经过 Prompt QC、格式合同和视频 QC 的最终执行包。
全局负面清单
所有图像/视频 Prompt 必须按需合并 rules/negative-prompt.md，并至少包含：
no watermark, no logo, no random large text, no garbled Chinese, no broken faces,
no duplicated limbs, no messy panels, no low-quality collage, no text overlay,
no speech bubbles (unless manga format), no cartoon style (unless specified),
no flat illustration, no marketing poster style© jijiutong, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 214 other files (scripts) in the repository root of jijiutong/ai-visual-director.
- SKILL.md
- .gitignore
- LICENSE
- README.md
- README.zh-CN.md
- api-config.template.env
- demo/demo-script.md
- demo/zero-to-one-demo.md
- docs/README.md
- docs/capabilities.md
- docs/commands.md
- docs/system-architecture.md
- docs/usage.md
- engines/README.md
- engines/act-structure.md
- engines/aesthetic-director.md
- engines/asset-plan.md
- engines/auto-repair.md
- … and 197 more
Open the folder on GitHubat commit b47f664
Compare with similar skills
AI Visual Director 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 |
|---|---|---|---|---|---|---|
| AI Visual Director this skilljijiutong/ai-visual-director | 176 | — | ~1k | Automated safety check: Pass | MIT | |
| Seedance Storyboard in Shanghai Animation Styleliangdabiao/smy-seedance-storyboard | 138 | — | ~3k | Automated safety check: Pass | None | |
| Canghe Comicfreestylefly/canghe-skills | 461 | 8 repos | ~3.2k | Automated safety check: Pass | None | |
| Xhs ImagenNimaChu/xhs-imagen | 120 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Hbg Life SimulationMr-funny/hbg-life-simulation | 141 | — | ~5.8k | Automated safety check: Pass | MIT | |
| Knowledge Comic CreatorJimLiu/baoyu-skills | 27k | 2 repos | ~5.5k | Automated safety check: Pass | MIT |
Similar skills
Canghe Comic
freestylefly/canghe-skills
Knowledge comic creator supporting multiple art styles and tones.
Xhs Imagen
NimaChu/xhs-imagen
Create complete Xiaohongshu image-and-text posts from a topic, article, document, or rough idea, including research, fact checking, post copy, pagination, storyboards, a 3:4 cover, 9:16 content…
Hbg Life Simulation
Mr-funny/hbg-life-simulation
Create Chinese HBG “模拟人生 / 人生副本” narrative videos with a consistent comic IP, a rapid multi-life opening, continuous natural-speed narration, synchronized short captions, dense static manga…
Knowledge Comic Creator
JimLiu/baoyu-skills
Writes original educational comics with detailed panel layouts in a chosen art style and tone, generating the images in batches through whichever backend is available.
Seedance 2.0 Storyboard Prompts
elementsix/elementsix-skills
Interviews you about a video idea, then writes a timed shot-by-shot prompt for Seedance 2.0 using its image, video and audio reference syntax.
Related
Categories
Questions about AI Visual Director
What does AI Visual Director do?
Routes story-to-video work through slash commands for character cards, scene images, storyboards, video prompts and posters, with prompt QC and draft, lock and commit states. This is the master routing skill of a larger Chinese-language visual production toolkit. It turns stories, scripts, novel excerpts or storyboard ideas into an executable visual plan using commands such as `/create`, `/source`, `/storyboard`, `/character`, `/scene`, `/video`, `/style` and `/poster`, also available under an `/avd/` namespace.
When should I use AI Visual Director?
AI Visual Director fits situations like: turning a story or script into a storyboard and video prompts; making a character card or scene card that stays consistent across shots; producing a poster or cover visual from a story; checking video prompts for quality before sending them to a video model.
How do I install AI Visual Director in Claude Code?
Run `npx skills add jijiutong/ai-visual-director --skill ai-visual-director -a claude-code`. Or copy the skill folder (the jijiutong/ai-visual-director repository) into .claude/skills/ai-visual-director in your project. Claude Code loads it when a task matches its description.
How do I install AI Visual Director in Codex?
Run `npx skills add jijiutong/ai-visual-director --skill ai-visual-director -a codex`. Or copy the skill folder (the jijiutong/ai-visual-director repository) into .agents/skills/ai-visual-director in your project. Codex loads it when a task matches its description.
Can I use AI Visual Director 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 jijiutong/ai-visual-director --skill ai-visual-director -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-visual-director, .gemini/skills/ai-visual-director, .github/skills/ai-visual-director and .opencode/skills/ai-visual-director in your project.
What does AI Visual Director need to run?
SKILL.md names no scripts, command-line tools or credentials: AI Visual Director is instructions for the agent only. Our summary lists: API settings copied from `api-config.template.env` for image or video generation.
Does AI Visual Director 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 AI Visual Director 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does AI Visual Director use?
AI Visual Director is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does AI Visual Director use?
About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to AI Visual Director?
Skills that share tags, products or a category with AI Visual Director: Seedance Storyboard in Shanghai Animation Style (liangdabiao/smy-seedance-storyboard, 138 stars), Canghe Comic (freestylefly/canghe-skills, 461 stars), Xhs Imagen (NimaChu/xhs-imagen, 120 stars) and Hbg Life Simulation (Mr-funny/hbg-life-simulation, 141 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains AI Visual Director?
jijiutong (a GitHub user) maintains it in jijiutong/ai-visual-director, which has 176 GitHub stars. The repository was last updated on July 19, 2026.
Source: jijiutong/ai-visual-director on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.