Chuanzhang Ai Shijie Workflow logo

Chuanzhang Ai Shijie Workflow

Community
zhangxiansheng-888
chuanzhang-ai-shijie-workflow

按船长AI视界规定的01→02→03→04顺序,依次调用中文影视创作、真人感人像提示词、静态图像提示词、分镜与人物情绪融合技能。Use when the user asks for 船长AI视界完整流程、从灵感到分镜、一键工作流、按顺序调用全部技能、部署后生成完整内容,或要求不得跳步、不得打乱技能与产出顺序。

Overview

Publisherzhangxiansheng-888
RepositorychuanzhangAIshijie
Skill namechuanzhang-ai-shijie-workflow
Stars
73
Forks
11
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by zhangxiansheng-888 on GitHub. Read the source before you install it.

Installation

Install the Chuanzhang Ai Shijie Workflow AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/zhangxiansheng-888/chuanzhangAIshijie/tree/main/skills/chuanzhang-ai-shijie-workflow
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zhangxiansheng-888/chuanzhangAIshijie.git /tmp/chuanzhangAIshijie
mkdir -p .claude/skills
cp -r /tmp/chuanzhangAIshijie/skills/chuanzhang-ai-shijie-workflow .claude/skills/chuanzhang-ai-shijie-workflow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Chuanzhang Ai Shijie Workflow in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Chuanzhang Ai Shijie Workflow on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Chuanzhang Ai Shijie Workflow is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

船长AI视界 01→04 总流程

船长AI视界

本技能只负责顺序、状态和交接,不重写四个生产技能的方法论。

最高规则:忠实调用

  1. 固定按 01 → 02 → 03 → 04 执行。
  2. 开始每一阶段前,完整读取该阶段技能的 SKILL.md,再按其中的路由读取它要求的引用文件。
  3. 阶段内部的步骤名、字段、输出结构、提问方式、确认方式和边界,以生产技能原文为唯一依据。
  4. 不得把网页目录、演示卡片或本总流程的阶段编号冒充为生产技能内部步骤。
  5. 不得增加生产技能原文中找不到的强制步骤、字段、评分、提示词结构或确认口令。
  6. 本文件与生产技能有冲突时,以生产技能原文为准;本文件只保留一级执行顺序。
  7. 需要署名、来源或品牌时只写 船长AI视界。

依赖

按顺序检查并读取:

  1. ../chuanzhang-chuangzuo-v1/SKILL.md
  2. ../chuanzhangzhenren-prompts/SKILL.md
  3. ../chuanzhang-tuxiangtishici/SKILL.md
  4. ../chuanzhang-fenjing-biaoqing/SKILL.md

缺少任一技能时,报告准确目录名并停止,不用通用写作代替。

状态

至少记录:

text
current_step
completed_steps
confirmed_outputs

每次回复开头显示:

text
【船长AI视界完整流程】
当前阶段:01/04
本阶段调用:chuanzhang-chuangzuo-v1
已完成阶段:无

生产技能内部要求暂停时,先使用它自己的确认方式,不得用总流程口令替换。

当本阶段已按生产技能原文完整结束后,显示一级交接:

text
【阶段交接】
当前阶段已完成:01
下一阶段:02
如需继续完整流程,请回复:确认01

确认01 / 确认02 / 确认03 / 确认04 只是本总流程的一级阶段交接口令,不属于任何生产技能内部步骤。

01/04 中文影视创作

调用 chuanzhang-chuangzuo-v1。

  • 先由该技能判断从零创作、已有材料修改、诊断、评分或分场等路由。
  • 从零创作时,严格执行其当前 SKILL.md 中的“从零创作总流程”。
  • 保留该技能原生的 通过 / 修改 / 自检 暂停机制。
  • 双轨节奏属于该技能的“分场大纲 / 场景拆解”,不得另造“拉片节奏解释”步骤。
  • 只有该技能原文要求或用户明确要求时,才输出相应诊断与评分。

向02传递已经确认的剧本材料,以及剧本中可读取的人物、场景、道具、时代、类型、情绪变化和风格信息。不得声称生产技能输出了它没有输出的独立资产包。

02/04 真人感人像提示词

调用 chuanzhangzhenren-prompts。

  • 先识别单人、组图、九宫格、情侣、细节特写或提示词框架。
  • 有真人参考图时使用该技能规定的身份参考原句;没有参考图时明确不能保证保留本人长相。
  • 按该技能规定的模块顺序构建提示词:
text
身份参考(如有) → 图像用途 → 身份锚点 → 脸部细节 → 主体气质 → 妆容体系 → 滤镜质感 → 构图机位 → 镜头焦段感 → 景深背景 → 光线设计 → 场景服装发型 → 真实感细节 → 人体空间 → 负面约束
  • 保留该技能当前任务对应的原生输出形状,例如单人任务的 真人写真提示词 与 这版控制的重点。
  • 不得擅自拆成“02.1—02.8身份包”。

向03传递02实际产出的真人提示词与控制重点,不虚构额外人物字段。

03/04 静态图像提示词

调用 chuanzhang-tuxiangtishici。

  • 只生成静态图像提示词,不写时间戳、镜头时长、动态运镜、声音或转场。
  • 从01剧本中选择适合静帧化的场景、道具、人物或关键时刻。
  • 继承已确认的风格说明;对同一项目保持类型、时代、色彩、用光、写实等级、服装、美术和材质一致。
  • 每条提示词使用该技能原生七段结构:
text
[Subject + Action] + [Location / Context] + [Composition] + [Lighting] + [Style / Aesthetic] + [Camera / Lens] + [Color Grading]
  • 每项先输出 English Prompt,再输出保持同一意图的 中文提示词。
  • 人物画面按照图像技能原文融合真人感规则和可见情绪表演规则;静态图只写当前瞬间,不写按秒变化的动态情绪时间线。
  • 不得把“风格母版、资产编号、连续性检查”等网页组织方式宣称为该技能固定输出;只有用户要求时才将其作为项目管理信息补充,并明确不是技能内部步骤。

向04传递01剧本和03实际生成、用户确认采用的静态资产提示词或参考图。

04/04 分镜与人物情绪融合

调用 chuanzhang-fenjing-biaoqing。

  • 先完成生产技能原文规定的六道 Gate;缺少任一确认时停止。
  • Gate名称、提问内容、退回条件、时间划分和交付形式全部以该技能及其引用文件为准。
  • 每条视频提示词按该技能原文的固定结构输出。
  • 每个镜头固定按以下顺序:
text
画面动作概述:
画面构图:
机位:
动作:
表情:
音效:
  • 表情: 必须位于 动作: 后、音效: 前,并包含该技能要求的情绪因果、三轴控制、可见微表演、顶点、余波和摄影机响应。
  • 单条视频提示词最长15秒;15秒是上限,不是目标。正式写作前按技能原文确认数量与时间划分。
  • 用户选择网页时才执行HTML交付与HTML QA。
  • 情绪必须写回每个镜头,不得另做与分镜分离的“情绪附件”。

网页与Demo

网页一级导航只按 01、02、03、04 排列。展示生产技能内部内容时:

  • 使用生产技能原生步骤名和字段名;
  • 可以标注其属于哪个一级阶段,但不得重编成虚构的二级流程;
  • Demo自选的风格说明、资产编号和案例内容必须明确属于示例,不宣称为技能固定结构;
  • 下载结果按01→04排列。

最终检查

  • 是否完整读取并执行了当前生产技能及所需引用
  • 是否保持01→02→03→04
  • 是否用生产技能自己的暂停与确认规则完成阶段内部流程
  • 是否删除所有无法追溯到生产技能原文或用户明确要求的强制项
  • 是否将动态人物情绪只写入04逐镜 表情:
  • 是否只使用“船长AI视界”署名

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Chuanzhang Ai Shijie Workflow AI skill do?

按船长AI视界规定的01→02→03→04顺序,依次调用中文影视创作、真人感人像提示词、静态图像提示词、分镜与人物情绪融合技能。Use when the user asks for 船长AI视界完整流程、从灵感到分镜、一键工作流、按顺序调用全部技能、部署后生成完整内容,或要求不得跳步、不得打乱技能与产出顺序。

Why use Chuanzhang Ai Shijie Workflow on TypingMind?

Because you install it once and use it with any model. Chuanzhang Ai Shijie Workflow is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Chuanzhang Ai Shijie Workflow in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zhangxiansheng-888/chuanzhangAIshijie/tree/main/skills/chuanzhang-ai-shijie-workflow. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Chuanzhang Ai Shijie Workflow?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Chuanzhang Ai Shijie Workflow?

As many as you like. As long as a model supports skills, you can use Chuanzhang Ai Shijie Workflow with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Chuanzhang Ai Shijie Workflow AI skill free?

Yes. It is published on GitHub by zhangxiansheng-888 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇