Single Path Process Diorama logo

Single Path Process Diorama

Organization
ZSeven-W
single-path-process-diorama

将 3–5 步线性流程制作成单张完整、非宫格的微缩剧场成品。适用于流程故事封面、制作过程图、软件交付旅程与科普式微缩场景;以单一路径、可追踪载体、可辨识动作和题材匹配的材质表达顺序。不用于需要精确分支和数据尺度的流程图、实际操作规程或普通城市微缩景观。

Overview

PublisherZSeven-W
Repositorycraft-skills
Skill namesingle-path-process-diorama
Stars
233
Forks
33
Bundled files
16
LicenseApache-2.0
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.

  • 16 bundled files

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

  • Open source

    Published by ZSeven-W on GitHub. Read the source before you install it.

Installation

Install the Single Path Process Diorama 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/ZSeven-W/craft-skills/tree/main/skills/single-path-process-diorama
  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/ZSeven-W/craft-skills.git /tmp/craft-skills
mkdir -p .claude/skills
cp -r /tmp/craft-skills/skills/single-path-process-diorama .claude/skills/single-path-process-diorama
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Single Path Process Diorama 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 Single Path Process Diorama 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 Single Path Process Diorama 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.

单路径流程微缩剧场

把流程变成一个能沿着观看的世界,交付真实图片,不只是提示词。先保证故事可以读,再让材质与光线增添吸引力。

适用边界

  • 适合用户已给定或可以明确约定的 3–5 步线性流程。步数不固定为五步。
  • 有并行、回环、异常路径时,不要偷偷删减;先说明这张图只表现哪条主线。用户需要完整逻辑时改用流程图建议,不冒充精确工程图。
  • 把功能类比与真实机械流程区分开。软件核心被打包可以是比喻;咖啡不能直接从完整豆子流成饮品。
  • 这是带流程语义的艺术图,不承诺看一张无字图就能唯一反推出抽象专业术语。
  • 只使用用户授权参考。不把某一原型的轨道、配色、材质或固定人物作为通用模板。

输入与能力预检

先用最小必要判断决定是否开画,避免为了适配画幅悄悄修改故事:

  • 只有题材、未给流程:可提出一个明确标注为演示的 3–5 步主线,说明关键假设。不把自己补的步骤说成用户确认或行业标准。
  • 超过五步:只有用户允许概括时,才合并相邻子动作;保留原步骤到宏观阶段的完整映射和原顺序。若每步必须独立可见,不擅自删减或硬塞五站,解释限制,提出分成多张完整世界或改用流程图的方案,等用户选择。
  • 必须完整表达分支/回环:说明单路径艺术图无法忠实承载全部逻辑,先给流程图或待确认的单条主线建议;没有授权就不丢弃失败、退款、重试等路径。
  • 用户只要方案或明确禁止生图时,交付方案并标注“未生成、视觉未验证”,不调用生图工具,不制造 final.png。
  • 缺少生图工具:可交付待执行提示词,但明确这是降级交付,不是成品。缺少看图能力时,不自称视觉验收通过;缺少独立审查者时,把自审与独立审查区分记录。

对已经清楚的简单流程直接推进,不把预检变成让用户填写长表。能力和试用入口见 references/runtime.md。

先做一个短契约

在生成前记录这些内容,不要求用户填长表:

  1. 已知流程、宏观步数与阅读方向。
  2. 每步的输入状态 → 唯一主要动作 → 输出状态。
  3. 贯穿载体的识别特征,以及可以合法发生的形态变化。
  4. 一个连续路径如何经过每步,起终点在哪里。
  5. 相邻动作如何区分;哪些道具只是背景、不应被读成额外一步。
  6. 画幅、文字需求、用户约束和本轮生成上限。

未提供流程而只说“试试”时,选一个贴近对话的常识场景,并明确这是选定的演示主线,不是行业唯一标准。

让宏观节点清楚,而不是把画面隔成盒子

  • 每个节点只保留一个主动作。用空间留白、地形转折和不同剪影分开节点,不用框线或独立岛屿。
  • 属于同一阶段的子动作应在同一工作台、建筑或演员组里完成,避免包装、贴标、出库被无意扩成三站。
  • 连接线可以是路、传送带、窄渠、桌面操作带、地形或载体的运动痕迹;不必每次都画橙色 S 形轨道。
  • 路径应可追踪且不形成误读的岔路、死路、自交。只允许短暂遮挡,进出口关系要可见。
  • 起点表现输入,终点表现完成后的用途。终点可以是大主景,但不要再附一个像第六站的独立结局。
  • 静态图可以重复同一载体的不同时间状态,明确这是连续时间的压缩,不是多件不同物品。用颜色、形状或一个纹样保持身份;工艺改变时保留合理的关联,不强迫咖啡粉仍然长成咖啡豆。
  • 相邻动作采用不同证据:自动测试用无人探针,人类审核用两人对照;研磨用豆子进入、粉末出来,冲煮用水经过粉床。
  • 道具与人物可以自然越过区域,保留一张完整世界的设计感。

美术方向服务题材

先确定材质、光线、色谱、尺度和视觉节奏,再形成短提示词。不要把“精致”等同于遍地金属齿轮、发光核心和橙青配色。

可选方向,不是必选模板:

  • 精密工业:玻璃、阳极金属、陶瓷、少量工作灯。
  • 纸木工坊:木纹、纸纤维、陶器、织物与漫射日光。
  • 生活街区:灰泥建筑、纸箱、柏油、植物与自然人物活动。
  • 自然加工:泥土、水、植物和制程中真实可见的材料变化。

主动作附近有细节,连接处安静。人物小不等于不可辨识;避免景深把后半流程全部虚化。需要参考时先观察其材质与空间关系,不照抄具体构图或专属标志。

文字是受控选项

  • 用户要求无字时生成纯净图,交付简短中文流程说明;如专业语义无法唯一辨认,应直说。
  • 用户未要求无字且题材抽象时,可用每站一个 2–4 字的环境路牌,必要时加序号和一个短标题。中文必须与契约逐字一致,标牌数量不能膨胀。
  • 标牌只是确认步骤,不得靠大段文案弥补缺失动作。不能为补字把图拆成宫格。
  • 若生成文字错误,仅针对错字修订并复查整图;文字退回图外说明时要告知用户,不能把错误文字当成最终图。

生成与修订

使用当前环境可用的图像生成工具,整页一次生成。工具或模型参数按实际可用能力设置,不伪造种子确定性、质量等级或图像文件路径。

  • 按“世界与材质 → 路径 → 顺序动作 → 载体变化 → 文字/限制”写提示词。
  • 第一轮默认一张主图;自行质检后至多两次定向修订,除非用户另给预算。
  • 保留旧稿,写清选稿与淘汰原因;修订时锁定没有问题的构图、路径、角色和阶段。
  • 禁止逐站单独生成后拼接。原生文字或环境与主体一体生成;若用户明确要可编辑标注,可另外提供导览文件。
  • 连续两次修订仍有重要语义错误时,报告未达标,不能靠贴“已验证”标签结束。

成品质检

使用 references/qa.md 检查最终文件,不能只审提示词。至少看原尺寸和等比缩略图。

交付前运行零依赖文件验证器:python3 scripts/verify_delivery.py <交付目录> --ratio 3:4 --require-all-docs(画幅按实际约定替换)。若有独立审查 JSON,增加 --review <review.json> 校验其 reviewed_image_sha256 是否指向最终图。这个脚本只检查 PNG 完整性、比例、四件套文档和哈希绑定,输出的 ok 绝不表示画面或流程语义通过。

从“视觉完成度”和“流程忠实度”两轴判断。以下是发布阻断项:

  • 核心工序缺失、倒序或违反约定;
  • 路径断裂或产生误导分支;
  • 载体变化无因果、关键手与物/水与容器关系不成立;
  • 乱码、文字与工序错配、主要人物或物体意外裁断;
  • 实际生成的是宫格拼贴而非完整场景。

专业名词无法无字盲猜不是自动失败;若图只剩装饰、换标题就能解释任意流程,流程忠实度仍然不合格。缩略图应保留路径、宏观节点和主载体,不要求看清所有微型零件。

交付

默认向用户展示最终图片和一句顺序说明。保存:

  • final.png:最终选中的完整成品;
  • prompt.md:实际使用过的生成与修订提示词;
  • scene-contract.md:短契约;
  • qa.md:绑定最终文件哈希的质检,包含未通过与未验证项。

缩略图、替代稿与执行记录放在评测工作区。研究阶段的基线、私人参考账本不随公开 Skill 打包。保存文件不意味着获得发布、上传、安装或推送授权。

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 Single Path Process Diorama AI skill do?

将 3–5 步线性流程制作成单张完整、非宫格的微缩剧场成品。适用于流程故事封面、制作过程图、软件交付旅程与科普式微缩场景;以单一路径、可追踪载体、可辨识动作和题材匹配的材质表达顺序。不用于需要精确分支和数据尺度的流程图、实际操作规程或普通城市微缩景观。

Why use Single Path Process Diorama on TypingMind?

Because you install it once and use it with any model. Single Path Process Diorama 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 Single Path Process Diorama in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ZSeven-W/craft-skills/tree/main/skills/single-path-process-diorama. 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 Single Path Process Diorama?

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 Single Path Process Diorama?

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

Is the Single Path Process Diorama AI skill free?

Yes. It is published on GitHub by ZSeven-W under the Apache-2.0 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 👇