Vertical Slicing logo

Vertical Slicing

Community
Dimon94
vertical-slicing

把大 spec、地图或单张票切成能逐片合入、部署、体验的垂直切片,或审查现有拆票是否垂直。用于用户显式调用 /vertical-slicing 或 $vertical-slicing。

Overview

PublisherDimon94
Repositoryskills
Skill namevertical-slicing
Stars
107
Forks
21
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

    Published by Dimon94 on GitHub. Read the source before you install it.

Installation

Install the Vertical Slicing 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/Dimon94/skills/tree/main/skills/vertical-slicing
  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/Dimon94/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/vertical-slicing .claude/skills/vertical-slicing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vertical Slicing 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 Vertical Slicing 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 Vertical Slicing 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.

Vertical Slicing

本 Skill 只决定切片的形状、顺序、依赖边,以及合入与放量的节奏。拆票流程、征询与发布归 to-tickets;逐票 token 预测归 ticket-sizing,它评估本 Skill 产出的最终切片。依赖 Skill 按当前运行时目录定位;缺失时交付切片清单并注明未发布。

工作方式是 small batches:先上一片 walking skeleton,再一片片加厚。每片合入 main、部署到生产、有人亲手体验,下一片的拆法再按体验修正。合入与部署逐片发生;对外放量按里程碑发生。

词汇

  • 垂直切片:一张票。它穿过实现一个行为所需的各层,交付一个人能从真实入口触发并看到的结果。Avoid:小模块(与 Module 撞名)、子需求、子任务。
  • 业务主线:story map backbone。用户按时间顺序完成的活动序列,每个活动是一个动词短语。所有切片挂在它上面。
  • 核心闭环:产生业务结果所需的最少 backbone 活动。其余活动各自作为加厚片补上。
  • walking skeleton:第一片。只覆盖核心闭环,每个活动只走最简单的一条路径,端到端跑通,可以简陋。
  • 加厚片:在骨架已有的 seam 后补一个变体:路径、规则、数据或界面。
  • 结构片:make the change easy。只改结构、行为不变,服务紧随其后的行为片。
  • 收尾片:删掉隐藏手法留下的第二条路径:toggle、旧 adapter、旧列。
  • 完成:合入 + 部署 + 至少内部可体验。flag 关着、只对内部账号开放也算完成;对外放量按里程碑记录,不阻塞下一片。
  • 波次:依赖图的层。第 1 波是没有入边的片;后一波的片只被更早波次阻塞。同波次并发开发,每片完成即单独合入,不等同波次其他片,也不等里程碑。
  • 里程碑:story map 上的一条 release 切线。它的片全部完成后,打开这批片的 release toggle,让目标用户真正使用,并触发验收、结算等对外节点。里程碑只决定放量,不决定合入。Avoid:阶段合并、批量发布。

Module、Interface、Seam 的定义沿用目标项目的架构词汇;目标项目未定义时按通用含义使用。

切片检查

每片逐项过;任一项答不上来,这片就要重切。

  1. 删除测试:删掉这张票,会有一个人能观察到的结果跟着消失。结构片和收尾片例外,它们分别指向自己服务的行为片和要删掉的路径。
  2. 可独立部署:单独合入 main 就能部署,现有行为保持不变。
  3. small batch:开发加检查目标为数小时到两天,上限一周;分支是 short-lived branch,约两天内合回 main。
  4. INVEST:重点答 Independent、Valuable、Testable。体验结果写成「谁 · 从哪个入口 · 做什么 · 看到什么」。
  5. 一种变更:结构变更和行为变更分开,各占一片。
  6. 隐藏有期限:用了 toggle、dark launch、branch by abstraction 或 expand-contract,就要有对应收尾片。release toggle 的收尾片紧跟所属里程碑的放量。
  7. 挂在主线上:能指出这片加厚的是哪个 backbone 活动。

切分 spec 或地图

  1. 画业务主线。 读输入的验收标准、目标项目术语与相关代码。写一句话业务结果,列 backbone 活动,指定体验人,圈出核心闭环。再标出终点要穿过的 seam:入口、跨 Module 的 Interface、持久状态。完成条件:每个 backbone 活动都有真实入口坐标,或标为 Unknown;核心闭环已圈定;seam 清单可指向代码。

  2. 切 walking skeleton。 核心闭环里的每个活动取最简单的一条路径;硬编码、单一用户、单一数据形态都可以。需要新建或改动的 Interface 尽量集中在骨架里,因为 Interface 后改最贵。骨架超出 small batch 时,先硬编码非核心的一段,仍超出再把核心闭环缩到更短的业务结果。Interface 形状或技术可行性还答不上来时,先切 spike 片,产出答案而非生产代码。完成条件:骨架的体验结果写成一句完整的「谁 · 入口 · 做什么 · 看到什么」,small batch 判断为上限内,并通过切片检查。

  3. 加厚。 核心闭环外的每个 backbone 活动各成一片;每片从骨架的 seam 后补一个变体或一个活动,拆法见 拆法库。先做强制规则和价值最大的路径;拆法优先选能让低价值部分被延后或丢弃的那种。完成条件:输入里每条验收标准都落到某一片,或明确列入「延后」「丢弃」并写理由。

  4. 补结构片与收尾片。 某片需要先加深一个 Module,才能把改动变小,就在它前面放一个结构片。未完成部分合入时需要隐藏,按拆法库的隐藏手法表选手法,并补收尾片。完成条件:每个隐藏手法都有收尾片;每个结构片都点名它服务的行为片。

  5. 连依赖边。 只在两种情况下连阻塞边:后片调用前片新建或改动的 Interface;或者后片依赖前片提供的能力(服务、配置、数据)。两片只改同一 Module 的 Implementation,是合并冲突风险,不是依赖。完成条件:每条边写明它依赖的 Interface 或能力;没有入边的片可以并发开工。

  6. 排波次与里程碑。 按阻塞边给每片标波次号。再沿业务主线画 release 切线:

    • 里程碑 1 是骨架,加上让目标用户第一次能真正使用所需的最少加厚片。缺了会让流程不可用、或会造成资损与数据错误的规则,归进同一里程碑;没有刹车的车不发。
    • 之后每个里程碑只多交付一个对外可感知的业务结果,并配一个自己的 release toggle。
    • release toggle 存活一两周以内,所以里程碑从首片合入到放量也在一两周以内;超出就把它切成两个对外结果。
    • 每个里程碑写明放量对象(灰度或全量的外部目标用户;内部体验已由每片的「完成」覆盖)、验收人与验收结果,以及目标项目约定的对外节点(演示、验收、结算或催款)。

    完成条件:每片有波次号与所属里程碑;每个里程碑都有放量对象、验收人和验收结果;不存在一个 toggle 一直覆盖到最后一片的计划。整份输入只排出一个里程碑时,写明理由。

  7. 交付切片清单。 按波次顺序给出下面两张表,交给 to-tickets 征询与发布,再交 ticket-sizing 估算。完成条件:每片已过切片检查,用户在发布前看到两张表。

片波次里程碑类型backbone 活动体验结果(谁 · 入口 · 做什么 · 看到什么)small batch 判断与依据隐藏手法 / 收尾片阻塞边(依赖的 Interface 或能力)

类型取值:骨架、加厚、结构、收尾、spike。

里程碑包含的片对外业务结果放量对象与动作验收人与验收结果对外节点收尾片

审查现有拆票

单张票:先过切片检查。全部通过就保留原票;超出 small batch,或含多个可独立体验的结果时,把这张票当输入走「切分 spec 或地图」。

多张票:逐票跑切片检查,再看整体:第一片是否是端到端骨架;所有票能否拼回业务主线;依赖边是否都有 Interface 或能力依据;波次与里程碑能否按「排波次与里程碑」排出。

重点信号:按层或按技术组件分票;先建全套基础设施再写功能;单列「联调」「集成」票;小票合入后攒成一次大发布,或按「阶段」攒齐再一起合并;所有 toggle 留到最后一张票才打开或删除;没有 backbone,越切越碎,切到核心时尺寸骤增。

每条 finding 指向具体票号与未过的检查项。重切方案按「切分 spec 或地图」各步完成条件交付两张表。已派发或已被 claim 的票只提建议,不改写。

执行交接

切片发布后,按依赖并发执行与逐票上线交给 delivery-pipeline 的独立票模式(delivery_mode: ticket_release)。ready 只看本票阻塞边,一票一 MR,部署读回后关票。合入授权与部署读回按该模式的 release_stage 规则执行;它的状态止于 deployed。里程碑的放量与对外节点按里程碑表执行,可映射到 tracker 的 milestone。宿主没有 delivery-pipeline 时,按目标项目自己的分支与发布合同逐票合入。

维护验证

修改切片检查、步骤或完成条件时,运行 前向验证案例。研究来源与访问限制见 研究记录。

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 Vertical Slicing AI skill do?

把大 spec、地图或单张票切成能逐片合入、部署、体验的垂直切片,或审查现有拆票是否垂直。用于用户显式调用 /vertical-slicing 或 $vertical-slicing。

Why use Vertical Slicing on TypingMind?

Because you install it once and use it with any model. Vertical Slicing 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 Vertical Slicing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Dimon94/skills/tree/main/skills/vertical-slicing. 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 Vertical Slicing?

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 Vertical Slicing?

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

Is the Vertical Slicing AI skill free?

It is published on GitHub by Dimon94. Check the repository for licensing terms. 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 👇