---
title: "zvoove Skills — Maximilian Dahl"
description: "Initiative case by Maximilian Dahl: how workflows built as the only designer became zvoove Skills, the shared AI library for product, design and engineering."
url: https://max.does.systems/en/work/zvoove-skills/
lang: en
---

Start again

Initiative case · AI enablement · Designing with AI · zvoove · staffing software · 2025 – 2026

# My working rules became the team’s AI infrastructure.

As the only designer for several teams, I built myself workflows and skills to keep up. On my own initiative this became zvoove Skills: the shared AI library of Product, Design and Engineering.

Start the story · S · Read the case · R

Role in the project · Initiator · Own initiative, no brief

Setting · AI Steering (Value Builders) · Founding member

Responsibility · Skills and foundation · zvoove Brain, design and PM skills, knowledge base and design system connected, guardrails

Status · Live · +2 · As of September 2026 · Live · Since March 2026: 19 skills at launch, 34 across three departments in August 2026 · In use · Dark Factory with the developers since August 2026, the pipeline belongs to Engineering · Open · Measured internally by tickets done · and 2 more states

S

## The path

1. 01
   Solve my own problem first
   write the way I work down instead of repeating it.
   Starting point
   - What slowed things down
      - Design was brought in too late
      - AI did not fit the system
      - Context got lost
   - The decision
      Instead of explaining the same things every day, I wrote down how I work. At first just for me. Then it turned out others could work with it just as well.

2. 02
   Connect knowledge instead of copying it
   the knowledge base via MCP, improved together with its team.
   MCP
   Knowledge over MCP · Agent · new session · Rebuilt · synthetic data
   1. Which fields does a timesheet export for customers need?
   2. `knowledge-base · search`3 results
      - 1**Timesheet · data model**Entity, 14 fields
      - 2**Export · CSV and PDF**Guideline
      - 3**Persona · dispatcher**Persona
      A customer export needs **9 of the 14 fields**: employee, assignment, date, start, end, breaks, hours, surcharges and approval. Internal cost centres stay out.
      1 · Timesheet · data model · 2 · Export · CSV and PDF · 3 · Persona · dispatcher
   Write a message …
   Connected over MCP
   - **Knowledge Base**Data model, personas, domain terms
   - **UnityUI**Tokens and components
   - **Jira**Tickets and comments
   Rebuilt: an agent queries the Knowledge Base over MCP instead of someone pasting context into every session.

3. 03
   Product managers build for themselves
   PM skills and an AI-ready design system.
   Product
   Until the first customer feedback · simplified, not measured
   Before · Feedback after the build
   _Idea · Idea · The PM's rough thought.__Ticket · Ticket · A ticket without a screen.__Waiting for design · Waiting for design · One designer for several teams: the ticket waits.__Draft · Draft · Design drafts, the PM aligns.__Build · Build · Engineering builds. Only then do customers see anything.__Customer feedback · Customer feedback · Only after the build: changes now mean rework._
   1. Idea · The PM's rough thought.
   2. Ticket · A ticket without a screen.
   3. Waiting for design · One designer for several teams: the ticket waits.
   4. Draft · Design drafts, the PM aligns.
   5. Build · Engineering builds. Only then do customers see anything.
   6. Customer feedback · Only after the build: changes now mean rework.
   With the skills · Feedback before the first ticket
   _Idea · Idea · The PM's rough thought.__Spec → prototype · Spec → prototype · PM skill and prototype skill: the thought becomes a spec, and from it, automatically, a near-live prototype in UnityUI.__Customer feedback · Customer feedback · On a near-live prototype, before a ticket exists._no detour · No detour to the feedback · Ticket, waiting for design, draft and build now come after the first customer feedback, no longer before it.
   1. Idea · The PM's rough thought.
   2. Spec → prototype · PM skill and prototype skill: the thought becomes a spec, and from it, automatically, a near-live prototype in UnityUI.
   3. Customer feedback · On a near-live prototype, before a ticket exists.
   4. No detour to the feedback · Ticket, waiting for design, draft and build now come after the first customer feedback, no longer before it.
   with skills · Waiting · Customer feedback · PM skill · Prototype skill

4. 04
   A chain instead of single prompts
   from idea to handover.
   chain
   The chain · five stations
   01 · Spec
   A sentence, a Figma link or meeting notes become a buildable spec: persona, problem, user stories, acceptance criteria, edge cases.
   - Persona
   - Problem
   - User stories
   - Acceptance criteria
   - Edge cases
   02 · Design refinement
   Every ticket with a user-facing surface gets its design task. It covers flow, error behaviour, states, permissions, copy and translation and stays in sync with the ticket.
   - Flow
   - Error behaviour
   - States
   - Permissions
   - Copy
   - Translation
   03 · Figma to UnityUI
   Spacing, typography, colours and layout come from Figma and are translated into UnityUI code, checked against the design tokens.
   - Spacing
   - Typography
   - Colour
   - Layout
   checked against the design tokens
   04 · Quality gate
   Every component is checked from six angles: code quality, design system compliance, accessibility, security, performance, completeness, with severities from P0 to P3.
   - Code quality
   - Design system fidelity
   - Accessibility
   - Security
   - Performance
   - Completeness
   Severities P0 to P3
   05 · Handover
   A ten-part package with context, architecture decisions, test instructions and a quick start for reviewers.
   - Context
   - Architecture decisions
   - Test guide
   - Reviewer quick start
   ten-part package

5. 05
   No effect without a yes
   every action waits for approval.
   approval
   Claude Code · Example · paraphrased
   1. /pm-ticket “Export timesheets as CSV”
   2. Spec: persona, problem, user stories, acceptance criteria, edge cases
   3. Design task: flow, error behaviour, states, permissions, copy
   4. Create the ticket and comment in the team?

6. 06
   Let go to scale
   a shared structure with reviews and owners.
   team
   From tool to platform
   1. 01 · For me · Workflows and skills to cope as the only designer.
   2. 02 · Connected · Knowledge base via MCP, access improved with its team.
   3. 03 · For product managers · PM skills and the AI-ready design system.
   4. 04 · zvoove Brain · Enablement for the whole company.
   5. 05 · zvoove Skills · Continued within the AI Steering (Value Builders), with reviews and owners.

7. 07
   Supply the material, not the pipeline
   skills and patterns for the Dark Factory.
   agents
   Dark Factory
   **01**Export timesheets as CSV · created with the PM ticket skill
   1. ZVS-1482
      Export timesheets as CSV
      darkfactory · on
   2. Pipeline
   3. Quality gate · P0–P3
      - Code quality
      - Design system compliance
      - Accessibility
      - Security
      - Performance
      - Completeness
   4. Code
      Pull request
      Export timesheets as CSV
      Checks passed
      waits for review from Engineering
   My part
   From zvoove Skills. Engineering owns the pipeline; my part is the material it draws on.
   - PM ticket skill · mine, carried on with the team
   - Design refinement skill · extended for the Dark Factory
   - UnityUI pattern library · being expanded
   Level 5 of 5 · agents implement tickets on their own · In use since August 2026

8. 08
   From 19 to 34 skills
   Today within the AI Steering (Value Builders), with reviews and six owners.
   today
   The library · Repository snapshots
   1. 13 Mar 2026_19 skills · four plugin packages, all by me_19 skills · four plugin packages, all by me
   2. August 2026_**12**by me · Design and PM skills, knowledge and guardrails__**22**by five colleagues · from Product, Design and Engineering_34 skills · Product, Design and Engineering, six owners
   12 by me · 22 by five colleagues
   From the library, a selection
   - design-refinement · Design
   - unity-ui-qa · Design
   - unity-ui-pattern-gen · Design
   - unity-ui-storybook · Design
   - product-spec · Product
   - discovery-to-prototype · Product
   - zvoove-wording-checker · Product
   - user-insights · Product
   - dev-handover · Engineering
   - jira-to-build · Engineering

My working rules became _the team’s AI infrastructure_.

02 · Out of necessity

## One designer for many teams only works with a system

At zvoove Germany I was the only designer, responsible for several teams and products at once. Every team needed design, and I could not be everywhere at the same time.

So I started taking work off my own plate. I had been building my own workflows for AI tools since September 2024; now I wrote workflows and skills that held research, personas, design system rules and constraints, so I no longer had to explain them in every session.

What slowed me down, and later everyone else

1. Design was brought in too late
   Questions about states, errors, permissions and copy only surfaced during implementation.

2. AI did not fit the system
   Output from AI tools ignored UnityUI: hard-coded values, wrong components, crashes.

3. Context got lost
   Personas, domain terms like the German temporary-staffing law and product wording had to be explained again in every session.

4. Design did not scale
   Few designers, many teams: every question waited for a person.

5. No shared rules
   Everyone worked with AI differently, and nobody owned it.

On top of that, product development as a whole was slow. What slowed me down as a lone designer would, over time, slow everyone down.

Context

The decision

Instead of explaining the same things every day, I wrote down how I work. At first just for me. Then it turned out others could work with it just as well.

03 · Connecting knowledge

## Connect knowledge instead of copying it

In parallel, zvoove built a knowledge base from the database records about our products. It was meant to let customer support pull up any data through an AI chat and answer tickets and calls more easily.

I connected it to my workflows through its MCP access. To make that just as easy for others, I worked closely with the team that runs the knowledge base and improved the MCP access together with them.

Knowledge base · one source, three paths

Knowledge base

Product data from the database, reachable via MCP.

MCP

- My workflows
   Connected via the MCP access, improved together with the team.

- Customer support
   AI chat for tickets and calls.

- zAIn
   From proof of concept to the AI layer in the product.

The same knowledge base led to something else. The PM lead, the tech lead and I had the same idea: turn it into an AI assistant for the product. We started an initiative group, built a proof of concept and pushed it internally. It became [zAIn](https://max.does.systems/en/work/zain/) and later the whole AI layer in the product.

Learning

A skill is only as good as the knowledge it is connected to. Improving the access was worth more than any additional prompt.

04 · For product managers

## Product managers build prototypes that feel real

Once my own workflows held up, I started writing skills for product managers: from a rough thought to a structured spec, from a ticket to a design task.

At the same time I brought in the design system. UnityUI is an existing system that I did not create. Separately from the skills, I made it AI-ready from autumn 2025, first with Figma Make, later together with the frontend lead. Since then it works in Figma Make, Claude Design, Claude Code, Codex and Lovable.

Two strands, one result

1. Strand 1
   PM skills
   Specs, tickets and design tasks in the same structure, with personas and domain terms from the shared foundation.

2. Strand 2
   AI-ready design system
   UnityUI with tokens and components that AI tools apply correctly.

3. Result
   Near-live prototypes
   Product managers use them to validate on their own, run discovery and back up tickets and requirements. We work together in Claude Design or Figma Make until I take over the detailing and the states.

Until the first customer feedback · simplified, not measured

Before · Feedback after the build

_Idea · Idea · The PM's rough thought.__Ticket · Ticket · A ticket without a screen.__Waiting for design · Waiting for design · One designer for several teams: the ticket waits.__Draft · Draft · Design drafts, the PM aligns.__Build · Build · Engineering builds. Only then do customers see anything.__Customer feedback · Customer feedback · Only after the build: changes now mean rework._

1. Idea · The PM's rough thought.

2. Ticket · A ticket without a screen.

3. Waiting for design · One designer for several teams: the ticket waits.

4. Draft · Design drafts, the PM aligns.

5. Build · Engineering builds. Only then do customers see anything.

6. Customer feedback · Only after the build: changes now mean rework.

With the skills · Feedback before the first ticket

_Idea · Idea · The PM's rough thought.__Spec → prototype · Spec → prototype · PM skill and prototype skill: the thought becomes a spec, and from it, automatically, a near-live prototype in UnityUI.__Customer feedback · Customer feedback · On a near-live prototype, before a ticket exists._no detour · No detour to the feedback · Ticket, waiting for design, draft and build now come after the first customer feedback, no longer before it.

1. Idea · The PM's rough thought.

2. Spec → prototype · PM skill and prototype skill: the thought becomes a spec, and from it, automatically, a near-live prototype in UnityUI.

3. Customer feedback · On a near-live prototype, before a ticket exists.

4. No detour to the feedback · Ticket, waiting for design, draft and build now come after the first customer feedback, no longer before it.

with skills · Waiting · Customer feedback · PM skill · Prototype skill

Before, the first customer feedback came only after the build: the idea became a ticket without a screen, waited for design, went through draft and alignment, and then into the build. With the skills, product managers get feedback on a near-live prototype, before the first ticket.

### AI Playbook 2.0 Lite

For my PM colleagues I wrote the AI Playbook 2.0 Lite: how to build with Claude, Claude Design and Claude Code, how to plug in skills from the zvoove Skills plugin and what to use for what, with weekly learnings and shared ownership.

Context

The decision

I did not produce more design. I handed out the material that lets others start right on their own.

05 · The chain

## From idea to handover, step by step

Single prompts help one person. An organisation needs a chain in which each step picks up the previous result, checks it and passes it on. On 13 March 2026 it sat in the repository as 19 skills in four plugin packages, all written by me.

The chain · five stations

01 · Spec

A sentence, a Figma link or meeting notes become a buildable spec: persona, problem, user stories, acceptance criteria, edge cases.

- Persona

- Problem

- User stories

- Acceptance criteria

- Edge cases

02 · Design refinement

Every ticket with a user-facing surface gets its design task. It covers flow, error behaviour, states, permissions, copy and translation and stays in sync with the ticket.

- Flow

- Error behaviour

- States

- Permissions

- Copy

- Translation

03 · Figma to UnityUI

Spacing, typography, colours and layout come from Figma and are translated into UnityUI code, checked against the design tokens.

- Spacing

- Typography

- Colour

- Layout

checked against the design tokens

04 · Quality gate

Every component is checked from six angles: code quality, design system compliance, accessibility, security, performance, completeness, with severities from P0 to P3.

- Code quality

- Design system fidelity

- Accessibility

- Security

- Performance

- Completeness

Severities P0 to P3

05 · Handover

A ten-part package with context, architecture decisions, test instructions and a quick start for reviewers.

- Context

- Architecture decisions

- Test guide

- Reviewer quick start

ten-part package

Learning

The strongest skill catches a whole class of errors. The QA skill for UnityUI grew out of real production bugs. Instead of fixing each bug on its own, it checks in eleven phases whether it can happen again, and learns from every new finding.

06 · Guardrails

## No effect without a yes

AI that creates tickets or writes comments needs clear limits. So the same rule applies to every skill: a skill starts on its own when the request fits, but every action with a real effect waits for explicit approval.

Claude Code · Example · paraphrased

1. /pm-ticket “Export timesheets as CSV”

2. Spec: persona, problem, user stories, acceptance criteria, edge cases

3. Design task: flow, error behaviour, states, permissions, copy

4. Create the ticket and comment in the team?

Principles · How the library keeps its quality

1. Approval before effect
   Tickets, comments and messages only happen after a yes.

2. One shared foundation
   Personas, glossary, product wording and AI guardrails live in one central place. Every skill refers to them instead of copying them.

3. Reviews per department
   Changes go through pull requests. Design, product and engineering each review their own area.

4. Automatic checks
   Every skill is validated automatically before it is merged.

On top of that comes the AI Playbook I wrote: general rules for working with AI, with prompting help, direction, mission and vision, and the call to label AI-built work. It is used across the group. In August 2026 the skill catalogue followed, which makes the skills findable for everyone.

07 · Becoming a platform

## My tool became infrastructure

My workflows became zvoove Brain: the idea of tying the company’s knowledge to roles, workflows and processes, so everyone has what they need at hand and nobody has to search. Enablement for the whole company, started without a mandate.

From tool to platform

1. 01 · For me · Workflows and skills to cope as the only designer.

2. 02 · Connected · Knowledge base via MCP, access improved with its team.

3. 03 · For product managers · PM skills and the AI-ready design system.

4. 04 · zvoove Brain · Enablement for the whole company.

5. 05 · zvoove Skills · Continued within the AI Steering (Value Builders), with reviews and owners.

The VP of Engineering founded the AI Steering (Value Builders) to steer AI topics and enablement at zvoove Germany. I am a founding member. That is where zvoove Brain became zvoove Skills. I am responsible for the skills, including all design skills.

The library · Repository snapshots

1. 13 Mar 2026_19 skills · four plugin packages, all by me_19 skills · four plugin packages, all by me

2. August 2026_**12**by me · Design and PM skills, knowledge and guardrails__**22**by five colleagues · from Product, Design and Engineering_34 skills · Product, Design and Engineering, six owners

12 by me · 22 by five colleagues

The most important result is not the number of skills but the owner entries: colleagues from other teams now write and maintain skills of their own. The library is distributed as a plugin marketplace for Claude Code and Cursor.

Context

The decision

I moved the library from my own repository into a shared structure with reviews and owners. The price: I no longer decide everything alone. The gain: it grows without me, too.

08 · Dark Factory

## Automation is only as good as the system it reads

Dark Factory is the level at which agents implement tickets on their own, the fifth level in Dan Shapiro’s public maturity model for AI-assisted coding. At zvoove it started as a pilot in August 2026 and is now in use by the developers. Engineering owns the pipeline.

My part is the material it draws on. A ticket created with my PM ticket skill can be handed to the Dark Factory with “darkfactory on”. To improve its results, I started extending the design refinement skill for it and building out the UnityUI pattern library.

Dark Factory

**01**Export timesheets as CSV · created with the PM ticket skill

1. ZVS-1482
   Export timesheets as CSV
   darkfactory · on

2. Pipeline

3. Quality gate · P0–P3
   - Code quality
   - Design system compliance
   - Accessibility
   - Security
   - Performance
   - Completeness

4. Code
   Pull request
   Export timesheets as CSV
   Checks passed
   waits for review from Engineering

My part

From zvoove Skills. Engineering owns the pipeline; my part is the material it draws on.

- PM ticket skill · mine, carried on with the team

- Design refinement skill · extended for the Dark Factory

- UnityUI pattern library · being expanded

Level 5 of 5 · agents implement tickets on their own · In use since August 2026

Learning

Automation moves work rather than removing it. The fewer people stand between ticket and code, the more precise the rules, patterns and skills have to be.

09 · Outcome

## What came of it

1. Connect knowledge
   Knowledge base connected via MCP, shared foundation
   Stop explaining context in every session

2. Enable product managers
   PM skills and AI-ready UnityUI in five tools
   Prototypes without a detour through design

3. Scale
   34 skills, six owners (August 2026)
   from one person to the organisation

4. Anchor
   AI Steering (Value Builders), reviews per department
   Responsibility beyond me

5. Automate
   Dark Factory in use by the developers
   Implement tickets without manual work

6. What is still open · open
   internally by tickets done
   Measure the effect

Conclusion

I did not introduce AI. I wrote down how we work and connected it so that AI can work by it.

10 · Looking back

## What I learned and would do differently today

### Caveats

1. What is still open
   It is measured internally by tickets done. What is documented is scope, structure and who contributes skills.

2. From the handover on, it is team work
   Since the library moved into the AI Steering group, many people grow it: 22 of the 34 skills come from others.

3. The pipeline is not mine
   Engineering owns the Dark Factory. My share is the material it draws on.

4. I did not create UnityUI
   I made the existing system AI-ready, first on my own, then with the frontend lead.

5. zAIn was a joint initiative
   The PM lead, the tech lead and I had the idea for the assistant together. I started the skills on my own.

6. As of September 2026
   All information reflects that point in time.

### Learnings

1. Where I get stuck, the organisation soon will
   Carrying many teams on your own, you see early where the system jams. What slowed me down would soon have slowed everyone. I solved it before it got there.

2. Knowledge beats prompts
   The biggest leaps came from better access to knowledge, not from better wording.

3. Guardrails create trust
   Because nothing happens without a yes, tasks can be handed to AI without giving up control.

4. Letting go is scaling
   The library has grown since it stopped belonging only to me.

### What I would do differently today

1. Measure from day one
   Before starting, I would record a baseline: how long it takes from ticket to handover and how often design questions come too late. Without it, the effect stays a good story instead of evidence.

2. Look for a frame earlier
   I built on my own for a long time. Reviews and owners came with the AI Steering group. I could have looked for that frame earlier instead of adding it afterwards.

3. Plan for maintenance
   The AI Playbook is used across the group but no longer maintained. Today I would decide from the start who maintains each artefact, the way the skills now have their owners.

4. Start with a few skills and real teams
   Fewer skills, tried earlier with individual teams, would have shown sooner which ones hold up.

> I built it to understand how something like this works. I brought it into the company because a system is only worth something once others work with it.
> 
> Maximilian Dahl

fin (for now)

**Case notes · How to read this case.**

Evidence · Repository snapshots from March and August 2026, Confluence documentation and my own account.

Images · Software screens rebuilt, with synthetic names and data. Diagrams rebuilt, skill contents paraphrased.

Team · AI Steering (Value Builders), engineering (Dark Factory), frontend lead (UnityUI), the knowledge base team, PM lead and tech lead (zAIn initiative).

Rights · zvoove and UnityUI are trademarks of the zvoove Group. This shows my work there; it is not official zvoove communication.

Last updated · As of September 2026
