Plan Ui Change logo

Plan Ui Change

OrganizationPopular
dotnet
plan-ui-change

Plan complex Blazor UI features by decomposing them into focused components. USE FOR: building a complex Blazor page with multiple sections, planning component decomposition, designing a multi-section dashboard or layout, breaking down a large UI feature into composable components, pages with sidebars and content panels, any page with 3+ distinct visual sections or multiple interacting sub-features, identifying parent-child relationships and data flow. DO NOT USE FOR: creating new Blazor projects or apps from scratch (use create-blazor-project), implementing a single individual component (use author-component), writing component code with parameters and EventCallback (use author-component), or simple single-component pages.

Overview

Publisherdotnet
Repositoryskills
Skill nameplan-ui-change
Stars
5.4K
Forks
416
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Plan Ui Change 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.
  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/dotnet/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/plugins/dotnet-blazor/skills/plan-ui-change .claude/skills/plan-ui-change
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Plan Ui Change 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 Plan Ui Change 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 Plan Ui Change 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.

Plan a Blazor UI Change

When asked to build a complex UI feature, plan the component decomposition first, then immediately implement it. A single monolithic page component is almost never the right answer — break the UI into focused, composable components.

Planning Workflow

Step 1 — Map the Visual Regions

Read the request and identify every distinct visual region. Each region that has its own data, behavior, or layout responsibility is a candidate component.

Draw the component tree:

InventoryDashboard          (page — owns data, orchestrates layout)
├── StockSummaryBar         (read-only stats: total items, low-stock count, value)
├── InventoryFilters        (search box, category dropdown, stock-level toggle)
├── InventoryTable          (sortable table of products)
│   └── InventoryRow        (single product row with inline edit/delete)
└── AddProductForm          (slide-out form for new products)

Rules for identifying components:

  • Distinct responsibility — a region owns its own state or behavior → separate component
  • Repeated structure — items in a list, cards in a grid → extract the item template
  • Independent interactivity — a section that handles user input separately from its siblings → separate component
  • Size — any section that would exceed ~150 lines of markup on its own → split it

Step 2 — Classify Each Component

For every component in the tree, determine:

ComponentActionRender ModeState OwnedLines (est.)
InventoryDashboardCreateInteractiveServerproduct list, filter state~80
StockSummaryBarCreate(inherits)none — receives data~30
InventoryFiltersCreate(inherits)search text, selected category~60
InventoryTableCreate(inherits)sort column, sort direction~50
InventoryRowCreate(inherits)inline-edit mode flag~60
AddProductFormCreate(inherits)form model~80

A page component that exceeds ~200 lines of combined markup + code is too large. If your estimate puts a single component above that, split further.

Step 3 — Design Data Flow

Identify the state owner for each piece of data, then map how it flows:

InventoryDashboard (owns: products[], filters)
  ├─ [Parameter] products ──→ StockSummaryBar (reads aggregate stats)
  ├─ [Parameter] filters ──→ InventoryFilters
  │   └─ EventCallback<Filters> OnFiltersChanged ──→ InventoryDashboard
  ├─ [Parameter] filteredProducts ──→ InventoryTable
  │   └─ [Parameter] product ──→ InventoryRow
  │       ├─ EventCallback<Product> OnSave ──→ InventoryTable ──→ InventoryDashboard
  │       └─ EventCallback<Product> OnDelete ──→ InventoryTable ──→ InventoryDashboard
  └─ EventCallback<Product> OnProductAdded ←── AddProductForm

Rules:

  • Data always flows down through [Parameter]
  • Events always flow up through EventCallback<T>
  • The page/parent owns the data and passes filtered/transformed views to children
  • Children never mutate parameters — they notify the parent via callbacks
  • If data must cross more than 2 levels without intermediate components needing it, use a cascading value or a scoped service

Step 4 — Identify Reuse Opportunities

Before creating a new component, check if an existing component in the project can serve the purpose. Look for:

  • Existing list-item components that match the structure
  • Shared filter/search components already in the project
  • Generic components (e.g., DataTable<T>, Pagination) that accept templates

If a component will be used in more than one page, place it in a Shared/ or Components/ folder.

Step 5 — Order the Implementation

Build bottom-up — leaf components first, then parents that compose them:

  1. Models/DTOs — define the data shapes
  2. Services — data access, business logic (interface + implementation)
  3. Leaf components — components with no children (InventoryRow, StockSummaryBar)
  4. Container components — components that compose leaves (InventoryTable, InventoryFilters)
  5. Page component — wires everything together, registers routes
  6. Configuration — DI registration, render mode setup

Each component should be independently compilable. Never reference a component that doesn't exist yet.

Output Format

Present the plan briefly, then immediately proceed to implement — never stop at just the plan or ask for confirmation before writing code. The plan is a thinking tool, not a deliverable.

markdown
## Component Plan: [Feature Name]

### Component Tree
[ASCII tree showing parent-child relationships]

### Component Table
| Component | Action | Render Mode | Purpose | Est. Lines |
|-----------|--------|-------------|---------|------------|
| ... | ... | ... | ... | ... |

### Data Flow
[State owner] → [Parameters down] → [EventCallbacks up]

### Implementation Order
1. [First file to create — why]
2. [Second file — why]
...

After outputting the plan, immediately begin implementing the components in the order listed. Do not wait for approval or ask "shall I proceed?" — the plan is a guide for you to follow, not a proposal for the user to approve.

Anti-Patterns to Avoid

Anti-PatternWhy It's WrongCorrect Approach
One page component with 500+ linesImpossible to test, reuse, or maintainDecompose into focused components
Passing 10+ parameters through intermediate componentsParameter drilling obscures intentUse cascading values or a scoped state service
Child component fetching its own data from an APIMultiple components making redundant callsParent owns data, passes via parameters
Inline rendering of list items with complex markupDuplicated logic, no reuse, hard to testExtract item template into its own component
Building everything in one file then "refactoring later"Refactoring rarely happens; the monolith shipsPlan the decomposition upfront
Generic components for one-off usageOver-engineering adds complexityOnly extract generics when reuse is proven

Guidelines

  • Plan briefly, then implement. Write a concise component table and data flow map, then immediately create the .razor files — never stop at just the plan.
  • Prefer many small components over one large one. A component with a single clear purpose is easier to understand, test, and reuse.
  • State ownership is the first decision. Before writing fetch logic, decide which component owns the data.
  • Build bottom-up. Create leaf components first so parent components can reference them immediately.
  • Name components after what they render, not what they do internally: ProductCard not ProductRenderer, OrderFilters not FilterHandler.

Frequently asked questions

What does the Plan Ui Change AI skill do?

Plan complex Blazor UI features by decomposing them into focused components. USE FOR: building a complex Blazor page with multiple sections, planning component decomposition, designing a multi-section dashboard or layout, breaking down a large UI feature into composable components, pages with sidebars and content panels, any page with 3+ distinct visual sections or multiple interacting sub-features, identifying parent-child relationships and data flow. DO NOT USE FOR: creating new Blazor projects or apps from scratch (use create-blazor-project), implementing a single individual component (u...

Why use Plan Ui Change on TypingMind?

Because you install it once and use it with any model. Plan Ui Change 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 Plan Ui Change in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dotnet/skills/tree/main/plugins/dotnet-blazor/skills/plan-ui-change. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Plan Ui Change?

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 Plan Ui Change?

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

Is the Plan Ui Change AI skill free?

Yes. It is published on GitHub by dotnet 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 👇