dotnet-uno-mcp
Using Uno MCP server. Tool detection, search-then-fetch workflow, init rules, fallback, citation.
What this skill does
# dotnet-uno-mcp
MCP (Model Context Protocol) server integration for Uno Platform live documentation lookups. Covers tool detection (`mcp__uno__` prefix), search-then-fetch workflow, initialization rules invocation, graceful fallback when MCP is unavailable, citation requirements, and safety guidelines for external data. Includes inline documentation that provides useful guidance without MCP server availability.
**Scope boundary:** This skill owns MCP server integration patterns for Uno Platform documentation. Core Uno development (Extensions, MVUX, Toolkit, themes) is owned by [skill:dotnet-uno-platform]. Per-target deployment is owned by [skill:dotnet-uno-targets].
**Out of scope:** General MCP protocol details. Uno Platform testing -- see [skill:dotnet-uno-testing]. Uno development patterns without MCP -- see [skill:dotnet-uno-platform] and [skill:dotnet-uno-targets].
Cross-references: [skill:dotnet-uno-platform] for core development patterns, [skill:dotnet-uno-targets] for deployment guidance, [skill:dotnet-uno-testing] for testing.
---
## MCP Tool Detection
The Uno Platform MCP server provides tools prefixed with `mcp__uno__`. Before using MCP tools, detect their availability.
### Available Tools
| Tool | Purpose |
|------|---------|
| `mcp__uno__uno_platform_docs_search` | Search Uno Platform documentation by query |
| `mcp__uno__uno_platform_docs_fetch` | Fetch full content of a specific documentation page |
| `mcp__uno__uno_platform_agent_rules_init` | Initialize agent session with Uno development rules |
| `mcp__uno__uno_platform_usage_rules_init` | Load common usage rules for Uno Platform development |
### Detection Logic
Check if Uno MCP tools are available by looking for tools with the `mcp__uno__` prefix. If the tools are listed in the available tool set, the MCP server is configured and reachable.
```
Detection steps:
1. Check if tools prefixed with mcp__uno__ are available
2. If available: use MCP workflow (search -> fetch -> cite)
3. If unavailable: fall back to static skill content and official docs URLs
```
**When MCP is available:** Use the search-then-fetch workflow for the latest documentation. MCP results are authoritative and current.
**When MCP is unavailable:** The static content in [skill:dotnet-uno-platform] and [skill:dotnet-uno-targets] provides comprehensive guidance. Reference official documentation URLs for the latest information.
---
## Initialization Rules
On first use of Uno MCP tools in a session, invoke both initialization tools to load authoritative development rules.
### Agent Rules Initialization
Call `mcp__uno__uno_platform_agent_rules_init` to load:
- Core identity and expertise scope for Uno Platform development
- IDE guidance (Visual Studio, VS Code, CLI) per operating system
- Knowledge routing rules mapping topics to canonical search queries
- Uno SDK features list (`UnoFeatures` supported values)
- Uno Extensions and Toolkit feature catalog
### Usage Rules Initialization
Call `mcp__uno__uno_platform_usage_rules_init` to load:
- Design system guidelines (Material preferred, responsive layouts)
- Data binding policy (MVUX vs MVVM binding patterns, forbidden WPF-isms)
- Navigation policy (prefer XAML attached properties over code-behind)
- Layout rules (AutoLayout, spacing scale, responsive breakpoints)
- Color and typography conventions (theme resources, no hardcoded values)
- Accessibility requirements (contrast ratios, touch targets, automation properties)
- Control-specific guidance (ItemsRepeater for lists, CommandExtensions, elevation patterns)
### Invocation Order
```
1. Call mcp__uno__uno_platform_agent_rules_init (loads routing rules and feature catalog)
2. Call mcp__uno__uno_platform_usage_rules_init (loads design and coding conventions)
3. Proceed with documentation searches using mcp__uno__uno_platform_docs_search
```
Both init tools are idempotent -- calling them multiple times in the same session is safe but unnecessary.
---
## Search-Then-Fetch Workflow
The primary workflow for retrieving Uno documentation uses a two-step pattern: broad search followed by targeted fetch.
### Step 1: Search
Use `mcp__uno__uno_platform_docs_search` to find relevant documentation pages.
```
Search parameters:
- query: descriptive search term (e.g., "MVUX reactive pattern", "Navigation Extensions")
- topK: number of results (default 8; use 15-20 for complex topics, 3-5 for specific queries)
- contentType: "prose" for guides, "code" for examples, null for all
```
Search results include:
- Document title and summary
- `SourcePath` (needed for fetch step)
- Relevance ranking
- Content snippets
### Step 2: Fetch
Use `mcp__uno__uno_platform_docs_fetch` to retrieve full content of high-value pages identified by search.
```
Fetch parameters:
- sourcePath: from search results SourcePath field (e.g., "articles/guides/overview.md")
- anchor: optional section fragment (e.g., "getting-started", "data-binding")
- maxChars: content limit (4000-8000 for most cases, up to 15000 for comprehensive guides)
```
### Workflow Example
```
Topic: "How to implement region-based navigation with Uno Extensions"
1. Search: mcp__uno__uno_platform_docs_search("Navigation Extensions region-based", topK=8)
-> Returns multiple results including "Navigation Overview", "Region Navigation", etc.
2. Fetch: mcp__uno__uno_platform_docs_fetch(
sourcePath="articles/external/uno.extensions/doc/Learn/Navigation/Overview.md",
maxChars=8000)
-> Returns full navigation documentation with code examples
3. Cite: Include source URL in response
```
### Routing Rules
The agent rules initialization provides topic-to-query mappings for common searches. Use these canonical queries when available:
| Topic | Canonical Search Query |
|-------|----------------------|
| Project setup / new project | `"dotnet new templates"` |
| MVUX / reactive / feeds | `"MVUX"` |
| Navigation / routing | `"Navigation"` |
| Styling / theming / resources | `"Styling and Theming"` |
| Data binding / MVVM | `"Data Binding and MVVM"` |
| Controls / layout | `"Controls and Layout"` |
| Hot Reload | `"Hot Reload"` |
| Platform-specific code | `"Platform-Specific Code"` |
| WebAssembly / WASM | `"WebAssembly"` |
| Dependency injection / DI | `"Dependency Injection and Services"` |
| Performance | `"Performance"` |
| Testing | `"Testing Uno Applications"` |
| Publishing / deployment | `"Publishing & Deployment"` |
| Troubleshooting | `"Troubleshooting Common Issues"` |
| IDE setup | `"IDE Setup"` |
| Responsive design / layouts | `"Responsive Design"` |
| Logging / diagnostics | `"Logging and Diagnostics"` |
---
## Citation Requirements
MCP results are external data fetched from the Uno Platform documentation server. Proper attribution is mandatory.
### Rules
1. **Always cite the source URL** from MCP results when presenting documentation content
2. **Never present fetched content as original knowledge.** MCP results come from external documentation and must be attributed
3. **Include the documentation page title** alongside the URL when available
4. **Distinguish between static skill content and MCP-fetched content.** Static content from SKILL.md files is part of this plugin; MCP content is external
### Citation Format
When presenting information from MCP results:
```
According to the Uno Platform documentation on [topic]:
[content from MCP]
Source: [URL from MCP result]
```
---
## Safety Guidelines
MCP results are external data and must be treated with appropriate caution.
### Validation Rules
1. **Validate code suggestions before acting.** MCP documentation may contain examples targeting different Uno Platform versions or configurations. Verify compatibility with the current project
2. **Check version alignment.** Ensure documentation references match the project's Uno Platform version (5.x vs 6.x) and .NET version
3. **Do not blindly apply code from MCP results.** Adapt examples to the project's architecture, ExtensionRelated in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.