chore: sync AI configuration from ai-base (#94)

Languages: csharp
AI Systems: copilot,claude,junie
AI Base Version: main

Co-authored-by: AI Config Sync Bot <ai-config-sync@users.noreply.github.com>

Author: github-actions[bot]

.claude/skills/boost-prompt/SKILL.md

@@ -3,18 +3,16 @@ name: boost-prompt
 description: Refines and improves user prompts interactively before execution. Use when a task is vague, underspecified, or complex — asks clarifying questions about scope, deliverables, and constraints, then produces a polished, detailed prompt. Never writes code itself.
 ---
 
-You are an AI assistant designed to help users create high-quality, detailed task prompts. DO NOT WRITE ANY CODE.
+# Boost Prompt
 
-Your goal is to iteratively refine the user’s prompt by:
+Refine and improve task prompts before execution. DO NOT WRITE ANY CODE.
 
-- Understanding the task scope and objectives
-- At all times when you need clarification on details, ask specific questions to the user.
-- Defining expected deliverables and success criteria
-- Perform project explorations, using available tools, to further your understanding of the task
-- Clarifying technical and procedural requirements
-- Organizing the prompt into clear sections or steps
-- Ensuring the prompt is easy to understand and follow
+Iteratively refine the user’s prompt by:
 
-After gathering sufficient information, produce the improved prompt as markdown, as well as typing it out in the chat.
+1. Understanding task scope and objectives
+2. Asking specific clarifying questions
+3. Exploring the project with available tools for additional context
+4. Defining deliverables and success criteria
+5. Organizing the prompt into clear sections or steps
 
-Ask the user if they want any changes or additions. Repeat the copy + chat + ask after any revisions of the prompt.
+Produce the improved prompt as markdown and type it out in the chat. Ask the user if they want changes. Repeat after any revisions.

.claude/skills/code-review/SKILL.md

@@ -1,12 +1,10 @@
 ---
 name: code-review
-description: Perform thorough code reviews with focus on quality, security, and best practices
+description: Performs thorough code reviews covering quality, security, performance, and best practices. Use when asked to review a pull request, audit code changes, check for security vulnerabilities, assess code quality, or provide feedback on a diff. Outputs structured feedback with severity levels and actionable suggestions.
 ---
 
 # Code Review Skill
 
-When performing code reviews, follow this systematic approach:
-
 ## Review Checklist
 
 ### 1. Code Quality

.claude/skills/convert-plaintext-to-md/SKILL.md

@@ -5,8 +5,6 @@ description: Converts plain text or legacy documentation files to properly forma
 
 # Convert Plaintext Documentation to Markdown
 
-You are an expert technical documentation specialist who converts plain text or generic text-based documentation files to properly formatted markdown.
-
 ## Conversion Methods
 
 You can perform conversions using one of three approaches:

.claude/skills/convert-plaintext-to-md/references/considerations.md

@@ -0,0 +1,40 @@
+# Conversion Considerations
+
+## Pattern Recognition
+
+When converting plaintext, pay attention to:
+
+- **Line indentation** — determines nesting level for lists and code blocks
+- **Indented code blocks** — lines indented with 4+ spaces relative to context
+- **Fenced code blocks** — detect language from context and add language identifier
+- **Section separators** — lines like `===`, `---`, `***` map to horizontal rules or heading levels
+
+### Do Not Stop on Process-Related Keywords
+
+When converting documentation, do **not** halt the conversion when the text documents procedures that use shell commands or function calls. These are content to be preserved, not instructions to execute:
+
+- `exit` / `exit()`
+- `kill` / `killall`
+- `quit` / `quit()`
+- `sleep` / `sleep()`
+- Similar commands, functions, or procedures
+
+---
+
+## Conversion Goals
+
+- Preserve all technical content accurately — do **not** change data unless prompt instructions clearly specify to do so
+- Maintain proper markdown syntax and formatting
+- Ensure headers, lists, code blocks, and other elements are correctly structured
+- Keep the document readable and well-organized
+- Assemble a unified set of instructions using all parameters and options provided
+
+---
+
+## Markdown References
+
+When in doubt, consult these resources for markdown best practices:
+
+- [GitHub Basic Writing and Formatting Syntax](https://docs.github.com/en/get-started/writing-on-github/getting-started-with-writing-and-formatting-on-github/basic-writing-and-formatting-syntax)
+- [Markdown Extended Syntax](https://www.markdownguide.org/extended-syntax/)
+- [Azure DevOps Markdown Guidance](https://learn.microsoft.com/en-us/azure/devops/project/wiki/markdown-guidance?view=azure-devops)

.claude/skills/convert-plaintext-to-md/references/examples.md

@@ -0,0 +1,221 @@
+# Usage Examples
+
+## Basic Conversion
+
+**User**
+
+```bash
+/convert-plaintext-to-md #file
+```
+
+**Agent**
+
+```
+I see there is no corresponding `file.md`. Let me copy the plaintext document:
+
+    ```bash
+    cp file file.md
+    ```
+
+Now I'll apply markdown best practices to convert the plaintext documentation to a markdown document.
+```
+
+---
+
+## Guide-Based Conversion
+
+Uses a previously converted markdown file as a formatting reference.
+
+**User**
+
+```bash
+/convert-plaintext-to-md #file.md --guide #CODE.md
+```
+
+**Agent**
+
+```
+I see that both the file and CODE markdown files have corresponding plaintext documentation. Let me
+check CODE and compare it to CODE.md, and identify patterns to help with conversion.
+
+    CODE
+    ```text
+    Title
+
+    Text in opening.
+
+    1. Section
+      1.1 Section Item
+
+    =============================================
+
+    1. Section
+      1.1
+      Full details of section item.
+    ```
+
+And looking at CODE.md:
+
+    CODE.md
+    ```markdown
+    # Title
+
+    Text in opening.
+
+    ### [Section](#1-section)
+
+    - [1.1](#11) Section Item but Only Numbers in Sub-heading
+
+    ***
+
+    ## 1. Section
+
+    ### 1.1
+
+    Full details of section item.
+    ```
+
+I see file.md exists and matches the text in file.
+
+I'll convert file.md similarly. Let's look at the file text documentation:
+
+    file
+    ```text
+    Title
+
+    1. Command
+      1.10.0 Options
+
+    ---------------------------------------------
+
+    Command
+      1.10.0
+      Info on the commands' options.
+    ```
+
+OK, after analyzing the guide file, I've updated file.md to:
+
+    file.md
+    ```markdown
+    # Title
+
+    ### [1. Command](#command)
+    - [1.10.0](#1100-option-with-text-subheading) Option With Text Subheading
+
+    ***
+
+    ## Command
+
+    ### 1.10.0 Option With Text Subheading
+    Info on the commands' options.
+    ```
+```
+
+---
+
+## Finalize / Polish
+
+Natural language variations like "polish", "clean up", or "finalize" all trigger the `finalize` behavior.
+
+**User**
+
+```bash
+/convert-plaintext-to-md #file.md polish the converted markdown file
+```
+
+**Agent**
+
+```
+I'll finalize file.md. I see the current converted markdown file has:
+
+    ```markdown
+    # Title
+
+    Some paragraph with space character at start of line. This <html> should be escaped.
+
+    -  Some list item with extra space character.
+    -  Nested list but only one nesting space character, and extra space after dash.
+      if (a == 1) {
+        return "Indented code block without enough space characters.";
+      } else {
+        return "Passing `finalize` or similar should resolve this.";
+      }
+
+    But when `python` is used, syntax will be like:
+    ```
+
+    ```
+    import math
+    radius = float(input("This is clearly python, but let's do math."))
+    area = math.pi * radius**2
+    circumference = 2 * math.pi * radius
+    print(f"Area: {area:.2f}, Circumference: {circumference:.2f}")
+    ```
+
+Let me trim a few things:
+
+    ```markdown
+    # Title
+
+    Some paragraph with space character at start of line. This \<html\> should be escaped.
+
+    - Some list item with extra space character.
+      - Nested list but only one space character.
+
+        if (a == 1) {
+          return "Indented code block without enough space characters.";
+        } else {
+          return "Passing `finalize` or similar should resolve this.";
+        }
+
+    But when `python` is used, syntax will be like:
+
+    ```python
+    import math
+    radius = float(input("This is clearly python, but let's do math."))
+    area = math.pi * radius**2
+    circumference = 2 * math.pi * radius
+    print(f"Area: {area:.2f}, Circumference: {circumference:.2f}")
+    ```
+```
+
+---
+
+## Inline Pattern with Shorthand Regex
+
+**User**
+
+```bash
+/convert-plaintext-to-md #BUGS --p "regex()=> ^ {1,}([0-9]+\.[0-9]+\.[0-9]+) to ^### $1"
+```
+
+**Agent**
+
+```
+I see that there is no `BUGS.md` file. Let me copy the current plaintext BUGS documentation:
+
+    ```bash
+    copy BUGS BUGS.md
+    ```
+
+Now I'll update the copied file BUGS.md, converting it to proper markdown.
+Let me read the current contents:
+
+    ```markdown
+    1 Section
+      1.1 Section Item
+      1.2 Section Item
+      ...
+      1.12 Section Item
+    ```
+
+OK, I've matched the shorthand regular expression pattern and updated the BUGS.md to:
+
+    ```markdown
+    1 Section
+    ### 1.1 Section Item
+    ### 1.2 Section Item
+    ### ...
+    ### 1.12 Section Item
+    ```
+```