Metalama framework development. Use when working on Metalama itself - aspect testing, test directives, code model, templates, diagnostics.
/plugin marketplace add postsharp/PostSharp.Engineering.AISkills/plugin install metalama-dev@postsharp-engineeringThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Guide for developing the Metalama framework itself.
Note: For writing aspects, templates, and using Metalama APIs, use the metalama skill (installed separately). This skill is specifically for developing the Metalama framework code.
| Type | Description | Project suffix | Output |
|---|---|---|---|
| Aspect tests | Snapshot-based, runs through Metalama pipeline | *AspectTests | Foo.t.cs |
| Unit tests | Classic xUnit | *UnitTests | - |
| Standalone tests | Self-contained projects | - | Optional test.json |
Aspect tests support: code transformations, diagnostics, code fixes, live templates, design-time code generation, diff preview. Can execute Program.Main and compare output.
Docs: Aspect testing
For test directive documentation, use the metalama skill which has complete reference for all @ directives and metalamaTests.json options.
Quick reference: Metalama.Testing.AspectTesting/TestOptions.cs contains all options with XML documentation.
| Path | Contents |
|---|---|
%TEMP%\Metalama\CompileTimeTroubleshooting\ | Build error details |
Metalama.Testing.AspectTesting/TestOptions.cs | Test options documentation |
../Metalama.Documentation/content | Conceptual documentation |
%TEMP%\Metalama\CompileTimeTroubleshooting\...\errors.txt for actual errors.csproj → .targets → Engine code../Metalama.Documentation/content for affected articlesThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.