sjnims · sjnims · Jan 25, 2026 · Jan 25, 2026 · Jan 25, 2026 · Jan 25, 2026
@@ -6,13 +6,13 @@
   },
   "metadata": {
     "description": "Unofficial plugin-dev plugin marketplace for plugin-dev Claude Code plugin - the plugin itself was initially created by Daisy Hollman at Anthropic.",
-    "version": "0.3.1"
+    "version": "0.3.2"
   },
   "plugins": [
     {
       "name": "plugin-dev",
       "description": "Comprehensive toolkit for developing Claude Code plugins. Includes 9 expert skills covering hooks, MCP integration, LSP servers, commands, agents, marketplaces, and best practices. AI-assisted plugin creation and validation.",
-      "version": "0.3.1",
+      "version": "0.3.2",
       "author": {
         "name": "Daisy Hollman",
         "url": "https://github.com/anthropics/claude-code/",

@@ -0,0 +1,4 @@
+# MCP integration docs use mcp__plugin_*__* patterns that prettier
+# incorrectly converts __ to ** (treating as emphasis)
+plugins/plugin-dev/skills/mcp-integration/SKILL.md
+plugins/plugin-dev/skills/mcp-integration/references/tool-usage.md
@@ -7,6 +7,19 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.3.2] - 2026-01-24
+
+### Fixed
+
+- **Restore MCP tool naming patterns** - Fixed `mcp__plugin_*__*` patterns in mcp-integration docs that prettier corrupted to `mcp**plugin_*__*`; added .prettierignore to prevent recurrence
+
+### Documentation
+
+- **Expand LSP integration skill** - Aligned with official Claude Code docs for comprehensive LSP server guidance
+- **Optimize agent-development skill** - Trimmed SKILL.md to target word count for faster loading
+- **Align tools/allowed-tools format** - Updated documentation to match official Claude Code docs terminology
+- **Update CI/CD workflow documentation** - Fixed workflow list in docs/ci-cd.md (added yaml-lint.yml, removed non-existent weekly-maintenance.yml)
+
 ## [0.3.1] - 2026-01-24
 
 ### Fixed
@@ -219,7 +232,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Based on original plugin by Daisy Hollman at Anthropic
 - Expanded with enhanced skills, additional utilities, and CI/CD infrastructure
 
-[Unreleased]: https://github.com/sjnims/plugin-dev/compare/v0.3.1...HEAD
+[Unreleased]: https://github.com/sjnims/plugin-dev/compare/v0.3.2...HEAD
+[0.3.2]: https://github.com/sjnims/plugin-dev/compare/v0.3.1...v0.3.2
 [0.3.1]: https://github.com/sjnims/plugin-dev/compare/v0.3.0...v0.3.1
 [0.3.0]: https://github.com/sjnims/plugin-dev/compare/v0.2.1...v0.3.0
 [0.2.1]: https://github.com/sjnims/plugin-dev/compare/v0.2.0...v0.2.1

@@ -6,7 +6,7 @@ Guidance for Claude Code working in this repository.
 
 Plugin marketplace containing the **plugin-dev** plugin - a toolkit for developing Claude Code plugins. Provides 9 skills, 3 agents, 3 slash commands.
 
-**Version**: v0.3.1 | [CHANGELOG.md](CHANGELOG.md)
+**Version**: v0.3.2 | [CHANGELOG.md](CHANGELOG.md)
 
 ## MCP Tool Requirements (CRITICAL)
 

@@ -11,6 +11,7 @@ Documentation for GitHub Actions workflows, labels, and templates.
 | `component-validation.yml` | Plugin components changed      | Validate plugin components |
 | `version-check.yml`        | Version files changed          | Ensure version consistency |
 | `validate-workflows.yml`   | `.github/workflows/**` changed | Lint GitHub Actions        |
+| `yaml-lint.yml`            | `.github/workflows/**` changed | Lint YAML files            |
 | `claude-pr-review.yml`     | All PRs (non-draft)            | AI-powered code review     |
 
 ## Other Workflows
@@ -19,7 +20,6 @@ Documentation for GitHub Actions workflows, labels, and templates.
 - `stale.yml` - Manages stale issues/PRs (Mon/Wed/Fri)
 - `semantic-labeler.yml` - Auto-labels issues/PRs
 - `ci-failure-analysis.yml` - Analyzes CI failures
-- `weekly-maintenance.yml` - Scheduled maintenance tasks
 - `sync-labels.yml` - Synchronizes repository labels
 - `greet.yml` - Greets new contributors
 

@@ -1,6 +1,6 @@
 {
   "name": "plugin-dev",
-  "version": "0.3.1",
+  "version": "0.3.2",
   "description": "Comprehensive toolkit for developing Claude Code plugins. Includes 9 expert skills covering hooks, MCP integration, LSP servers, commands, agents, marketplaces, and best practices. AI-assisted plugin creation and validation.",
   "author": {
     "name": "Daisy Hollman",

@@ -80,17 +80,13 @@ For complete format with all options, see [Agent File Structure](#agent-file-str
 - Action should not happen automatically
 - Workflow requires user confirmation at each step
 
-For command development guidance, see the `command-development` skill.
-
 ### Choose Skills When
 
 - Providing knowledge or procedural guidance
 - Extending Claude's domain expertise
 - No autonomous execution needed
 - Information should be available contextually on-demand
 
-For skill development guidance, see the `skill-development` skill.
-
 ## Agent File Structure
 
 ### Complete Format
@@ -293,68 +289,41 @@ permissionMode: acceptEdits
 
 **Security note:** Use restrictive modes (`plan`, `acceptEdits`) for untrusted agents. `bypassPermissions` should only be used for fully trusted agents.
 
-## System Prompt Design
-
-The markdown body becomes the agent's system prompt. Write in second person, addressing the agent directly.
-
-### Structure
-
-**Standard template:**
-
-```markdown
-You are [role] specializing in [domain].
-
-**Your Core Responsibilities:**
-
-1. [Primary responsibility]
-2. [Secondary responsibility]
-3. [Additional responsibilities...]
-
-**Analysis Process:**
-
-1. [Step one]
-2. [Step two]
-3. [Step three]
-   [...]
+### Fields NOT Available for Agents
 
-**Quality Standards:**
+Some frontmatter fields are specific to skills and do not apply to agents:
 
-- [Standard 1]
-- [Standard 2]
+| Skill-Only Field           | Purpose                                | Why Not for Agents                                      |
+| -------------------------- | -------------------------------------- | ------------------------------------------------------- |
+| `context: fork`            | Run skill in separate subagent context | Agents already run as subprocesses by design            |
+| `agent`                    | Specify agent type for forked context  | Only applies when `context: fork` is set                |
+| `user-invocable`           | Control slash menu visibility          | Agents aren't invoked via slash commands                |
+| `disable-model-invocation` | Block programmatic Skill tool usage    | Agents use Task tool, not Skill tool                    |
+| `allowed-tools`            | Restrict tool access (skill syntax)    | Agents use `tools` field instead (different field name) |
 
-**Output Format:**
-Provide results in this format:
+**Key distinction:** Skills provide knowledge and guidance that loads into context. Agents are autonomous subprocesses that execute independently. This architectural difference explains why context-forking options don't apply to agents—they're already isolated processes.
 
-- [What to include]
-- [How to structure]
+## System Prompt Design
 
-**Edge Cases:**
-Handle these situations:
+The markdown body becomes the agent's system prompt. Write in second person, addressing the agent directly.
 
-- [Edge case 1]: [How to handle]
-- [Edge case 2]: [How to handle]
-```
+**Key elements:**
 
-### Best Practices
+- Role definition ("You are [role] specializing in [domain]")
+- Core responsibilities (numbered list)
+- Process steps (concrete, actionable)
+- Quality standards (measurable criteria)
+- Output format (specific structure)
+- Edge cases (how to handle exceptions)
 
-✅ **DO:**
+**Best practices:**
 
 - Write in second person ("You are...", "You will...")
-- Be specific about responsibilities
-- Provide step-by-step process
-- Define output format
-- Include quality standards
-- Address edge cases
+- Be specific, not vague
 - Keep under 10,000 characters
+- Include concrete steps, not generic instructions
 
-❌ **DON'T:**
-
-- Write in first person ("I am...", "I will...")
-- Be vague or generic
-- Omit process steps
-- Leave output format undefined
-- Skip quality guidance
-- Ignore error cases
+For detailed templates and patterns (Analysis, Generation, Validation, Orchestration agents), see `references/system-prompt-design.md`.
 
 ## Creating Agents
 
@@ -441,6 +410,16 @@ plugin-name/
 
 All `.md` files in `agents/` are auto-discovered.
 
+### Portable Paths
+
+When referencing files within your plugin (scripts, references, etc.) from agent system prompts, use `${CLAUDE_PLUGIN_ROOT}` for portable paths:
+
+```markdown
+Run the validation script at `${CLAUDE_PLUGIN_ROOT}/scripts/validate.sh`
+```
+
+This variable resolves to the plugin's installation directory at runtime, ensuring paths work regardless of where the plugin is installed.
+
 ### Namespacing
 
 Agents are namespaced automatically:
@@ -489,26 +468,6 @@ Ensure system prompt is complete:
 
 ## Quick Reference
 
-### Minimal Agent
-
-```markdown
----
-name: simple-agent
-description: Use this agent when... Examples: <example>...</example>
-model: inherit
-color: blue
----
-
-You are an agent that [does X].
-
-Process:
-
-1. [Step 1]
-2. [Step 2]
-
-Output: [What to provide]
-```
-
 ### Frontmatter Fields Summary
 
 | Field          | Required | Format                     | Example                  |
@@ -567,19 +526,3 @@ Development tools in `scripts/`:
 - **`create-agent-skeleton.sh`** - Generate new agent file from template
 - **`validate-agent.sh`** - Validate agent file structure
 - **`test-agent-trigger.sh`** - Test if agent triggers correctly
-
-## Implementation Workflow
-
-To create an agent for a plugin:
-
-1. Define agent purpose and triggering conditions
-2. Choose creation method (AI-assisted or manual)
-3. Create agent file using skeleton: `./skills/agent-development/scripts/create-agent-skeleton.sh agent-name agents/`
-4. Write frontmatter with all required fields
-5. Write system prompt following best practices
-6. Include 2-4 triggering examples in description
-7. Validate with `./skills/agent-development/scripts/validate-agent.sh agents/your-agent.md`
-8. Test triggering with real scenarios
-9. Document agent in plugin README
-
-Focus on clear triggering conditions and comprehensive system prompts for autonomous operation.
@@ -47,7 +47,7 @@ name: [identifier from JSON]
 description: [whenToUse from JSON]
 model: inherit
 color: [choose: blue/cyan/green/yellow/magenta/red]
-tools: ["Read", "Write", "Grep"] # Optional: restrict tools
+tools: Read, Write, Grep # Optional: restrict tools
 ---
 
 [systemPrompt from JSON]
@@ -101,7 +101,7 @@ Explicit review request triggers the agent.
 
 model: inherit
 color: blue
-tools: ["Read", "Grep", "Glob"]
+tools: Read, Grep, Glob
 ---
 
 You are an expert code quality reviewer specializing in identifying issues in software implementations.

@@ -43,7 +43,7 @@ assistant: "I'll use the code-reviewer agent to validate the changes."
 
 model: inherit
 color: blue
-tools: ["Read", "Grep", "Glob"]
+tools: Read, Grep, Glob
 ---
 
 You are an expert code quality reviewer specializing in identifying issues, security vulnerabilities, and opportunities for improvement in software implementations.
@@ -152,7 +152,7 @@ Direct test generation request triggers the agent.
 
 model: inherit
 color: green
-tools: ["Read", "Write", "Grep", "Bash"]
+tools: Read, Write, Grep, Bash
 ---
 
 You are an expert test engineer specializing in creating comprehensive, maintainable unit tests that ensure code correctness and reliability.
@@ -214,7 +214,6 @@ describe('[module name]', () => {
   // More tests...
 })
 ```
-````
 
 **Edge Cases:**
 
@@ -223,7 +222,6 @@ describe('[module name]', () => {
 - Unclear behavior: Add tests for observable behavior, note uncertainties
 - Complex mocking: Prefer integration tests or minimal mocking
 - Untestable code: Suggest refactoring for testability
-
 ````
 
 ## Example 3: Documentation Generator
@@ -256,18 +254,20 @@ Explicit documentation request triggers the agent.
 
 model: inherit
 color: cyan
-tools: ["Read", "Write", "Grep", "Glob"]
+tools: Read, Write, Grep, Glob
 ---
 
 You are an expert technical writer specializing in creating clear, comprehensive documentation for software projects.
 
 **Your Core Responsibilities:**
+
 1. Generate accurate, clear documentation from code
 2. Follow project documentation standards
 3. Include examples and usage patterns
 4. Ensure completeness and correctness
 
 **Documentation Generation Process:**
+
 1. **Analyze Code**: Read implementation to understand:
    - Public interfaces and APIs
    - Parameters and return values
@@ -288,6 +288,7 @@ You are an expert technical writer specializing in creating clear, comprehensive
 5. **Validate**: Ensure accuracy and completeness
 
 **Quality Standards:**
+
 - Documentation matches actual code behavior
 - Examples are runnable and correct
 - All public APIs documented
@@ -296,6 +297,7 @@ You are an expert technical writer specializing in creating clear, comprehensive
 
 **Output Format:**
 Create documentation in project's standard format:
+
 - Function/method signatures
 - Description of behavior
 - Parameters with types and descriptions
@@ -305,11 +307,12 @@ Create documentation in project's standard format:
 - Notes or warnings if applicable
 
 **Edge Cases:**
+
 - Private/internal code: Document only if requested
 - Complex APIs: Break into sections, provide multiple examples
 - Deprecated code: Mark as deprecated with migration guide
 - Unclear behavior: Document observable behavior, note assumptions
-````
+```
 
 ## Example 4: Security Analyzer
 
@@ -341,7 +344,7 @@ Explicit security review request triggers the agent.
 
 model: inherit
 color: red
-tools: ["Read", "Grep", "Glob"]
+tools: Read, Grep, Glob
 ---
 
 You are an expert security analyst specializing in identifying vulnerabilities and security issues in software implementations.
@@ -429,9 +432,9 @@ Take these templates and customize:
 
 Restrict or expand based on agent needs:
 
-- **Read-only agents**: `["Read", "Grep", "Glob"]`
-- **Generator agents**: `["Read", "Write", "Grep"]`
-- **Executor agents**: `["Read", "Write", "Bash", "Grep"]`
+- **Read-only agents**: `Read, Grep, Glob`
+- **Generator agents**: `Read, Write, Grep`
+- **Executor agents**: `Read, Write, Bash, Grep`
 - **Full access**: Omit tools field
 
 ### Customize Colors