docs: update documentation for Skill tool consolidation (#186)

## Description

Updates documentation to reflect the consolidation of the SlashCommand
tool into the Skill tool in Claude Code. The SlashCommand tool has been
deprecated and its functionality merged into the unified Skill tool,
which can now invoke both slash commands and Agent Skills
programmatically.

## Type of Change

- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to not work as expected)
- [x] Documentation update (improvements to README, CLAUDE.md, or
component docs)
- [ ] Refactoring (code change that neither fixes a bug nor adds a
feature)
- [ ] Test (adding or updating tests)
- [ ] Configuration change (changes to .markdownlint.json, plugin.json,
etc.)

## Component(s) Affected

- [x] Commands (`/plugin-dev:*`)
- [x] Skills (methodology and best practices)
- [ ] Agents (plugin-validator, skill-reviewer, agent-creator)
- [ ] Hooks (event-driven automation)
- [ ] Marketplace (marketplace.json, distribution)
- [x] Documentation (README.md, CLAUDE.md, SECURITY.md)
- [ ] Configuration (.markdownlint.json, plugin.json)
- [ ] Issue/PR templates
- [ ] Other (please specify):

## Motivation and Context

The Claude Code documentation at
https://code.claude.com/docs/en/slash-commands#skill-tool states:

> "In earlier versions of Claude Code, slash command invocation was
provided by a separate `SlashCommand` tool. This has been merged into
the `Skill` tool."

Our documentation referenced the deprecated `SlashCommand` tool and
needed updating to reflect this change. Additionally, the
`user-invocable` and `disable-model-invocation` frontmatter fields for
skills were undocumented.

Related to #184

## How Has This Been Tested?

**Test Configuration**:

- Claude Code version: Latest
- GitHub CLI version: 2.73.0
- OS: macOS Darwin 25.2.0

**Test Steps**:

1. Ran `markdownlint '**/*.md' --ignore node_modules` - passes with no
errors
2. Verified all internal links in updated files reference correct paths
3. Reviewed content against official Claude Code documentation

## Checklist

### General

- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my own code
- [x] I have commented my code, particularly in hard-to-understand areas
(if applicable)
- [x] My changes generate no new warnings or errors

### Documentation

- [x] I have updated the documentation accordingly (README.md,
CLAUDE.md, or component docs)
- [x] I have updated YAML frontmatter (if applicable)
- [x] I have verified all links work correctly

### Markdown

- [x] I have run `markdownlint` and fixed all issues
- [x] My markdown follows the repository style (ATX headers, dash lists,
fenced code blocks)
- [x] I have verified special HTML elements are properly closed (`<p>`,
`<img>`, `<example>`, `<commentary>`)

### Shell Scripts (if applicable)

- [ ] Shell scripts pass `shellcheck` - N/A
- [ ] Scripts are executable (`chmod +x`) - N/A
- [ ] Scripts use `${CLAUDE_PLUGIN_ROOT}` for portable paths - N/A

### Component-Specific Checks

<details>
<summary><strong>Skills</strong> (click to expand)</summary>

- [x] Description uses third-person with specific trigger phrases
- [x] SKILL.md is 1,000-2,200 words (progressive disclosure)
- [x] Detailed content is in `references/` subdirectory
- [x] Templates follow the established format

</details>

### Testing

- [ ] I have tested the plugin locally with `claude --plugin-dir
plugins/plugin-dev`
- [ ] I have tested the full workflow (if applicable)
- [ ] I have verified GitHub CLI integration works (if applicable)
- [ ] I have tested in a clean repository (not my development repo)
- [ ] I have run relevant validation scripts (validate-agent.sh,
validate-command.sh, validate-hook-schema.sh, etc.)

### Version Management (if applicable)

- [ ] I have updated version numbers in all version files - N/A (docs
only)
- [ ] I have updated CHANGELOG.md with relevant changes - Can be done at
release

## Additional Notes

### Changes Made

1. **Renamed `slashcommand-tool.md` → `skill-tool.md`**
   - Comprehensive rewrite to document the unified Skill tool
   - Updated permission rule syntax (`Skill(name:*)` format)
   - Added table showing what the Skill tool can invoke
   - Added section on `user-invocable` field for skills

2. **Updated command-development/SKILL.md**
   - Changed trigger phrase from "SlashCommand tool" to "Skill tool"
   - Updated reference to renamed file

3. **Updated skill-development/SKILL.md**
   - Added documentation for `user-invocable` frontmatter field
- Added documentation for `disable-model-invocation` frontmatter field
   - Added visibility comparison table
   - Updated validation checklist with new optional fields

4. **Updated commands/start.md**
   - Changed `allowed-tools` from `SlashCommand` to `Skill`
   - Updated instructions to reference Skill tool

5. **Updated frontmatter-reference.md**
   - Changed all SlashCommand references to Skill tool

6. **Updated CLAUDE.md**
   - Changed tool reference in workflow command security section

## Reviewer Notes

**Areas that need special attention**:
- The `skill-tool.md` reference file was significantly rewritten -
please verify accuracy against official docs
- New `user-invocable` and `disable-model-invocation` documentation in
skill-development skill

**Known limitations or trade-offs**:
- This PR addresses only the documentation updates; the meta-skill
feature request from #184 will be handled separately

---

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>

Author: sjnims

CLAUDE.md

@@ -302,7 +302,7 @@ allowed-tools: Read, Write, Edit, Grep, Glob, Bash(mkdir:*), Bash(git init:*), .
 
 **Design contrast with `/plugin-dev:start`:**
 
-The entry point command uses `disable-model-invocation: true` and restricts tools to `AskUserQuestion, SlashCommand, TodoWrite` since it only routes to other commands. The workflow commands need broader access because they perform the actual file creation work.
+The entry point command uses `disable-model-invocation: true` and restricts tools to `AskUserQuestion, Skill, TodoWrite` since it only routes to other commands. The workflow commands need broader access because they perform the actual file creation work.
 
 **For security-sensitive environments:**
 

plugins/plugin-dev/commands/start.md

@@ -1,7 +1,7 @@
 ---
 description: Start plugin development - choose your path
 argument-hint: [description]
-allowed-tools: AskUserQuestion, SlashCommand, TodoWrite
+allowed-tools: AskUserQuestion, Skill, TodoWrite
 model: sonnet
 disable-model-invocation: true
 ---
@@ -73,13 +73,13 @@ After the user selects an option:
 **If they chose "A plugin"**:
 
 - Acknowledge their choice
-- Use the SlashCommand tool to invoke `/plugin-dev:create-plugin`
+- Use the Skill tool to invoke `/plugin-dev:create-plugin`
 - Pass through any context from $ARGUMENTS if provided
 
 **If they chose "A marketplace"**:
 
 - Acknowledge their choice
-- Use the SlashCommand tool to invoke `/plugin-dev:create-marketplace`
+- Use the Skill tool to invoke `/plugin-dev:create-marketplace`
 - Pass through any context from $ARGUMENTS if provided
 
 ---

plugins/plugin-dev/skills/command-development/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: command-development
-description: This 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", "SlashCommand tool", "programmatic command invocation", "disable-model-invocation", "prevent Claude from running command", "debug command", "command debugging", "troubleshoot command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, programmatic invocation control, debugging commands, or command development best practices for Claude Code.
+description: This 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", "Skill tool", "programmatic command invocation", "disable-model-invocation", "prevent Claude from running command", "debug command", "command debugging", "troubleshoot command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, programmatic invocation control, debugging commands, or command development best practices for Claude Code.
 ---
 
 # Command Development for Claude Code
@@ -193,7 +193,7 @@ argument-hint: [pr-number] [priority] [assignee]
 
 ### disable-model-invocation
 
-**Purpose:** Prevent SlashCommand tool from programmatically calling command
+**Purpose:** Prevent Skill tool from programmatically calling command
 **Type:** Boolean
 **Default:** false
 
@@ -704,7 +704,7 @@ Commands should validate inputs and resources before processing:
 ## Additional Resources
 
 For detailed frontmatter field specifications, see `references/frontmatter-reference.md`.
-For SlashCommand tool, programmatic invocation, and permission configuration, see `references/slashcommand-tool.md`.
+For Skill tool, programmatic invocation, and permission configuration, see `references/skill-tool.md`.
 For plugin-specific features and patterns, see `references/plugin-features-reference.md`.
 For plugin integration and validation patterns, see `references/plugin-integration.md`.
 For interactive user input patterns using AskUserQuestion, see `references/interactive-commands.md`.

plugins/plugin-dev/skills/command-development/references/frontmatter-reference.md

@@ -280,7 +280,7 @@ Run tests matching $1 with options: $2
 **Required:** No
 **Default:** false
 
-**Purpose:** Prevent SlashCommand tool from programmatically invoking command
+**Purpose:** Prevent Skill tool from programmatically invoking command
 
 **Examples:**
 ```yaml
@@ -314,13 +314,13 @@ disable-model-invocation: true
    ```
 
 **Default behavior (false):**
-- Command available to SlashCommand tool
+- Command available to Skill tool
 - Claude can invoke programmatically
 - Still available for manual invocation
 
 **When true:**
 - Command only invokable by user typing `/command`
-- Not available to SlashCommand tool
+- Not available to Skill tool
 - Safer for sensitive operations
 
 **Best practices:**