Master plugin user experience design, command workflows, and interaction patterns. Create intuitive, user-friendly plugin interfaces.
Designs intuitive plugin commands and workflows with clear naming, helpful error messages, and progressive disclosure. Use when creating or improving plugin interfaces to ensure users can discover and use commands easily.
/plugin marketplace add pluginagentmarketplace/custom-plugin-design-system/plugin install custom-plugin-design-system@pluginagentmarketplace-design-systemThis skill inherits all available tools. When active, it can use any tool Claude has access to.
assets/design_config.yamlreferences/DESIGN_GUIDE.mdscripts/design_checker.pyDesign commands users will love:
# /create-plugin - Create new plugin
## What This Does
Creates a new plugin with guided setup.
## Usage
/create-plugin [name] [--type agent|command|skill]
## Example
$ /create-plugin my-plugin --type agent Creating... ✅ Next: /design-plugin my-plugin
✅ /create-plugin Clear action
✅ /design-plugin Obvious purpose
✅ /test-plugin Self-explanatory
✅ /optimize-plugin What it does
Verb-noun pattern:
├─ /create-X
├─ /design-X
├─ /test-X
└─ /optimize-X
User Input:
/create-plugin
System Response:
1. What's your plugin name?
> my-plugin
2. Plugin type?
[1] Agent-based
[2] Command-based
[3] Skill library
> 1
3. Number of agents?
> 3
Output:
✅ Plugin created
Next: /design-plugin
Beginner:
/create-plugin my-plugin
(simple, guided)
Intermediate:
/create-plugin my-plugin --type agent --agents 3
(more options)
Advanced:
/create-plugin --config config.json --skip-validation
(all options)
❌ Bad: Invalid input
✅ Good: Plugin name must be 3-50 characters, lowercase, hyphens only
❌ Bad: Error 500
✅ Good: Plugin creation failed: skill-one not found in agents/
❌ Bad: Fatal error
✅ Good: Missing required field 'description' in plugin.json
✅ Task completed
├─ What was done
├─ Where to find it
└─ What's next
⚠️ Warning: Using old syntax
├─ Recommendation: Update to new syntax
└─ Link: /help/migration-guide
❌ Error: Manifest invalid
├─ Issue: Missing "author" field
├─ Fix: Add "author": "Your Name"
└─ Help: /help/plugin-json
✅ Success (green)
⚠️ Warning (yellow)
❌ Error (red)
ℹ️ Info (blue)
→ Action (arrow)
[Icon] [Brief message]
├─ [Detail 1]
├─ [Detail 2]
└─ [Action or suggestion]
Help:
├─ /help Show all commands
├─ /help /create-plugin Help for specific command
└─ /help --agents List all agents
Related:
├─ Run: /create-plugin
├─ Then: /design-plugin
└─ Then: /test-plugin
After /create-plugin:
→ Suggestion: Run /design-plugin next
(natural workflow progression)
After /test-plugin:
→ Suggestion: Run /optimize-plugin
(next logical step)
✅ Simple words
✅ Short sentences
✅ Active voice
✅ No jargon
❌ "Facilitate optimization"
✅ "Make faster"
✅ Good contrast
✅ Large text
✅ Clear structure
✅ Readable font
✅ All commands accessible via keyboard
✅ No mouse required
✅ Clear keyboard shortcuts
User types: /create
System shows: Available commands starting with 'create'
├─ /create-plugin
├─ /create-agent
└─ /create-skill
Creating plugin...
⠋ Creating folders
✅ Folders created
⠙ Writing files
✅ Files written
⠹ Validating structure
✅ Validation complete
✅ Done!
Are you sure you want to delete my-plugin?
(This cannot be undone)
[Yes, delete] [No, cancel]
/create → /design → /test → /deploy
/test
├─ Tests pass → /deploy
└─ Tests fail → Fix issues → /test again
/explore-agents
├─ Agent details
└─ Related agents
After error:
❌ Skill name invalid
💡 Need help?
├─ Show format examples
├─ Visit docs
└─ Ask @plugin-developer
Level 1: What does this command do?
Level 2: How do I use it?
Level 3: What options are available?
Level 4: Advanced use cases?
Users often ask about:
├─ "How do I structure my plugin?"
→ /design-plugin command
└─ "How do I test it?"
→ /test-plugin command
We notice users struggle with:
├─ JSON formatting
→ Add JSON validation
└─ Naming conventions
→ Add clear examples
Use this skill when:
Status: ✅ Production Ready | SASMP: v1.3.0 | Bonded Agent: 03-plugin-designer
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", 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.