Master plugin performance optimization, best practices, and marketplace readiness. Learn to optimize for speed, efficiency, and user satisfaction.
Optimize plugin performance and prepare for marketplace submission. Use when your plugin needs speed improvements, best practices validation, or pre-deployment checks. Run `/optimize-plugin` to get actionable recommendations and auto-fix critical issues.
/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/optimization_config.yamlreferences/OPTIMIZATION_GUIDE.mdscripts/perf_analyzer.pyOptimize your plugin:
# Get optimization recommendations
/optimize-plugin my-plugin
# Fix issues automatically
/optimize-plugin my-plugin --auto-fix
# Detailed optimization report
/optimize-plugin my-plugin --report
Agent invocation: < 1 second
Skill loading: < 500ms
Command execution: < 2 seconds
Hook triggering: < 100ms
Total workflow: < 5 seconds
Before:
This agent specializes in various aspects of the field,
including many different topics that are related to the
general area of expertise. The agent can help with many
different things such as...
After:
Specializes in X, Y, Z with focus on ABC.
✅ DO:
├─ Focus on single domain
├─ Provide 5-10 capabilities
├─ Document integrations
├─ Use clear language
└─ Include status/date
❌ DON'T:
├─ Mix unrelated topics
├─ Create vague descriptions
├─ Ignore other agents
├─ Use technical jargon
└─ Skip examples
✅ DO:
├─ Name lowercase-hyphenated
├─ Provide Quick Start code
├─ Explain core concepts
├─ Include real projects
└─ Add usage guidelines
❌ DON'T:
├─ Use uppercase/underscores
├─ Skip working examples
├─ Theory only
├─ Ignore real-world use
└─ Leave users confused
✅ DO:
├─ Use verb-noun naming
├─ Document all options
├─ Show example output
├─ Suggest next steps
└─ Clear error messages
❌ DON'T:
├─ Generic names
├─ Undocumented flags
├─ Missing output examples
├─ Leave guessing
└─ Cryptic errors
Agent files: 250-400 lines
Skill files: 200-300 lines
Command files: 100-150 lines
Total plugin: < 50KB
Trim verbose sections
→ Remove redundant text
→ Link to external resources
→ Use clear headings
Consolidate examples
→ Use concise code
→ Remove verbose comments
→ Focus on essential cases
Organize content
→ Logical sections
→ Clear headings
→ Table formatting
STRUCTURE ✅
[✅] plugin.json valid
[✅] Files exist and referenced
[✅] Naming conventions followed
[✅] No broken references
CONTENT ✅
[✅] README comprehensive
[✅] Examples working
[✅] All commands documented
[✅] Links verified
QUALITY ✅
[✅] All tests passing
[✅] No console errors
[✅] Performance baseline met
[✅] Error handling complete
STANDARDS ✅
[✅] YAML frontmatter valid
[✅] Markdown properly formatted
[✅] JSON valid syntax
[✅] No deprecated features
# Plugin Name
[One-liner description]
## Features
[Key features]
## Installation
[One-liner install]
## Quick Start
[Get running in 30 seconds]
## Usage
[Command reference]
## Documentation
[Link to detailed docs]
## Contributing
[How to contribute]
## License
[MIT or other]
Before:
# Process the data and return enriched information
result = process_data(input)
After:
# Process and return enriched data (Input: raw dict → Output: validated)
result = process_data(input)
Load time: < 500ms ✅
Skill load: < 300ms ✅
Command response: < 2s ✅
Hook trigger: < 100ms ✅
Test coverage: > 90% ✅
Error rate: < 1% ✅
Documentation: 100% ✅
Best practices: > 95% ✅
Track:
├─ Command usage patterns
├─ Agent popularity
├─ Skill effectiveness
├─ Error occurrence rate
├─ User feedback sentiment
└─ Performance trends
VERSION & DOCS
[✅] Version bumped (1.0.0)
[✅] CHANGELOG updated
[✅] README updated
QUALITY
[✅] All tests pass
[✅] No warnings
[✅] No console errors
[✅] Performance ok
CODE
[✅] All files present
[✅] References valid
[✅] Manifest valid
[✅] Lint passes
DEPLOYMENT
[✅] Git tagged
[✅] Changes committed
[✅] Marketplace ready
[✅] Monitoring set up
❌ Broken functionality
❌ Invalid manifest
❌ Missing core features
❌ Security issues
⚠️ Performance below baseline
⚠️ Incomplete documentation
⚠️ Error handling gaps
⚠️ Unclear UX
💡 Performance optimization
💡 UX enhancements
💡 Documentation polishing
💡 Code organization
1.0.0 → 1.0.1 (Bug fixes, patches)
1.0.0 → 1.1.0 (New features, backward compatible)
1.0.0 → 2.0.0 (Breaking changes)
feat: Add new command
fix: Correct agent description
docs: Update documentation
refactor: Improve structure
perf: Optimize loading
test: Add tests
Structure: 30% (file org, manifest, naming)
Content: 30% (quality, completeness, clarity)
Functionality: 20% (working, integration, features)
Performance: 10% (speed, size, efficiency)
Documentation: 10% (README, examples, help)
Target: 95%+ for production
Deploy
↓
Monitor metrics
↓
Gather user feedback
↓
Identify improvements
↓
Update plugin
↓
Deploy again
Weekly: Monitor metrics, collect feedback
Monthly: Fix bugs, update docs
Quarterly: Add features, optimize performance
Annually: Major improvements, breaking changes
Use this skill when:
Status: ✅ Production Ready | SASMP: v1.3.0 | Bonded Agent: 05-plugin-optimizer
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 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 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.