Master plugin testing, quality assurance, and validation. Learn unit testing, integration testing, and how to ensure plugin quality.
Validates plugin structure, content, and functionality before deployment. Use `/test-plugin` to catch JSON errors, broken references, and quality issues early.
/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/testing_config.yamlreferences/TESTING_GUIDE.mdscripts/test_runner.pyTest your plugin:
# Validate structure
/test-plugin my-plugin
# Run all tests
/test-plugin my-plugin --all
# Detailed report
/test-plugin my-plugin --report
Test individual components:
Agent:
✅ Description present and valid
✅ Capabilities list complete
✅ Content properly formatted
✅ Status and date included
Skill:
✅ Name lowercase-hyphens
✅ Quick Start code runs
✅ 3+ concepts documented
✅ Real projects included
Command:
✅ Executes without error
✅ Options documented
✅ Example output provided
Test component interactions:
Agent → Agent:
✅ Agent A links to Agent B
✅ Both agents available
✅ Integration documented
Agent → Skill:
✅ Agent recommends skill
✅ Skill accessible
✅ Connection clear
Command → Agent:
✅ Command invokes agent
✅ Agent responds appropriately
✅ Workflow makes sense
{
"manifest_valid": {
"description": "plugin.json valid JSON",
"check": "JSON.parse(plugin.json)"
},
"files_exist": {
"description": "All referenced files exist",
"check": "For each agent/skill/command file"
},
"naming_correct": {
"description": "Files follow naming conventions",
"check": "lowercase-hyphens pattern"
},
"references_valid": {
"description": "All manifested references valid",
"check": "Check each file path"
}
}
Agent:
✅ YAML frontmatter valid
✅ Description < 1024 chars
✅ Capabilities 5-10 items
✅ Content 250-400 lines
✅ Markdown properly formatted
Skill:
✅ YAML frontmatter valid
✅ Name < 64 chars, lowercase
✅ Quick Start code works
✅ Core concepts explained
✅ Real projects included
Command:
✅ Markdown valid
✅ Usage clear
✅ Options documented
✅ Example provided
✅ Next steps suggested
Agent Invocation:
✅ Agent loads without error
✅ Content renders correctly
✅ Integrations accessible
✅ No broken links
Skill Loading:
✅ Skill accessible from agent
✅ Code examples accurate
✅ Links functional
✅ Metadata correct
Command Execution:
✅ Command recognized
✅ Options work as documented
✅ Output as expected
✅ Next steps provided
PLUGIN TEST REPORT
═══════════════════════════════════════
Plugin: my-plugin
Version: 1.0.0
Date: 2025-01-18
STRUCTURE TESTS
✅ Manifest valid (5/5)
✅ Files exist (8/8)
✅ Naming correct (6/6)
├─ Result: PASS
CONTENT TESTS
✅ Agents valid (3/3)
✅ Skills valid (5/5)
✅ Commands valid (4/4)
├─ Result: PASS
FUNCTIONALITY TESTS
✅ Agents invoke (3/3)
✅ Skills load (5/5)
✅ Commands execute (4/4)
├─ Result: PASS
QUALITY SCORE: 98% ✅
READY FOR PRODUCTION: YES ✅
═══════════════════════════════════════
❌ Error in plugin.json line 15
Missing comma after "name": "value"
Fix:
"name": "value", ← Add comma
"version": "1.0.0"
❌ Agent agents/missing.md referenced but not found
Fix:
1. Create the file, OR
2. Remove reference from plugin.json
❌ Invalid YAML in agents/agent.md
Fix:
- Check indentation (use spaces, not tabs)
- Ensure quotes around values with special chars
- Verify array syntax with dashes
⚠️ Warning: Skill content only 150 lines
Recommended: 200-300 lines
Fix:
- Add more examples
- Expand core concepts
- Include more projects
Agent initialization: < 500ms ✅
Skill loading: < 300ms ✅
Command execution: < 2s ✅
Overall workflow: < 5s ✅
Agent files: < 400 lines ✅
Skill files: < 300 lines ✅
Command files: < 150 lines ✅
Manifest: < 50KB ✅
# Quick test (5 min)
/test-plugin my-plugin
# Full test (10 min)
/test-plugin my-plugin --full
# Continuous monitoring
/test-plugin my-plugin --watch
✅ Structure tests
✅ Content validation
✅ Format checking
✅ Reference validation
✅ Performance baseline
✅ Integration tests
[ ] All structure tests pass
[ ] All content validation passes
[ ] No broken references
[ ] Performance acceptable
[ ] Documentation complete
[ ] Examples working
[ ] Error messages helpful
[ ] Integration smooth
[ ] User acceptance tested
[ ] Ready for marketplace
Before release:
✅ Version bumped
✅ CHANGELOG updated
✅ All tests passing
✅ Documentation updated
✅ Examples verified
✅ Performance baseline met
✅ Code reviewed
Use this skill when:
Status: ✅ Production Ready | SASMP: v1.3.0 | Bonded Agent: 04-plugin-tester
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.