Use when complexity is spiraling, implementing the same concept multiple ways, or accumulating special cases - finds one insight that eliminates multiple components: 'if this is true, we don't need X, Y, or Z'. Do NOT use when code is already simple or when complexity is genuinely necessary - premature simplification can remove important edge case handling.
/plugin marketplace add jrc1883/popkit-claude/plugin install popkit@popkit-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
When complexity spirals, stop adding code. Look for the ONE insight that eliminates multiple components at once.
Core principle: The best fix often isn't more code - it's realizing you don't need code you thought you did.
Red flags triggering this skill:
When you notice complexity spiraling:
Write down everything the feature currently needs:
For each component, ask: "What assumption makes this necessary?"
Examples:
Look for ONE change that eliminates MULTIPLE components:
If [X is true], we don't need:
- Component A
- Component B
- Component C
- Edge case handler D
The best insights:
Before implementing:
Counter-intuitive order:
This ensures you actually get the simplification.
Before (complex):
Insight: "If we make the server the single source of truth and accept brief loading states, we don't need..."
After (simple):
Removed: 5 components, ~500 lines
Before (complex):
Insight: "If we just use TypeScript constants and rebuild on change, we don't need..."
After (simple):
Removed: 5 components, ~300 lines
Before (complex):
Insight: "If users are either admin or not-admin for our use case, we don't need..."
After (simple):
isAdmin booleanRemoved: 5 components, ~400 lines
Don't confuse simplification with:
| Wrong Approach | Why It Fails |
|---|---|
| Hiding complexity in abstractions | Complexity still exists, just hidden |
| Moving code to a library | Still maintaining it |
| "It's simple if you understand it" | Complexity for newcomers matters |
| Deferring problems | Technical debt grows |
True simplification:
After finding an insight, apply this test:
If I explain this feature to a new developer:
- Before: Need to explain X, Y, Z, and their interactions
- After: Just explain A
If "after" isn't dramatically simpler, keep looking.
Sometimes complexity is inherent:
In these cases:
When stuck in complexity:
The goal isn't less code - it's fewer concepts.
100 lines of straightforward code > 20 lines of clever code Removing a feature > Simplifying a feature Saying "no" > Building a workaround
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.