Claude Code productivity patterns including EPCC workflow, context management, and extended thinking triggers. Use when starting sessions or managing context.
Provides EPCC workflow patterns (Explore→Plan→Code→Commit) and context management strategies. Use at session start or when context is overloaded to maintain productivity and prevent context overflow.
/plugin marketplace add mjohnson518/claude_superpowers/plugin install mjohnson518-claude-superpowers@mjohnson518/claude_superpowersThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/claude-md-template.mdMaximize productivity through proven workflow patterns.
Never execute git commands. Output all git commands for manual execution.
The core workflow for every session: Explore → Plan → Code → Commit
Read CLAUDE.md and relevant source files.
Summarize the current state. Do not write code yet.
Think hard about implementing [feature].
Consider edge cases and affected files.
Output the plan. Do not implement yet.
Implement step 1 of the plan.
Run tests after changes.
Generate git commands for manual execution.
Do not run git commands.
| Phrase | Use For |
|---|---|
| "think hard" | Architecture decisions |
| "ultrathink" | Complex algorithms, security |
| "think step by step" | Multi-step procedures |
| "analyze thoroughly" | Refactoring, debugging |
/context
Before clearing:
Dump progress to progress-[project]-[date].md:
- What was accomplished
- Current state
- Next steps
- Git commands to run
After clearing:
/clear
Read CLAUDE.md and progress file. Continue with [next task].
Context overflow: /clear, then read only essential files
Stuck in loop: "Stop. Summarize what's not working. Try different approach."
Quality issues: "Pause. Re-read requirements. Think hard. Start fresh."
See references/claude-md-template.md for CLAUDE.md template.
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.