pro-workflow

What problem does it solve?

This skill tackles the overhead of building reliable Claude Code workflows by combining memory management, parallel sessions, and structured wrap-up rituals to reduce correction cycles and context switching.

Core Features & Use Cases

• Self-Correction Loop: Claude learns from user corrections and builds memory of rules to improve future sessions.
• Parallel Worktrees: Run multiple Claude sessions in parallel to reduce idle time while thinking.
• Wrap-Up Ritual: End sessions with a documented checklist to capture learnings and plan next steps.
• Split Memory Architecture: Organize memory into CLAUDE.md, AGENTS.md, SOUL.md, and LEARNED.md for modularity.
• 80/20 Review: Batch reviews at checkpoints to optimize iteration time.
• Model Selection: Adaptive thinking and multi-model guidance for different task types.
• Context Discipline: Manage token budgets and prune explorations to stay within limits.
• Learning Log: Auto-document insights from sessions for future reference.

Quick Start

Switch to dev mode and begin a session by establishing CLAUDE.md structure, then enable parallel worktrees and the wrap-up ritual as you complete tasks.