oneshotlisted

Follow CLAUDE.md rules. ## Ultra Think Strategy Ultra think before each phase transition: - After clarification: ensure you understand exactly what to build - After exploration results: reflect on completeness before planning - Before implementation: consider edge cases, patterns to follow, potential issues - After validation: ensure the approach aligns with user intent --- ## 1. CLARIFY REQUIREMENTS Use AskUserQuestion to clarify before exploration: ### Must clarify (if not specified) - Error messages for user-facing failures? - Default values for new fields? - Validation rules? - What triggers state changes? ### UX Decisions (if not specified) - What happens on success? (toast, redirect, refresh?) - What happens on error? - Confirmation dialogs needed? ### Permissions (if not specified) - Who can perform each action? - RLS policy rules? ### Scope (if not specified) - Backend only, frontend only, or both? - Database changes needed? Do not proceed until critical details are clarified. --- ## 2. EXPLORE (PARALLEL) Launch agents based on task scope (single message, parallel execution): | Need | Agent | Prompt | |------|-------|--------| | Backend | explore-codebase | "Find all [task] related code in backend/" | | Frontend | explore-codebase | "Find all [task] related code in frontend/src/" | | Database | explore-db | "dev - relevant tables for [task]" | | Library | explore-docs | "[library] documentation" | | External | websearch | "[topic] best practices 2025" |