# Using Expert Mode > Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions - Skill: `tomevault-io/using-expert-mode` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/using-expert-mode` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/using-expert-mode/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/using-expert-mode --- # Using Expert Mode ## The Rule **Invoke relevant skills BEFORE any response or action.** Flow: **Check for skills → Invoke skill → Follow skill.** ## Skill Priority & Types - **Process skills first:** `brainstorming`, `systematic-debugging`, `test-driven-development` - **Then implementation:** `writing-plans`, `executing-plans`, `completing-work` - **Rigid** (TDD, debugging): Follow exactly — order and steps matter - **Flexible** (brainstorming, plans): Adapt structure to context while preserving intent ## Red Flags — You're Rationalizing - "This is just a simple question" - "I need more context first" / "Let me explore the codebase first" - "This doesn't need a formal skill" / "The skill is overkill" - "I remember this skill" / "I'll just do this one thing first" - "This is different because..." ## User Instructions Instructions say WHAT, not HOW. "Add X" or "Fix Y" does not mean skip workflows. --- > Converted and distributed by [TomeVault](https://tomevault.io/claim/apenlor) — claim your Tome and manage your conversions.