claude-config-doctor

Audit your Claude Code configuration and get improvement suggestions

Use this agent when you need to audit a user's Claude Code configuration for quality, consistency, and best practices. Supports both global (~/.claude/) and project-level (.claude/) configurations. <example> Context: User wants to check if their Claude Code setup is well-configured. user: "Claude Code の設定を見直したい" assistant: "cc-doctor エージェントで設定を監査します。" <commentary> The user wants a configuration audit. Use the cc-doctor agent for independent analysis. </commentary> </example> <example> Context: User has been using Claude Code for a while and suspects their config is bloated. user: "CLAUDE.md が長くなりすぎた気がする。最適化してほしい" assistant: "cc-doctor エージェントで設定全体を監査し、改善提案を出します。" <commentary> Config optimization request. The cc-doctor agent will analyze and suggest improvements. </commentary> </example> <example> Context: User wants to audit their project-level Claude Code configuration. user: "このプロジェクトの .claude/ 設定をチェックして" assistant: "cc-doctor エージェントでプロジェクトレベルの設定を監査します。" <commentary> Project-level config audit. The cc-doctor agent checks .claude/ in the current working directory. </commentary> </example> <example> Context: User just set up Claude Code and wants to verify their configuration. user: "初期設定が正しいか確認して" assistant: "cc-doctor エージェントで初期設定の妥当性を確認します。" <commentary> Initial setup verification. The cc-doctor agent checks against best practices. </commentary> </example>

Use this agent when you need to assess the Harness Engineering maturity of a user's Claude Code configuration. This agent evaluates hooks, feedback loops, evaluator patterns, session continuity, and overall HE readiness. <example> Context: User wants to check their HE maturity level. user: "/doctor --he" assistant: "cc-he-doctor エージェントで HE 成熟度を評価します。" <commentary> The user wants HE maturity assessment. Use cc-he-doctor for specialized HE analysis. </commentary> </example> <example> Context: User wants to know how to improve their harness. user: "ハーネスの改善点を教えて" assistant: "cc-he-doctor エージェントで現在の HE 成熟度を評価し、次のステップを提案します。" <commentary> Harness improvement request. Assess current state first, then recommend next steps. </commentary> </example> <example> Context: User wants to check HE maturity for a specific project. user: "/doctor project --he" assistant: "cc-he-doctor エージェントでプロジェクトの HE 成熟度を評価します。" <commentary> Project-scoped HE assessment. </commentary> </example>

This skill should be used when the user asks to "Claude Code の設定方法を知りたい", "~/.claude/ のベストプラクティスを教えて", ".claude/ の設定を整理したい", "how to configure Claude Code", "CLAUDE.md の書き方", or needs guidance on structuring their ~/.claude/ or project .claude/ directory for optimal Claude Code usage. This skill provides general guidance and best practices only. For auditing an actual configuration and getting specific improvement suggestions, use the `/doctor` command instead.

This skill should be used when the user asks about "Harness Engineering", "HE成熟度", "ハーネスエンジニアリング", "hooks のベストプラクティス", "AIエージェントの制御", "harness maturity", or needs guidance on implementing harness engineering patterns in their Claude Code setup. This skill provides conceptual guidance and best practices. For auditing the current HE maturity level, use the `/doctor --he` command instead.