Explore skills

ローカル変更をデフォルトブランチと比較してセルフレビューする。Issue 番号があれば要件適合もチェックする。ユーザーが「レビューして」「変更確認して」「/smart-review」「/smart-review #123」と言ったら起動する。

要件やスペックから「あるべきソフトウェア設計」を言語化する。新機能の設計着手時、既存機能の再設計時、仕様の解像度を上げたいときに使う。画面デザイン（UI/UX）は対象外。

Writing rules for clear, powerful, incarnated blog posts.

Go coding best practices and patterns. Use when working with Go or Golang files: implementation, testing, refactoring, architectural review, goroutines, channels, interfaces, error handling, memory management, and API development.

Adaptive summarization — output length scales with input length for comfortable reading. Triggers: "summarize", "summarize this", "tldr", "too long", "sum up", "key points", "give me summary", "eli5", "explain like I'm 5", "explain simply". NOT FOR: translation (just ask), content creation (use content-humanizer). Produces: summary at optimal compression ratio based on input length.

Switch between small local skill profiles: all, coding, writing, or minimal.

Adversarial red team — find security holes, logic bugs, wasted resources. Triggers: "critic", "red team", "attack this", "what's wrong", "find flaws", "challenge this". NOT FOR: code review before merge (use review), debugging (use systematic-debugging). Produces: prioritized list of flaws with severity and remediation steps.

6-model R&D Council debate — multi-round argument, cross-examination, consensus memo. Triggers: "/debate", "council", "R&D meeting", "model debate", "6 models discuss". NOT FOR: simple questions (just ask), code review (use review), brainstorming. Produces: executive memo with consensus position from 6 AI models.

Use when the user explicitly asks to reflect on, review, or learn from the current Claude Code session — e.g. "review this session", "reflect on this session", "why did that take so many tries", "what went wrong this session", or asks to turn this session's mistakes into project rules. Reads the session transcript, finds where Claude's output was rejected or required correction, distills the root

The most comprehensive Claude Code setup — 29 skills, 9 plugins, 13 hooks, 8 agents, 8 commands. Self-documenting, self-improving, CLI-first. Includes self-interview prompt for personalization.

The most comprehensive Claude Code setup — 29 skills, 9 plugins, 13 hooks, 8 agents, 8 commands. Self-documenting, self-improving, CLI-first. Includes self-interview prompt for personalization.

The most comprehensive Claude Code setup — 29 skills, 9 plugins, 13 hooks, 8 agents, 8 commands. Self-documenting, self-improving, CLI-first. Includes self-interview prompt for personalization.