dev-tools-plugin

Fetch daily AI news, research papers, and deep dive analysis with self-evolving source registry. Use when user says 'AIニュース', 'ai-news', '論文', 'papers', '最新AI', 'daily digest', '最新の論文', 'arxiv', 'AI最新動向', 'papers today', '今日のAI', '研究動向', 'AI news', '論文まとめ', 'AI業界ニュース', or wants any kind of AI research or industry news digest. Make sure to use this skill proactively when the user mentions AI papers, research trends, or wants to stay updated on AI developments.

Fetch daily business and tech industry news with self-evolving source registry. Use when user says 'ビジネスニュース', 'biz-news', 'テックニュース', 'スタートアップ', 'business news', 'tech news', '資金調達', 'M&A', '業界ニュース', or wants business/tech industry digest. Use proactively when the user mentions startup funding, tech acquisitions, industry trends, or wants to stay updated on business developments.

Claude Code settings catalog — discover what you can customize. Fetches latest settings and env vars from 3 sources (JSON Schema + official docs + official env-vars docs) to show all available options. Use when user says '設定', 'settings', '設定一覧', '設定カタログ', 'what can I configure', '何が設定できる', 'Claude Code設定', '設定項目', '環境変数', 'env vars', or wants to discover available Claude Code configuration options.

Git workflow safety procedures: diagnose why git add fails (3-layer gitignore system), recover from pre-commit hook failures (NEVER amend after hook failure), validate git add -A risks, and manage auto-generated directories. Use when git add fails, pre-commit hook fails, user attempts broad git add, gitignore issues arise, or git commit workflow encounters errors.

Deep-dive into problem clarity before building. Raises resolution on problems using 4 perspectives (depth, breadth, structure, time) through structured dialogue with Why Tree (7+ levels deep). Use when user says '課題を深掘り', '解像度を上げたい', '作る前に整理', 'problem shaping', 'shape the problem', or wants to clarify what to build and why.

End-of-day retrospective: review accomplishments, update task state, and prepare for tomorrow. Use when the user says '振り返り', '今日の成果', '帰る前に', 'daily log', 'wrap up', '1日の終わり', or wants to review what they accomplished today.

Comprehensive deep research that produces structured, multi-section reports with source citations. Only use when user explicitly requests deep/thorough research via '/deep-research' command or says '徹底調査', 'deep research', '調査レポート作成', '包括的なレポート'. Do NOT trigger for simple lookups like '調べて' or 'リサーチして' — use WebSearch or gemini-collab for those.

Blog drafting workflow: create a structured blog post draft from recent work, decisions, and learnings. Use when the user says 'ブログ', 'blog', '記事', 'アウトプット', '書きたい', or wants to turn recent work or learnings into a blog post.

Collaborate with Gemini CLI via tmux for web search, official docs/RFC/changelog lookup, compatibility checks, comparisons, or citations. Use when tasks require investigation with sourced information.

Start your work day with a briefing: restore yesterday's context, review tasks, and set today's goals. Use when the user says 'おはよう', '朝', 'morning', '今日のタスク', '昨日の続き', or starts a new day of work.

Collect feedback on task completion to improve prompts, CLAUDE.md, and skills. Use when the user says "improve prompts", "analyze feedback", "reflect on task", "/improve", or when Stop hook triggers for feedback collection. Enables continuous improvement loop for Claude Code configurations.

Save a quick memo to Obsidian for future recall. Use when the user says 'メモ', 'note', '覚えて', '記録', or wants to jot down a quick thought, tip, or reminder.

Autonomous multi-round debate between two Claude Code instances via tmux. Supports advocate/devil's-advocate, expert perspectives, and custom roles for design decisions, code review, debugging, and brainstorming. Use when user wants "Claude同士で議論", "ディベート", "多角的に検討", "debate", "pros and cons".

Chat with Codex via tmux for pair programming. Use when user wants to collaborate with Codex, get second opinion, design consultation, code review, or pair program with AI.

Chat with Cursor Agent via tmux for pair programming. Use when user wants to collaborate with Cursor, get second opinion, design consultation, or code review.

[INTERNAL] Common tmux operations for AI chat integration. Provides split, send, capture, kill commands with marker-based output extraction. This is an internal base skill used by codex-collab, cursor-collab, ai-research, and claude-collab. NOT user-invocable directly - other AI collaboration skills reference this as a dependency.

Session retrospective with AI-KPT framework. Reviews AI autonomous actions, detects omissions via counterfactual reasoning, persists learnings. Use when user says "振り返り", "retrospective", "KPT", "session review", "/hurikaeri".