Data & AI

Organize and normalize an Obsidian vault in a Zettelkasten, folder-first style. Use when asked to scan/analyze an Obsidian vault, generate Report.md and an executable Plan.md, normalize filenames (YYYYMMDD Title), merge YAML frontmatter (type/status/created/updated/tags/aliases/source), plan moves between top folders (00_Inbox/10_Literature/20_Permanent/30_Maps/40_Projects/90_Archive), fix wikilinks and markdown links after renames/moves, manage attachments in per-top-folder _assets, and apply changes with rollback via backups in 90_Archive/_organizer_backups.

Provides guidance and best practices for writing simple, understandable code that developers can easily maintain

Extract structured claims, predictions, hints, and opinions from AI research content. Use when processing tweets, blog posts, substacks, or other content from AI researchers to identify substantive assertions about AI capabilities, limitations, and progress.

Training monitoring dashboard setup with TensorBoard and Weights & Biases (WandB) including real-time metrics tracking, experiment comparison, hyperparameter visualization, and integration patterns. Use when setting up training monitoring, tracking experiments, visualizing metrics, comparing model runs, or when user mentions TensorBoard, WandB, training metrics, experiment tracking, or monitoring dashboard.

Documentation generation patterns for technical specs, API docs, user guides, and knowledge bases using real tools like Sphinx, MkDocs, TypeDoc, and Nextra. Use when creating docs from code, building doc sites, or automating documentation workflows.

Create detailed implementation plans from feature specs or bug reports with testable acceptance criteria. Use proactively when planning features, refactors, or fixes. Every task MUST have minimum 2 testable ACs and map to requirements.

This skill should be used when working with GitHub CLI (gh) for pull requests, issues, releases, and GitHub automation. Use when users mention gh commands, GitHub workflows, PR operations, issue management, or GitHub API access. Essential for understanding gh's mental model, command structure, and integration with git workflows.

Master machine learning fundamentals. Production-ready code examples, best practices, and real-world applications.

Handle token failures, API rate limits, and permission errors in GitHub Actions workflows with retry logic, validation checks, and actionable error messages.

Use esta skill quando trabalhar com o sistema de chat IA para criação de artigos. Contém workflow completo, detecção de intenção, comandos naturais, e arquitetura técnica.

Analyzes subagent usage patterns to determine when to delegate tasks, evaluates and improves existing subagent configurations, creates new custom subagents when needed, and identifies outdated subagent information. Use when deciding if a task should use a subagent, analyzing existing agents for effectiveness, recommending agent improvements, creating specialized agents for recurring patterns, or managing agent configurations. Optimizes Claude's subagent usage for performance, context preservation, and task specialization.

Comprehensive Docker containerization workflow covering multi-stage builds, docker-compose orchestration, image optimization, debugging, and production best practices. Use when containerizing applications, setting up development environments, or deploying with Docker.

Analyze recent changes and add test coverage for HEAD commit

Check comprehensive platform health including ArgoCD apps, pods, services, certificates, and resources across the Kagenti platform

Default testing standard for all implementation work - ensures code actually works through mandatory execution validation before confirming to user. Applies automatically whenever writing, modifying, debugging, or implementing any code (scripts, APIs, UI, configs, data operations, logic changes). This is the baseline expectation, not an optional extra - every implementation must be verified through actual execution, not assumed correct.

Submit complex code questions to OpenAI GPT-5 Pro for deep analysis when you have 20 minutes. Use when the user asks for architectural analysis, comprehensive code review, debugging complex issues, or requests expert analysis of their codebase that requires extended reasoning. Automatically handles file selection, code packing with Repomix, cost estimation, long-running API requests, and result presentation.

Kindle Web Reader/Kindle macOSアプリからスクリーンショットをキャプチャしてPDF生成。書籍名やASIN指定でKindle本を自動PDF化。Kindleライブラリ検索、Playwrightでページ自動取得、PNG画像からPDF変換、レイアウト設定（single/double）、範囲指定、品質調整、リサイズに対応。タイトル取得に失敗した場合は表紙キャプチャをAIで視認して命名する。

Generate a skeleton template for a new Claude Code Skill.

Pulls ticket details from Jira, creates feature branches with proper naming conventions, and handles planning steps. Use when starting work on a Jira ticket, creating branches for tickets, or when users mention "work on ticket", "start ticket", "create branch for", or Jira ticket IDs.

Verify OpenSCAD libraries (BOSL2, Round-Anything) are installed, troubleshoot common issues, understand best practices for spiral generation, and evaluate designs against professional CAD quality standards.