LLM & Agents

Creates summary for human review - and comprehensive implementation plan for LLM, complete code examples, and verification steps

Generate comprehensive implementation plans for features. Use when user requests "help me implement X", "create a plan for X", "break down feature X", "how should I build X", or asks for detailed implementation guidance. Activates for planning requests, not exploratory design discussions.

This skill creates structured implementation plans with human-readable summaries. Triggers: "create a plan", "make a plan", "write a plan", "plan this feature", "plan how to implement", "break this down", "spec this out", "design this change". Creates plans with diagrams, code examples, and verification steps. Not for executing plans (use implementing-plans) or brainstorming (use brainstorming).

Create a shareable Claude Code plugin package containing your commands, hooks, output styles, status lines, and agents. Use when you want to package and distribute your Claude Code customizations, create team plugins, or export your personal setup.

Refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Use before writing code or implementation plans.

Implement web search, url content extraction, website crawling, and deep research with the tavily API. Use when building agentic workflows, rag systems, or autonomous agents that require real-time context from the web.

Create standardized report headers with metadata for all agent-generated reports. Use when generating bug reports, security audits, dependency reports, or any worker output requiring consistent formatting.

Patterns for using Codex CLI as an automated code reviewer. Covers review prompts, structured output parsing, issue tracking, and configuration. Use when implementing review gates or automated quality checks.

Claude Codeセッションの標準的なMarkdownフォーマット規約。セッションログ、対話履歴、ツール実行結果を一貫した構造で記録する必要がある場合に使用。不正確な情報への注釈方法とnb標準のハッシュタグ形式も定義

Use this skill when the user asks to build, create, design, develop, or improve ANY frontend interface, web page, UI component, or visual element. This includes: - Building landing pages, websites, web apps, dashboards, portfolios, or any web interface - Creating UI components (buttons, forms, cards, navbars, modals, etc.) - Designing pages with React, Vue, Next.js, Svelte, or any frontend framework - Adding styling or improving visual design of existing components - Implementing specific design aesthetics (modern, dark, minimalist, brutalist, etc.) - User mentions "frontend", "UI", "UX", "design", "interface", "web design", or "styling" - User asks for "beautiful", "modern", "professional", "clean", or any aesthetic adjective - User requests help with CSS, Tailwind, styled-components, or any styling approach This skill automatically retrieves the appropriate design system prompt (Neo-brutalism, Modern Dark, Bauhaus, Cyberpunk, Material, etc.) to help create visually distinctive, production-grade frontend code instead of generic UI. IMPORTANT: Trigger this skill proactively for ANY frontend/UI work, not just when design style is explicitly mentioned.

Extract readable transcripts from Claude Code and Codex CLI session JSONL files

Generate images using OpenAI's DALL-E 3 API. Use when needing to create graphics, icons, backgrounds, or any visual assets. Requires OPENAI_API_KEY in environment.

Generate standardized conventional commit messages with Claude Code attribution. Use when creating automated commits, release commits, or any git commit requiring consistent formatting.

Functional mythological compression for OCTAVE documents. Semantic shorthand for LLM audiences, not prose decoration. Activates 60-70% compression with 88-96% zero-shot comprehension. Triggers on: mythology, archetype, SISYPHEAN, ICARIAN, semantic compression, evidence-based.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Create, manage, and cleanup git worktrees with Claude Code agents across all projects. USE THIS SKILL when user says "create worktree", "spin up worktrees", "new worktree for X", "worktree status", "cleanup worktrees", or wants parallel development branches. Handles worktree creation, dependency installation, validation, agent launching in Ghostty, and global registry management.

Use when building NuxtHub v0.10 applications - provides database (Drizzle ORM with sqlite/postgresql/mysql), KV storage, blob storage, and cache APIs. Covers configuration, schema definition, migrations, multi-cloud deployment (Cloudflare, Vercel), and the new hub:db, hub:kv, hub:blob virtual module imports.

Use when developing WordPress plugins: architecture and hooks, activation/deactivation/uninstall, admin UI and Settings API, data storage, cron/tasks, security (nonces/capabilities/sanitization/escaping), and release packaging.

Fundamental reading and writing capability for the OCTAVE format. Inject this to give an agent basic structural competence without the overhead of full architectural specifications. Triggers on: octave format, write octave, octave syntax, structured output.

Rope-first workflow for ANY mechanical Python rename/move (functions/methods/classes/variables/modules/packages), updating imports/references via scripts/rope_refactor.py; use even for small renames; only fallback if rope fails/dynamic imports.