LLM & Agents

Pair skills with specialist agents, generating both the skill spec and the agent system prompt with validation and routing notes.

Generate visual hierarchy diagrams of agent system showing levels and delegation. Use for documentation or onboarding.

自媒体写作交互式助手。帮助完成从选题到发布的完整流程。适用于：开始写新文章、检查草稿质量、诊断发布后数据不佳的原因。

Advanced AgentDB deployment patterns, multi-tenant controls, and durability hardening.

Testing React Native. Use when writing tests, reviewing test coverage, or setting up testing.

Run Mojo tests using mojo test command. Use when executing tests or verifying test coverage.

Create custom slash commands for Claude Code. Use when the user wants to create, add, or build a new slash command, custom command, or save a prompt as a command.

Monitor and report status of all tmux sessions including dev environments, spawned agents, and running processes. Uses tmuxwatch for enhanced visibility.

Facilitate council-style deliberation among specialized models with structured prompts, evidence gates, and explicit confidence ceilings.

Generate production-ready PowerPoint decks with structured prompts, design guardrails, and validation checkpoints.

INVOKE when: creating new skills, editing SKILL.md files, modifying .claude/ content. NEVER edit .claude/ directly - this skill shows the arsenal-first workflow.

Craft professional video prompts for Google Veo 3.1 using cinematic techniques, audio direction, and timestamp choreography. Use when generating AI videos, creating video prompts, or working with Veo 3.

Use when coordinating multiple AI agents in real-time - provides inter-agent messaging via tmux wrapper (sub-5ms latency) or file-based team inbox for async workflows

Tool usage requirements, failure patterns, consistency checks, and validation methodologies for Claude Code operations

Extract reusable templates and patterns from source artifacts with structured prompts and validation checkpoints.

Fast batch refactoring via MorphLLM edit_file. Use for "refactor across files", "batch rename", "update pattern everywhere", large files (500+ lines), or 5+ edits in same file.

Use this skill to create or update the root AGENTS.md file to register AgenticDev skills for AI agent discovery. Triggers include "register AgenticDev", "update AGENTS.md", "setup agent guide", or initializing a new project.

Centralizes persona-driven code reviews (Fowler, Torvalds, Carmack, React core, etc.) so Claude can pick or combine expert viewpoints when the user asks for a code review or perspective-specific critique.

Claude Code 설정을 안내합니다. CLAUDE.md, rules, commands, skills, agents 구조와 사용법, "설정", "가이드", "헬프" 요청 시 사용하세요.

This skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination", "parallel agents", "report format", "agent communication", or needs to understand how agents coordinate within the sprint system.