.claude/skills/alert-design/SKILL.md

.claude/skills/composite-actions/SKILL.md

.claude/skills/electron-distribution/SKILL.md

.claude/skills/pm2-ecosystem-config/SKILL.md

.claude/skills/tutorial-design/SKILL.md

Speak text aloud using high-quality AI voice synthesis (Kokoro TTS on Apple Silicon). Use when user asks to vocalize, narrate, or speak text out loud.

Automated worktree management for Claude Code development sessions with smart naming, auto-setup, and cleanup.

Multi-agent code analysis orchestration using claudemem. Share claudemem output across parallel agents. Enables parallel investigation, consensus analysis, and role-based command mapping.

Payment requests and delivery for AI agents and humans.

Close task in tracker. Use when the user invokes /close or asks to close a tracker issue.

This skill helps AI agents track assumptions they made about the codebase that turned out to be incorrect. The goal is to identify documentation gaps and create better onboarding context for future AI

Claude가 오케스트레이터로서 작업을 분석하고, Codex CLI를 sub-agent로 호출하여 실제 구현 작업을 수행하는 스킬입니다.

Read and integrate response from Codex. Use when user says codex read, get codex response, or check codex results.

Lisp machine self-modification patterns via MCP Tasks and Narya bridge types

Check the current status of Codex collaboration. Use when user says codex status, check codex, or collaboration status.

codex-system

Collect git info and prepare PR content for reedom-gh:pr-maker agent.

Manage backorders for out-of-stock items. Use when tracking unfulfilled demand, allocating incoming inventory to backorders, or prioritizing backorder fulfillment.

commit-standards

>

Ensure thorough validation, error recovery, and transparent reasoning in research tasks with multiple tool calls

content-validator

> Auto-trigger search when user needs to find something

Save working state before compaction or session end for reliable recovery

Automatically invokes init-explorer agent when project context is empty or unknown.

Knowledge about the context branch methodology for separating AI configuration from project code using git worktrees. Use when users ask about worktree structure, branch organization, or the separation of concerns pattern.

Split large CLAUDE.md into child files. Use when context files exceed line limits, are too verbose, or cover multiple distinct topics that should be separate.

새 작업 요청 시 기존 작업과의 맥락 유사성을 판단하고, 비유사한 경우 자동으로 git worktree를 생성하여 새 브랜치에서 작업합니다. 작업 시작, 새 기능 구현, 다른 이슈 작업 시 자동 활성화됩니다.

Find past conversations in your Claude Code history and get the commands to resume them.

Use when implementing full-text search or complex filtering in Convex - provides search indexes, streams, query optimization, pagination, and relevance scoring

Advanced scheduling - runtime crons, batch processing, timeouts, retry patterns

You are the coordinator managing a team of Claude agents via tmux.

>

>

Create an Excalidraw data flow diagram

Create a general Excalidraw diagram

Create an Excalidraw wireframe

Professional, skeptical communication style focused on critical thinking and coaching. Never over-enthusiastic, always verifies before agreeing, challenges ideas constructively. Use when you want a persona to act as an expert peer who coaches rather than serves.

**READ: Ecclesiastics 9: 10-11**

daily-work-logger

Synthesize findings from multiple research sources into coherent insights. Use when combining data from different sub-agents or research threads.

Match decompiled C code to original PowerPC assembly for Super Smash Bros Melee. Use this skill when asked to match, decompile, or fix a function to achieve 100% match against target assembly. Invoked with /decomp <function_name> or automatically when working on decompilation tasks.

Deep executor mode for complex goal-oriented tasks

Alias for /tour - Interactive walkthrough of Product Org OS

dev_invoke_codex-cli

Toggle demo mode (see `.claude/reference/demo-mode.md`)

| 項目 | 値 |