.claude/skills/agile-project-management/SKILL.md

.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

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.

This skill provides knowledge about Claude tools (Prompts, Skills, Subagents, Commands, and MCPs). Use this skill when knowledge about Claude tools is needed, when the user mentions Claude tools or when the user needs help identifying the best Claude tool to use/create for a task. Common questions include 'Should I create a Claude tool for this use-case?', 'What type of Claude tool should I create for this use-case?.

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.

Project handover process for lead generation websites. Documentation, training, credentials, maintenance. Use when project complete.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

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

Close and archive a completed feature, moving it from active backlog to completed.

Cheat sheet for Windows Command Prompt commands.

Trigger this skill when the user:

'CRITICAL guardrail for preventing code duplication and magic strings

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

Codex MCP 协作流程。触发场景：(1) 新功能开发 (2) 重构 (3) 复杂业务逻辑 (4) 代码审查。提供三阶段协作：需求分析→原型获取→审查，强调批判性思考与只读安全。

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

Set up conda with multiple group storage locations on HiPerGator, including cache isolation

Manage bluera-base plugin configuration

Reads config.json and prompts user for application parameters. Merges configuration with defaults for project generation.

When consulting with external LLMs:

Compare document similarity using TF-IDF, cosine similarity, and Jaccard index. Use for plagiarism detection, duplicate finding, or content matching.

> 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.

Writing controller handler functions

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

Invoke COORD_ENGINE for scheduling engine work

Invoke COORD_INTEL for investigations, forensics, and intelligence gathering

Invoke COORD_TOOLING for tools and skills development