Loading...
Loading...
Found 693 Skills
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
vox.ai 개발 베스트 프랙티스를 적용한다. (1) 한국어 음성 에이전트 system prompt 설계/작성/리팩터링(템플릿, {{...}} 변수 주입, 필러 옵션, Character normalization, 도구/무음 액션, 테스트/운영), (2) vox MCP 서버(https://mcp.tryvox.co/, Streamable HTTP, OAuth 또는 API token)를 ChatGPT/Claude Desktop/Claude Code/Cursor/OpenCode/Codex/VS Code Copilot 등에 연결할 때 사용한다.
Fully autonomous epic execution. Runs until ALL children are CLOSED. Local mode uses /swarm with runtime-native spawning (Codex sub-agents or Claude teams). Distributed mode uses /swarm --mode=distributed (tmux + Agent Mail) for persistence and coordination. NO human prompts, NO stopping.
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto review loop minimax" or "minimax review".
Send text messages to specified contacts via the WeChat desktop client on macOS. Used when the user provides a contact name and message content, such as "Send a WeChat message to Zhang San: xxx", "Open WeChat to send a message to someone", "Send specified text via WeChat". The WeChat desktop client must be installed before running, and accessibility permissions must be granted to the current terminal or Codex. Only exact matching is performed during execution: first search for the contact, then verify that the current session title exactly matches the target; stop if the match fails to avoid sending messages by mistake.
Sync user-level AI configs (~/.claude/, ~/.codex/) with the dotfiles/ directory. Use when dotfiles drift, after sessions that change permissions/hooks, on new machines, or when the user says "sync", "pull dotfiles", "push configs".
Generate migration deliverables for bringing relevant Megatron changes into MindSpeed after branch alignment and impact mapping are complete. Use when Codex already has a confirmed MindSpeed-to-Megatron branch pairing and needs to produce a migration report, candidate patch, or guarded workspace edits instead of redoing upstream analysis from scratch.
Turns a free-form project description into PROJECT_MANIFEST.md and SOFTWARE_FACTORY_MANIFEST.md for a 6-agent software factory pipeline. Agent-agnostic: works in Claude Code, Codex CLI, Gemini CLI.
Connect AI coding agents (Claude Code, Cursor, VS Code, OpenAI Codex) to Grafana Cloud via the Model Context Protocol (MCP) server. Use when the user asks to connect Claude Code to Grafana, set up MCP for Grafana, use Grafana tools in Cursor, query Grafana from an AI agent, configure the Grafana MCP server, or make AI agents interact with Grafana Cloud APIs. Triggers on phrases like "MCP server", "connect Claude Code to Grafana", "Grafana MCP", "AI agent Grafana", "Claude Grafana tools", "Cursor Grafana", or "agent observability".
Fetch recent posts from one or more X/Twitter accounts through twitterapi.io, output structured JSON/CSV records, optionally sync records to Feishu/Lark Bitable through feishu-cli, and optionally guide recurring execution through OpenClaw, Codex automations, cron, or launchd. Use when the user wants to monitor X bloggers, collect recent tweets, export tweet metrics, append tweets to Feishu Bitable, or set up a scheduled Twitter/X account tracking workflow.
Multi-model consensus council for validation, research, and brainstorming. Spawns parallel judges with configurable perspectives and optional explorer sub-agents using runtime-native backends (Codex sub-agents or Claude teams). Modes: validate, brainstorm, research. Triggers: council, validate, brainstorm, critique, research, analyze, multi-model, consensus.