Loading...
Loading...
Found 379 Skills
Audits GitHub Actions workflows for security vulnerabilities in AI agent integrations including Claude Code Action, Gemini CLI, OpenAI Codex, and GitHub AI Inference. Detects attack vectors where attacker-controlled input reaches AI agents running in CI/CD pipelines, including env var intermediary patterns, direct expression injection, dangerous sandbox configurations, and wildcard user allowlists. Use when reviewing workflow files that invoke AI coding agents, auditing CI/CD pipeline security for prompt injection risks, or evaluating agentic action configurations.
Convert a web URL into cleaned Markdown with deterministic routing. Use when Codex needs to read article-like content from links and should apply source-aware fetch strategies: default to r.jina.ai for general pages (including X/Twitter), use defuddle.md for YouTube links, and use browser-impersonated extraction for WeChat/Zhihu/Feishu pages with Mozilla Readability cleanup.
Independence-validated parallel fleet that runs each worker (claude -p or codex exec) in its own git worktree. Use when tasks touch non-overlapping files and you need merge-safe isolation (each worker on its own branch). For DAG-ordered one-shot workers with budgets, use dag-fleet. For headless iteration with a reviewer loop, use iterative-fleet.
Named Tmux Manager - Multi-agent orchestration for Claude Code, Codex, and Gemini in tiled tmux panes. Visual dashboards, command palette, context rotation, robot mode API, work assignment, safety system. Go CLI.
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.
Install and configure ToolUniverse with MCP integration for any AI coding client (Cursor, Claude Desktop, Windsurf, VS Code, Codex, Gemini CLI, Trae, Cline, Antigravity, OpenCode, etc.). Covers uv/uvx setup, MCP configuration, API key walkthrough, skill installation, and upgrading. Use when setting up ToolUniverse, configuring MCP servers, troubleshooting installation issues, upgrading versions, or when user mentions installing ToolUniverse or setting up scientific tools.
Use when the user wants to list, search, install, remove, inspect, validate, audit, or update skills. Use when asking "what skills do I have", "is there a skill for X", "check my skills for issues", or "install a skill". Also use when checking skill health across agents (Claude Code, Codex, Agents CLI).
Coding patterns extracted from OpenAI Codex Rust codebase - a production CLI/agent system with strict error handling, async patterns, and workspace organization
Curate a Chinese reading digest from a fixed bundle of RSS and Atom feeds, with a strong preference for AI agent thinking, frontier AI commentary, deep interviews, and non-boring high-signal essays. Use when Codex needs to pull the latest week's posts by default, or a specific day's posts when explicitly requested, summarize them, score each article on a 10-point scale, and output only the posts scoring above 7 in a concise Chinese daily-brief style.
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics
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.