Skill UI

This skill drives an existing browser instance using the Chrome DevTools Protocol (CDP). It is essential for complex web automation tasks that require visible interaction, JavaScript execution, or handling authenticated, stateful sessions. Use it when static data fetching is insufficient, such as simulating user logins, interacting with iframes, or performing visual verification. Supports headless and remote environments.

A comprehensive utility for managing complex cmux topologies, including workspaces, panes, and surfaces. This tool is essential for inspecting, controlling, and monitoring multiple AI coding agents running in parallel within a macOS terminal environment. It supports advanced functionalities such as browser automation and real-time status notifications, optimizing developer workflows.

Execute discrete, bounded coding, review, or verification tasks using the Codex CLI as an isolated subagent. This tool is ideal for tasks requiring explicit file ownership, such as isolated refactoring, feature implementation, or independent code verification, without relying on continuous conversational context. It runs in a safe sandbox environment.

Run comprehensive, read-only exposure checks against your local machine or project directories in response to security advisories and CVEs. This tool systematically checks various ecosystems (Node.js, Python, Homebrew, etc.) to generate a structured, non-invasive audit report, helping users understand their actual risk exposure without making any system changes.

This guide details the comprehensive workflow for distributing a single AI skill across various local agent skill directories (Codex, Claude, Pi, Hermes). It addresses canonical locations, symlink management, and specific synchronization commands to ensure that all agents detect the latest skill version while correctly navigating common development pitfalls.

This skill is designed to mitigate false-positive safety triggers from strict AI classifiers (e.g., cyber, bio/chem, reasoning). It operates by making minimal, surgical edits to sensitive phrases, abstracting away specific domains or actions while preserving the original benign intent and structure. It ensures the prompt remains policy-compliant without losing its core purpose, making it ideal for academic or defensive inquiries.

This skill helps developers create highly focused, folder-specific documentation (`CLAUDE.md` and `AGENTS.md`). It systematically analyzes all files in a target directory to extract project purpose, operational constraints, naming conventions, and critical decisions. This deep context ensures that future AI agents (like Claude or Codex) operate with localized knowledge, preventing them from relying on global, generalized instructions and improving their accuracy in that specific domain.

Drafts high-engagement, long-form LinkedIn posts using 16 reverse-engineered hook formulas. Instead of writing randomly, the skill focuses on the desired outcome (comments, reposts, likes, or saves). It integrates the user's voice, adheres to modern formatting rules, and includes an AI-tell scrub pass to ensure the content reads authentically and humanly.

This skill enforces highly efficient coding practices, guiding the AI to write the simplest, most direct code possible. It strictly follows an 'Efficiency Ladder' (YAGNI, reusing existing code, standard library, etc.) to prevent over-engineering, unnecessary abstractions, and boilerplate. Use this when the goal is maximum efficiency with minimal code.

This skill executes the DeepSWE benchmark, a comprehensive coding-agent evaluation suite. It uses OpenRouter and mini-swe-agent to score various Large Language Models (LLMs) on 113 tasks, providing reproducible results for model comparison, development assessment, and research benchmarking. Use this when a standardized, deep evaluation of LLM coding capabilities is required.

This skill guides users through complex, multi-step processes such as installation, configuration, or initial setup. It breaks down the process into small, atomic actions, presenting only the current required step and a limited, manageable checklist of remaining tasks. Ideal for onboarding new users or executing lengthy technical setups.

This skill acts as a critical reality-check layer before code generation. It ensures that every function call, import, method, and variable the agent uses is provably available in the user's specific installed environment and version. It prevents runtime bugs caused by hallucinated or improperly assumed APIs, making the generated code robust and reliable.