Agent skills for Codex CLI

Internal routing hub for mermaid diagram skills

Design a service mesh deployment — technology selection, mTLS policy, and traffic management config.

Build a library of metacognitive prompts targeting planning, monitoring, or evaluation for a specific task.

Define UX metrics and KPIs that connect design decisions to measurable outcomes.

Use when starting or continuing a Markdown-only Agent Team Mission with Claude Code or Codex background Agents and no Mexus server.

Create HTML technical documentation with code blocks, API workflows, system architecture diagrams, and syntax highlighting.

Comprehensive microservices architecture patterns covering service decomposition, communication, data management, and resilience strategies.

Architect and provision enterprise Azure infrastructure from workload descriptions.

Create a new sequentially numbered database migration with up/down SQL files

Develops and optimizes cross-platform mini-programs for WeChat, Alipay, and Douyin using Native, Taro, or uni-app frameworks.

Full-stack backend architecture and frontend-backend integration guide.

Use this skill when visual quality and design identity matter for a PDF.

Automate Missive tasks via Rube MCP (Composio).

IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or…

Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing.

Create and render OpenSCAD 3D models. Generate preview images from multiple angles, extract customizable parameters, validate syntax, and…

Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output.

Design and execute convergent, explanatory sequential, and exploratory sequential mixed methods research designs

Toolkit for mobile app testing using Maestro MCP.

Produce a mobile feature spec — user story, technical approach, component breakdown, platform-specific considerations, edge cases.

Use when an SGLang, vLLM, TensorRT-LLM, or TokenSpeed serving/model optimization task needs prior model-family PR evidence.