Agent Skills Hub

cmux

Control macOS cmux terminal topology, workspaces, and pane layouts via CLI. Ideal for AI coding agents requiring deterministic multi-pane navigation, surface routing, and attention cues.

opencode

Expert guide for OpenCode AI: TUI commands, CLI operations, AGENTS.md configuration, custom agent workflows, and project setup.

skill-template

A standardized template for creating and documenting modular Agent Skills to ensure consistent, efficient context engineering across AI agent systems.

nia

Research agent for Nia: index/search remote codebases, docs, and packages. Optimizes AI context by prioritizing full source indexing over web fetches to reduce hallucinations.

canvas

Interactive terminal UI toolkit for Claude Code. Spawn and control calendar, document, and flight booking interfaces directly within tmux panes.

context-optimization

Optimize agent context windows through KV-caching, observation masking, summarization-based compaction, and context partitioning to reduce costs and latency.

paper-plan

Generate a structured academic paper outline from research narrative, experiment data, and review conclusions.

parallel-worktrees

Create and manage git worktrees for parallel coding sessions. Enable zero-dead-time development by running tests, builds, and multiple branch sessions simultaneously without interference.

figma

Leverage the Figma MCP server to fetch design data, extract assets, and transform Figma nodes into production-ready React and Tailwind code with design system alignment.

manimgl-best-practices

Best practices and code patterns for ManimGL (3Blue1Brown's OpenGL animation engine). Provides templates, rules for 3D/interactive scenes, camera control, and LaTeX math visualization for technical creators.

gemini

CLI interface for Gemini AI, enabling one-shot model inference, text generation, and JSON-formatted data extraction for OpenClaw users.

symbols

Token-efficient codebase navigation through intelligent symbol indexing, domain chunking, and architectural layer filtering. Reduce token usage by 60-95% when exploring or developing complex systems.