Agent Skills Hub

deepwiki

Search and retrieve AI-generated documentation, architecture guides, and API references for 300+ popular GitHub repositories using DeepWiki and MCP.

claude-opus-4-5-migration

Migrate your codebase, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to the advanced Opus 4.5 model with automated configuration adjustments.

creating-opencode-agents

Expert guidance and configuration standards for creating specialized OpenCode AI agents, including YAML frontmatter, tool permissions, and operational modes.

dev

Development and maintenance of the PWAFire library: build PWA API modules, handle feature detection, manage testing, and contribute to codebase following strict sync/async patterns and error handling requirements.

using-superpowers

The foundational skill for the Superpowers methodology. Ensures agents correctly identify and invoke required development skills before starting any task or conversation.

refly

Base ecosystem skill for Refly. Creates, discovers, and runs domain-specific skills, routes user intent to workflows via symlinks, and automates multi-step pipelines via the Refly CLI.

e2b

Secure, isolated cloud sandbox environments for executing AI-generated code, running multi-language scripts, managing file systems, and integrating tools via the E2B MCP gateway.

docs-generator

Generate hierarchical, AI-optimized documentation structures (AGENTS.md, agent.d) to streamline codebase context, setup, and navigation for AI coding assistants and developers.

gemini-vision

Implement Google Gemini API vision capabilities for image/document analysis including captioning, object detection, segmentation, and multi-image comparison.

peon-ping-log

Track exercise reps like pushups and squats for the Peon Trainer. Log progress directly through your AI agent to trigger voice lines and stay motivated while coding.

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.

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.