Agent Skills Hub

tavily-web

Advanced web search, content extraction, and site crawling capabilities using the Tavily API, optimized for AI agent research and data gathering.

evaluation

Build systematic evaluation frameworks for AI agents using multi-dimensional rubrics, LLM-as-a-judge, and regression testing to measure performance, quality, and context engineering effectiveness.

podcast-generation

Generate real-time AI podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model with WebSocket streaming, complete with PCM to WAV conversion and frontend playback integration.

obsidian-markdown-structure

Validate and enforce consistent markdown document structure, including YAML frontmatter positioning, correct heading hierarchy, and logical content organization for Obsidian vaults.

hegelion

Dialectical reasoning and adversarial coding agent for MCP-enabled editors, forcing LLMs to resolve internal contradictions for higher quality outputs.

nano-banana

Automate Python scripting and Gemini-powered image generation using uv. Ideal for creating art, editing images, and running ad-hoc scripts.

debug-distributed

Debugging guide for AReaL distributed training issues, including hangs, NCCL errors, OOM, and numerical consistency in FSDP2/TP/CP/EP.

vvm

VVM (Vibe Virtual Machine) is a language for agentic programs where the LLM acts as the runtime. Orchestrate multi-agent workflows, manage state, and build resilient AI pipelines.

minimax-tts

Perform internet searches using the Zhipu AI web search API to retrieve real-time information, news, and current data.

claude-code

Standardized skill for Claude Code agents to dynamically query OpenRouter model recommendations and metadata via the Claudish CLI.

ship-learn-next

Transform passive learning content like transcripts and tutorials into actionable Ship-Learn-Next cycles with concrete implementation plans and progress-oriented quests.

paper-plan

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