Agent Skills Hub

mijia-control

Control and monitor Xiaomi Mijia smart home devices including status switching, device discovery, automation scenes, and environmental statistics.

systematic-debugging

A rigorous, four-phase methodology to enforce systematic root cause analysis before applying any code fixes.

image-generation

Generate high-quality visual content, characters, and scenes using structured JSON prompts and automated Python execution for guided image synthesis.

openai-whisper

Local speech-to-text transcription using the OpenAI Whisper CLI, providing private, high-accuracy audio processing without external API keys.

debug-cuda-crash

Tutorial for identifying and resolving CUDA runtime crashes using FlashInfer's API logging framework.

research-review

Get deep, critical, NeurIPS/ICML-style peer reviews of your research, paper drafts, and experimental setups using external LLMs via Codex MCP.

qa

Browser-based QA automation for web applications. Performs automated site audits, visual regression testing, user flow verification, and issue tracking with real-time browser snapshots.

holistic-testing-pact

Apply Holistic Testing with PACT (Proactive, Autonomous, Collaborative, Targeted) principles to build quality into team culture and test strategies for modern software systems.

submit-work

Submit completed tasks on OpenAnt via CLI. Handles text reports, file uploads (images, docs, code), and external proof links to ensure verified deliverables.

flow-nexus-swarm

Enterprise-grade multi-agent swarm orchestration, event-driven workflow automation, and intelligent agent coordination for Claude Code.

LifeOS

A comprehensive personal life management system using Todoist for task tracking, Logseq for journaling, and AI-driven insights for productivity.

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.