huangjihua007-rgb/aiwolfpk
AI狼人杀 - 4个AI互相猜疑，你坐着看戏。多模型PK + 单模型模拟，信息不对称反向锚点机制。
AI狼人杀 - 4个AI互相猜疑，你坐着看戏。多模型PK + 单模型模拟，信息不对称反向锚点机制。
npx skills add huangjihua007-rgb/aiwolfpkAI狼人杀 - 4个AI互相猜疑，你坐着看戏。多模型PK + 单模型模拟，信息不对称反向锚点机制。
Portable Claude Code skills toolkit. Install once, use in every repo.
A curated list of the best AgentOps tools for 2026 — observability, tracing, evaluation, cost monitoring, and guardrails for LLM agents. Covering open-source and SaaS tools with feature benchmarks and architecture guidance.
Codex skills pack without bundled runtime prompt
Make your AI assistant think critically: catch hallucinations, challenge assumptions, resist sycophancy. A cognitive architecture for Copilot. 17 skills, 33 instructions, 20 prompts, 3 agents. Shops the Plugin Mall for 284 more.
Track and analyze Claude Code Skill invocations: frequency, latency, token cost, triggering prompts, success/failure.
Integrate on-device AI using Foundation Models framework, Core ML, and open-source LLM runtimes on Apple Silicon. Covers Foundation Models (LanguageModelSession, @Generable, @Guide, SystemLanguageModel, structured output, tool calling), Core ML (coremltools, model conversion, quantization, palettization, pruning, Neural Engine, MLTensor), MLX Swift (transformer inference, unified memory), and llama.cpp (GGUF, cross-platform LLM). Use when building tool-calling AI features, working with guided generation schemas, converting models, or running on-device inference.