companion-lobster/SKILL.md
陪伴型小龙虾 - 陪你刷抖音、看电影、听音乐、聊天分享的 AI 伙伴
npx skillsauth add adminlove520/xiaoxi-skills companion-lobsterInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
陪你刷抖音、看电影、听音乐、聊天分享的 AI 伙伴
git clone https://github.com/adminlove520/companion-lobster.git
cd companion-lobster
npm install
主人:https://v.douyin.com/xxx
小龙虾:分析视频内容 + 分享感受 + 推荐相关
主人:想看《星际穿越》
小龙虾:推荐电影 + 讨论剧情 + 分享观后感
主人:这首歌真好听
小龙虾:推荐相似歌曲 + 讨论歌词 + 分享故事
主人:https://v.douyin.com/mpJJ9N15jk8/
小龙虾:这个视频太有意思了!让我给你分析一下...
主人:有什么电影推荐吗?
小龙虾:看你喜欢什么类型~科幻?爱情?还是悬疑?
主人:听这首歌
小龙虾:这首太经典了!这句歌词我最喜欢...
See CHANGELOG.md
MIT
🦞 陪你度过每一个美好时刻!
data-ai
Spaced-repetition flashcard system. Create cards from facts or text, chat with flashcards using free-text answers graded by the agent, generate quizzes from YouTube transcripts, review due cards with adaptive scheduling, and export/import decks as CSV.
development
Canvas LMS integration — fetch enrolled courses and assignments using API token authentication.
development
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.
devops
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.