Other

Trade (and keep full trading state) on the Belief Markets platform

图片识别与分析工具。使用视觉大模型识别图片内容，输出详细客观的识别结果供主模型分析。当用户发图片时，主模型必须直接调用此 skill，然后基于识别结果进行分析和回答。支持 SiliconFlow（默认）、OpenAI、Anthropic 等多服务商。

No description provided.

Prepare a skill for public release. Run through this checklist before publishing any skill to ensure it's reusable, clean, safe, and well-documented.

Fetches and summarizes recent arXiv and Hugging Face papers with Agentic Paper Digest. Use when the user wants a paper digest, a JSON feed of recent papers, or to run the arXiv/HF pipeline.

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

图片生成技能，当用户需要生成图片、创建图像、编辑/修改/调整已有图片时使用此技能。支持10种图片比例（1:1、16:9、9:16等）和3种分辨率（1K、2K、4K），支持文生图和图生图编辑。

Manage torrents with qBittorrent. Use when the user asks to "list torrents", "add torrent", "pause torrent", "resume torrent", "delete torrent", "check download status", "torrent speed", "qBittorrent stats", or mentions qBittorrent/qbit torrent management.

No description provided.

No description provided.

No description provided.

Transkribiert Audio-Dateien mit Speaker Diarization (wer spricht wann).