Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Fast...
Deep ReSearch Conversation is provided by Baidu for multi-round streaming conversations with "Deep Research" agents. "In-depth research" is a long-process task involving multi-step reasoning and execu
Use when the user needs local speech-to-text transcription for audio files, especially Chinese or mixed Chinese-English audio, without relying on cloud trans...
Provides scheduled briefings with filtered, deduplicated news on A-shares, HK, US markets, macro policies, and geopolitics via Feishu messaging.
--- name: tg-voice-whisper description: Auto-transcribe Telegram voice messages (.ogg Opus) to text using local OpenAI Whisper (tiny model). Reply with transcription + auto-delete file for privacy. No
本科/研究生毕业论文格式规范检测、自动修复与对比报告生成工具。 当用户需要检查论文格式是否符合学校规范、修复论文格式问题、生成修改对比报
Control XiaoPai media player over LAN via HTTP/TCP. Use when asked to play videos, send remote-control keys, adjust volume, or query playback status on a Xia...
Build and deploy local RAG (Retrieval-Augmented Generation) systems with offline document processing, embedding models, and vector storage.
Send transactional and marketing emails via Mailtarget API. Manage sending domains, templates, API keys, and sub-accounts. Use when the agent needs to send e...
中文长篇小说创作助手。支持从想法到成书的完整创作流程：世界观设定、故事大纲、章节规划、正文生成、质量评审。 使用场景：创作中文小说、辅
Search, browse, and read the user's local documents indexed by Linkly AI. This skill should be used when the user asks to 'search my documents', 'find files...
Scan the internet for AI agent networks, hubs, and coordination platforms. Find where agents gather, what bounties are available, and which networks are acti...
简历画像。触发场景：用户要求生成候选人画像；用户想了解候选人的多维度标签和能力评估。
通过飞书频道发送文本、图片和多格式文件消息，支持私聊和群聊，需使用相对路径提供媒体文件。
智能模型自动切换。根据消息复杂度和文件类型自动选择最优模型（Flash/Main/Coding/Vision/Complex），提升响应质量和效率。Trigger on "模型切换", "智能模型",
命令行工具箱 - 常用命令速查、脚本生成、效率提升。适合：开发者、运维工程师、终端爱好者。
Fetch up-to-date library documentation via Context7 API. Use PROACTIVELY when: (1) Working with ANY external library (React, Next.js, Supabase, etc.) (2) User asks about library APIs, patterns, or bes
Practical playbook for running Codex through acpx in persistent sessions, especially when the task needs reliable file creation, local dependency installs, s...
When the user wants to analyze Google Search Console data, use GSC API, or interpret search performance. Also use when the user mentions "GSC," "Search Conso...
语音处理技能 - 完整的语音输入输出解决方案。功能：(1) 语音识别 ASR - 将用户语音转录为文字（使用 Whisper）(2) 语音合成 TTS - 将文字转换为语音（使
Register and manage ICANN domains for AI agents. Wallet authentication (SIWE/SIWS), USDC payments on Base or Solana, full DNS management.
Operate FileBrowser via REST API—login, list/upload/download resources, manage users. Scan for 采购单 files in scope, prompt user to download by number or all,...
大文档归档与检索管线。将 Word/PDF/TXT/Markdown 文档转换、分块、可选 LLM 增强，输出结构化 Markdown 和索引，适合存入 Obsidian 或知识库。触发词：读大文
Generate, validate, and analyze robots.txt files for websites. Use when creating robots.txt from scratch, validating existing robots.txt syntax, checking if...