EchoBot

Work on this EchoBot repository when the task changes repository code or runtime behavior: agent loop, skill runtime, tool registry, session flow, routing, roleplay, commands, channels, gateway delivery, FastAPI API, browser UI, scheduling, memory, attachments, images, ASR, TTS, or tests. Use for requests like "修改 EchoBot 逻辑", "排查 route / 会话 / skill / 定时任务问题", "补测试", "重构这个仓库", or "review this EchoBot change".

Use when creating, revising, or validating a skill for this EchoBot repository, including SKILL.md frontmatter, trigger descriptions, project skill folders under skills/, bundled references or scripts or assets or agents, or EchoBot skill discovery, explicit activation, and lazy resource loading. Also use for requests like “更新 skill”, “写 SKILL.md”, “这个 skill 为什么没触发”, or “给 EchoBot 加一个项目内技能”.

Fetch the latest news and headlines from authoritative Chinese and international sources. Use this skill whenever the user asks about news, headlines, hot topics, breaking news, or current events — even casual phrasing like "今天有什么新闻？", "最新科技动态", "财经热点", "体育新闻", "娱乐八卦", "国际新闻", "what's in the news?", "any big stories today?". Covers politics, finance, tech, society, world, sports, and entertainment. Always use this skill for news-related requests, even if the user doesn't say the word "news" explicitly.

Fetch current weather conditions and forecasts — no API key needed. Use this skill whenever the user asks about weather, temperature, rain, wind, humidity, forecast, or whether to bring an umbrella — even casual phrasing like "is it cold outside?", "what's the weather like in Tokyo?", "will it rain tomorrow in Seattle?", or "check the weather for me". Works on Linux, macOS, and Windows without any setup.

Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; web_fetch fails; the site has anti-bot protections; write Python code to scrape/crawl; or write spiders.