media-skills

Publish Xiaohongshu image-notes by attaching to a logged-in Chrome via CDP (--cdp-url). Use when the user asks to 发布小红书图文, 上传小红书笔记, or validate creator login in CDP Chrome.

技术自媒体文章写作工作流。支持自定义选题；无明确素材时优先委派 subagent 调用 news-skill 获取热点并筛选选题，否则 inline 执行同等流程。经提纲审批后按写作指南完成写作，输出含配图占位符的 Markdown 文章，支持审查修改与写作经验复盘。使用场景：用户需要写技术博客、自媒体文章、AI/编程/产品类科普文；支持平台参数（xiaohongshu、wechat）加载对应平台写作规范。触发词：写文章、写一篇、帮我写、创作文章、生成文章。

每日科技资讯聚合工具，从多个优质RSS源（Anthropic、OpenAI、GitHub Blog、V2EX、宝玉、Karpathy、极客公园等）获取近48小时的技术内容，由你（LLM）直接完成筛选、评分、翻译和摘要，最终生成中文Markdown日报。当用户需要获取每日科技资讯、生成技术日报、查看今日AI/编程/开源/产品动态时使用。触发词：每日资讯、今日科技、技术日报、生成日报。

Posts WeChat Official Account (微信公众号) articles to Draft Box (草稿箱) via Official API. Supports HTML/Markdown/plain text input. Markdown workflows default to converting ordinary external links into bottom citations for WeChat-friendly output.

Save Markdown articles into the CSDN draft box and fetch CSDN creator analytics/article performance data with storageState.json or cookies.json. Use when the user asks to 保存 CSDN 草稿, 准备 CSDN 文章草稿, 批量生成 CSDN 草稿, 抓取 CSDN 创作中心运营数据, 获取最近文章的 7 日动态数据, 校验 CSDN 创作中心登录态, or export CSDN creator storage state.

Saves Markdown articles to Juejin drafts and fetches creator analytics using Playwright storageState.json or cookie JSON. Supports recent content analytics, 7-day article trends, and follower analytics.

Fetches WeChat Official Account analytics (content analysis and user analysis) from mp.weixin.qq.com using user-provided Playwright storageState.json or Cookie JSON. Supports Windows, macOS, and Linux, including Ubuntu servers without GUI.

为写好的 Markdown 文章设计配图提示词并生成图片。自动解析文章中的配图占位符，设计封面图和正文配图的生成提示词，调用 baoyu-image-gen 生成图片，将图片存放到文章对应目录，并将图片路径回写到文章中。触发场景：用户完成文章写作后需要配图、为已有 Markdown 文章生成插图、帮我配图、生成文章图片。

AI image generation with OpenAI, Google, OpenRouter, DashScope, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.