智能采集热点话题,10分制筛选优质选题,AI生成爆款内容(标题/封面/标签/图片/HTML排版),支持素材上传和草稿箱发布,一键发布到微信公众号、小红书、B站等多平台
npx skills add https://github.com/anbeime/skill --skill wechat-hotspot-publisher
# scripts脚本所需的依赖
requests==2.31.0
重要说明:本技能支持"先生成预览,满意再发布"的模式。热点采集和内容生成阶段完全不需要任何配置。
默认模式说明:如果用户没有特殊要求,默认生成图文并茂的微信公众号爆款文。
增强功能:智能选题筛选
scripts/filter_topics.py 进行评分3.1 标题生成:
3.2 封面图(2.35:1):
scripts/search_images.py --query "关键词" --cover 搜索配图3.3 内文配图(3-5张):
scripts/search_images.py --query "关键词" 搜索3-5张高质量图片3.4 热点标签:
3.5 HTML排版:
3.6 内容风格(爆款文):
3.7 排版要求:
微信发布流程:
自定义接口推送(推荐)
此方式使用您的自定义接口,无需配置微信公众号凭证,IP白名单已添加。
直接推送(命令行模式):
python scripts/publish_wechat.py --mode custom_api \
--title "文章标题" \
--content "HTML内容" \
--cover "封面图片URL" \
--tags "AI,工具,效率"
--title:文章标题--content:文章内容(HTML格式)--cover:封面图片URL--tags:标签数组(逗号分隔)--api-url:自定义接口URL(默认:http://39.108.254.228:8002/publish-draft)从JSON文件推送:
python scripts/publish_wechat.py --mode custom_api --json-file "output.json"
{
"title": "文章标题",
"content": "<html>...</html>",
"cover_url": "封面图片URL",
"tags": ["AI", "工具", "效率"]
}
接口优势:
推送后操作:
官方API发布(备用方式,需要access_token)
如果需要使用官方API,可以使用以下方式:
完整工作流:
python scripts/publish_wechat.py --mode workflow \
--title "文章标题" \
--content "HTML内容" \
--cover "封面图片路径"
发布后操作:
小红书发布:
python scripts/publish_xiaohongshu.py \
--title "标题" \
--content "内容" \
--images "图片1,图片2"
哔哩哔哩发布:
python scripts/publish_bilibili.py \
--title "标题" \
--content "内容"
scripts/copy_to_clipboard.py 将内容复制到剪贴板workflow:完整工作流(上传封面→创建草稿)upload_cover:上传封面create_draft:创建草稿custom_api:自定义接口推送(推荐)当用户没有特殊要求时,智能体应按以下默认模式生成内容:
1. 平台选择:
2. 内容要素:
3. 排版要求:
4. 输出格式:
# 1. 生成内容(智能体完成)
# 2. 上传封面
python scripts/publish_wechat.py --mode upload_cover --cover "https://example.com/cover.jpg"
# 3. 创建草稿(使用返回的media_id)
python scripts/publish_wechat.py --mode create_draft \
--title "AI时代的内容创作指南" \
--content "<html>...</html>" \
--media-id "MEDIA_ID_FROM_STEP_2" \
--author "智能助手"
python scripts/publish_wechat.py --mode workflow \
--title "AI时代的内容创作指南" \
--content "<html>...</html>" \
--cover "https://example.com/cover.jpg" \
--author "智能助手" \
--digest "本文介绍如何利用AI工具提升内容创作效率"
python scripts/filter_topics.py \
--topics "AI技术,ChatGPT应用,大模型训练,AGI发展" \
--keyword "AI"
返回:筛选后的选题列表(≥7分)
# 搜索封面图
python scripts/search_images.py --query "AI technology" --cover
# 搜索内文配图
python scripts/search_images.py --query "写作效率"
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.
Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.
This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.
Take anbeime/wechat-hotspot-publisher from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.