<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>WeChat Official Account | Attack on Life</title><link>https://en.1991421.cn/tag/wechat-official-account/</link><atom:link href="https://en.1991421.cn/tag/wechat-official-account/index.xml" rel="self" type="application/rss+xml"/><description>WeChat Official Account</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-US</language><lastBuildDate>Wed, 11 Mar 2026 23:25:13 +0800</lastBuildDate><image><url>https://en.1991421.cn/media/sharing.png</url><title>WeChat Official Account</title><link>https://en.1991421.cn/tag/wechat-official-account/</link></image><item><title>OpenClaw (Lobster) Implementing Social Media Image-Text Publishing</title><link>https://en.1991421.cn/2026/03/11/openclaw-implement-social-media-publishing/</link><pubDate>Wed, 11 Mar 2026 23:25:13 +0800</pubDate><guid>https://en.1991421.cn/2026/03/11/openclaw-implement-social-media-publishing/</guid><description>&lt;blockquote>
&lt;p>Lobster is quite popular, but it doesn&amp;rsquo;t produce any new technology itself. It simply provides mainstream IM tools with the capability to leverage AI. So I thought it could also solve the daily publishing workflow for social media creators.&lt;/p>
&lt;/blockquote>
&lt;p>&lt;figure class="image-figure">
&lt;img
src="https://static.1991421.cn/2026/03/2026-03-12-002100.jpeg"
alt="https://static.1991421.cn/2026/03/2026-03-12-002100.jpeg"
loading="lazy"
decoding="async"
class="rounded-lg"
/>
&lt;/figure>&lt;/p>
&lt;h2 id="existing-skills">
&lt;a class="heading-anchor-link" href="#existing-skills">Existing Skills&lt;/a>
&lt;button
class="heading-anchor"
type="button"
data-anchor="existing-skills"
aria-label="Copy anchor link"
title="Copy anchor link"
>
&lt;span class="heading-anchor-wrap" aria-hidden="true">
&lt;svg class="heading-anchor-icon heading-anchor-icon-default" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" fill="currentColor">
&lt;path d="M0 256C0 167.6 71.6 96 160 96h72c13.3 0 24 10.7 24 24s-10.7 24-24 24H160C98.1 144 48 194.1 48 256s50.1 112 112 112h72c13.3 0 24 10.7 24 24s-10.7 24-24 24H160C71.6 416 0 344.4 0 256zm576 0c0 88.4-71.6 160-160 160H344c-13.3 0-24-10.7-24-24s10.7-24 24-24h72c61.9 0 112-50.1 112-112s-50.1-112-112-112H344c-13.3 0-24-10.7-24-24s10.7-24 24-24h72c88.4 0 160 71.6 160 160zM184 232H392c13.3 0 24 10.7 24 24s-10.7 24-24 24H184c-13.3 0-24-10.7-24-24s10.7-24 24-24z">&lt;/path>
&lt;/svg>
&lt;svg class="heading-anchor-icon heading-anchor-icon-copied" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" fill="currentColor">
&lt;path d="M256 48C141.1 48 48 141.1 48 256s93.1 208 208 208 208-93.1 208-208S370.9 48 256 48zm107.1 145.1L230.6 325.6c-6.2 6.2-16.4 6.2-22.6 0l-59-59c-6.2-6.2-6.2-16.4 0-22.6s16.4-6.2 22.6 0l47.7 47.7 121.1-121.1c6.2-6.2 16.4-6.2 22.6 0s6.3 16.4.1 22.5z">&lt;/path>
&lt;/svg>
&lt;/span>
&lt;/button>
&lt;/h2>&lt;p>First, let me introduce some existing skills. You can directly ask your AI to install these, and you can ask the AI for usage instructions.&lt;/p>
&lt;ul>
&lt;li>&lt;a href="https://github.com/JimLiu/baoyu-skills/tree/main/skills" target="_blank" rel="noopener">https://github.com/JimLiu/baoyu-skills/tree/main/skills&lt;/a>
Explanation: From Baoyu&amp;rsquo;s skills, I currently only use baoyu-cover-image (for generating article cover image prompts) and baoyu-post-to-wechat (for solving WeChat Official Account publishing issues).&lt;/li>
&lt;/ul>
&lt;p>For other platforms like Toutiao and Xiaohongshu, I&amp;rsquo;m currently developing them myself because they&amp;rsquo;re highly customized, so I won&amp;rsquo;t share them for now.&lt;/p>
&lt;h2 id="principles-of-social-media-publishing">
&lt;a class="heading-anchor-link" href="#principles-of-social-media-publishing">Principles of Social Media Publishing&lt;/a>
&lt;button
class="heading-anchor"
type="button"
data-anchor="principles-of-social-media-publishing"
aria-label="Copy anchor link"
title="Copy anchor link"
>
&lt;span class="heading-anchor-wrap" aria-hidden="true">
&lt;svg class="heading-anchor-icon heading-anchor-icon-default" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" fill="currentColor">
&lt;path d="M0 256C0 167.6 71.6 96 160 96h72c13.3 0 24 10.7 24 24s-10.7 24-24 24H160C98.1 144 48 194.1 48 256s50.1 112 112 112h72c13.3 0 24 10.7 24 24s-10.7 24-24 24H160C71.6 416 0 344.4 0 256zm576 0c0 88.4-71.6 160-160 160H344c-13.3 0-24-10.7-24-24s10.7-24 24-24h72c61.9 0 112-50.1 112-112s-50.1-112-112-112H344c-13.3 0-24-10.7-24-24s10.7-24 24-24h72c88.4 0 160 71.6 160 160zM184 232H392c13.3 0 24 10.7 24 24s-10.7 24-24 24H184c-13.3 0-24-10.7-24-24s10.7-24 24-24z">&lt;/path>
&lt;/svg>
&lt;svg class="heading-anchor-icon heading-anchor-icon-copied" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" fill="currentColor">
&lt;path d="M256 48C141.1 48 48 141.1 48 256s93.1 208 208 208 208-93.1 208-208S370.9 48 256 48zm107.1 145.1L230.6 325.6c-6.2 6.2-16.4 6.2-22.6 0l-59-59c-6.2-6.2-6.2-16.4 0-22.6s16.4-6.2 22.6 0l47.7 47.7 121.1-121.1c6.2-6.2 16.4-6.2 22.6 0s6.3 16.4.1 22.5z">&lt;/path>
&lt;/svg>
&lt;/span>
&lt;/button>
&lt;/h2>&lt;ol>
&lt;li>
&lt;p>For platforms like Xiaohongshu and Toutiao, since they have PC web interfaces, you can use Playwright to simulate browser operations. Of course, you could also use API interfaces, but they&amp;rsquo;re too easily blocked. I personally recommend directly manipulating the web pages.&lt;/p>
&lt;/li>
&lt;li>
&lt;p>For WeChat Official Account, since there&amp;rsquo;s an &lt;a href="https://developers.weixin.qq.com/platform" target="_blank" rel="noopener">official API&lt;/a>, the aforementioned Skill recommends using the official API method for publishing, as it&amp;rsquo;s more stable. Of course, Baoyu&amp;rsquo;s skill is compatible with both API and non-API approaches. Without an API, it naturally falls back to browser page operations.&lt;/p>
&lt;/li>
&lt;/ol>
&lt;h2 id="image-generation">
&lt;a class="heading-anchor-link" href="#image-generation">Image Generation&lt;/a>
&lt;button
class="heading-anchor"
type="button"
data-anchor="image-generation"
aria-label="Copy anchor link"
title="Copy anchor link"
>
&lt;span class="heading-anchor-wrap" aria-hidden="true">
&lt;svg class="heading-anchor-icon heading-anchor-icon-default" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" fill="currentColor">
&lt;path d="M0 256C0 167.6 71.6 96 160 96h72c13.3 0 24 10.7 24 24s-10.7 24-24 24H160C98.1 144 48 194.1 48 256s50.1 112 112 112h72c13.3 0 24 10.7 24 24s-10.7 24-24 24H160C71.6 416 0 344.4 0 256zm576 0c0 88.4-71.6 160-160 160H344c-13.3 0-24-10.7-24-24s10.7-24 24-24h72c61.9 0 112-50.1 112-112s-50.1-112-112-112H344c-13.3 0-24-10.7-24-24s10.7-24 24-24h72c88.4 0 160 71.6 160 160zM184 232H392c13.3 0 24 10.7 24 24s-10.7 24-24 24H184c-13.3 0-24-10.7-24-24s10.7-24 24-24z">&lt;/path>
&lt;/svg>
&lt;svg class="heading-anchor-icon heading-anchor-icon-copied" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" fill="currentColor">
&lt;path d="M256 48C141.1 48 48 141.1 48 256s93.1 208 208 208 208-93.1 208-208S370.9 48 256 48zm107.1 145.1L230.6 325.6c-6.2 6.2-16.4 6.2-22.6 0l-59-59c-6.2-6.2-6.2-16.4 0-22.6s16.4-6.2 22.6 0l47.7 47.7 121.1-121.1c6.2-6.2 16.4-6.2 22.6 0s6.3 16.4.1 22.5z">&lt;/path>
&lt;/svg>
&lt;/span>
&lt;/button>
&lt;/h2>&lt;p>Compared to GPT and Gemini, Gemini is much more powerful. Chinese character rendering is now good without obvious issues. Since API pricing is a threshold issue and costs are a concern, I&amp;rsquo;m using the web-based solution directly. That is, using Playwright to simulate browser operations, generating images directly on the web page, and downloading them locally. This way, you can continue with image-text publishing.&lt;/p>
&lt;h2 id="writing-skills">
&lt;a class="heading-anchor-link" href="#writing-skills">Writing Skills&lt;/a>
&lt;button
class="heading-anchor"
type="button"
data-anchor="writing-skills"
aria-label="Copy anchor link"
title="Copy anchor link"
>
&lt;span class="heading-anchor-wrap" aria-hidden="true">
&lt;svg class="heading-anchor-icon heading-anchor-icon-default" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" fill="currentColor">
&lt;path d="M0 256C0 167.6 71.6 96 160 96h72c13.3 0 24 10.7 24 24s-10.7 24-24 24H160C98.1 144 48 194.1 48 256s50.1 112 112 112h72c13.3 0 24 10.7 24 24s-10.7 24-24 24H160C71.6 416 0 344.4 0 256zm576 0c0 88.4-71.6 160-160 160H344c-13.3 0-24-10.7-24-24s10.7-24 24-24h72c61.9 0 112-50.1 112-112s-50.1-112-112-112H344c-13.3 0-24-10.7-24-24s10.7-24 24-24h72c88.4 0 160 71.6 160 160zM184 232H392c13.3 0 24 10.7 24 24s-10.7 24-24 24H184c-13.3 0-24-10.7-24-24s10.7-24 24-24z">&lt;/path>
&lt;/svg>
&lt;svg class="heading-anchor-icon heading-anchor-icon-copied" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" fill="currentColor">
&lt;path d="M256 48C141.1 48 48 141.1 48 256s93.1 208 208 208 208-93.1 208-208S370.9 48 256 48zm107.1 145.1L230.6 325.6c-6.2 6.2-16.4 6.2-22.6 0l-59-59c-6.2-6.2-6.2-16.4 0-22.6s16.4-6.2 22.6 0l47.7 47.7 121.1-121.1c6.2-6.2 16.4-6.2 22.6 0s6.3 16.4.1 22.5z">&lt;/path>
&lt;/svg>
&lt;/span>
&lt;/button>
&lt;/h2>&lt;p>Although there are some solutions online, whether for security or customization reasons, you always end up needing to modify them. So how to write efficiently? Here&amp;rsquo;s my approach: I use the Chrome Claude plugin to write directly on the target page. This way, Claude helps generate the rough code and also verifies its effectiveness. Then I can copy the basic logic and have OpenClaw re-encapsulate it.&lt;/p>
&lt;h2 id="final-thoughts">
&lt;a class="heading-anchor-link" href="#final-thoughts">Final Thoughts&lt;/a>
&lt;button
class="heading-anchor"
type="button"
data-anchor="final-thoughts"
aria-label="Copy anchor link"
title="Copy anchor link"
>
&lt;span class="heading-anchor-wrap" aria-hidden="true">
&lt;svg class="heading-anchor-icon heading-anchor-icon-default" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 576 512" fill="currentColor">
&lt;path d="M0 256C0 167.6 71.6 96 160 96h72c13.3 0 24 10.7 24 24s-10.7 24-24 24H160C98.1 144 48 194.1 48 256s50.1 112 112 112h72c13.3 0 24 10.7 24 24s-10.7 24-24 24H160C71.6 416 0 344.4 0 256zm576 0c0 88.4-71.6 160-160 160H344c-13.3 0-24-10.7-24-24s10.7-24 24-24h72c61.9 0 112-50.1 112-112s-50.1-112-112-112H344c-13.3 0-24-10.7-24-24s10.7-24 24-24h72c88.4 0 160 71.6 160 160zM184 232H392c13.3 0 24 10.7 24 24s-10.7 24-24 24H184c-13.3 0-24-10.7-24-24s10.7-24 24-24z">&lt;/path>
&lt;/svg>
&lt;svg class="heading-anchor-icon heading-anchor-icon-copied" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512" fill="currentColor">
&lt;path d="M256 48C141.1 48 48 141.1 48 256s93.1 208 208 208 208-93.1 208-208S370.9 48 256 48zm107.1 145.1L230.6 325.6c-6.2 6.2-16.4 6.2-22.6 0l-59-59c-6.2-6.2-6.2-16.4 0-22.6s16.4-6.2 22.6 0l47.7 47.7 121.1-121.1c6.2-6.2 16.4-6.2 22.6 0s6.3 16.4.1 22.5z">&lt;/path>
&lt;/svg>
&lt;/span>
&lt;/button>
&lt;/h2>&lt;p>So far, the most critical image generation and publishing are sorted out. This actually saves considerable time, and it also makes it easy to do multi-platform simultaneous publishing. So, let&amp;rsquo;s get to it!&lt;/p></description></item></channel></rss>