ZJU-REAL/Easel / skills/builtin/skill-wechat-publisher
skill-wechat-publisher
Verified微信公众号文章自动创作与发布工具。给定参考文章、文字或文档,自动搜索整理全网相关信息、生成图文并茂的公众号文章,并发布到微信公众号草稿箱。特别强调反 AI 检测写作。 触发场景(沾边就用):用户提到"公众号 / 微信文章 / 推文 / 公号 / 发文 / mp / 草稿箱 / 群发",或要求把话题/文档/笔记写成公众号文章并发布到微信。
brief.md.example
View on GitHub---
# 必填:贴图的核心主题,帮助 Claude 理解语境
topic: "Claude Code /rewind 命令"
# 可选:配图风格。**正常情况下留空**,会走:
# 账号 newspic_image_style → 全局兜底 infographic-warm(高密度手绘水彩信息图)
# 换配色:infographic-warm(默认暖黄) | infographic-blue(冷蓝) | infographic-dark(深夜) | infographic-mint(薄荷)
# 特殊场景:如果你只想要一句金句大字卡而不是信息图,可以写 quote-card-minimal / tech-card-blue
# 完整列表见 assets/image-styles/README.md 或 `python3 scripts/wechat_api.py list-image-styles`
# image_style: infographic-warm
# 可选:卡片数量。不写按要点数,且必须 ≤ 要点数,≤ 20
card_count: 4
# 可选:贴图标题
title: "Claude Code 里,最有用的命令之一"
# 可选:发到哪个账号。不写用 --account 或 wechat-publisher.yaml 的 default
account: main
---
# 要点
(每行一条,1./2./3. 或 -/*/+ 都行。Claude 会把每条拆成一张卡。
太长的条目会自动按分隔符切成卡面主文字 + 副文字,一般 15 字内主文字效果最好。)
1. /rewind 厉害的地方不是"撤销一下",而是给你一个更对的工作流
2. 你可以输入 /rewind,也可以连续按两次 Esc,快速回滚代码
3. AI 解决不好问题,常常不是因为它不够会写,而是你不敢让它放手试
4. /rewind 的价值,就是把"试错"这件事真正变得可控
# 短文本
(100-300 字。这段会作为贴图的"短描述"显示在微信图片消息里。
这段会过 AI 味 gate —— 别用套话,写具体的人味感受。
不写也行,publish.py 前 Claude 会根据"要点"生成一段填回来。)
/rewind 的价值,不是能把代码撤回来。
是它让你**敢让 AI 放手去试**。
按两次 Esc 就能回到刚才的状态。这件事本身,
比"解决某个具体 bug"要值钱得多。
## 用法
1. 人类写 brief.md(就是本文件)
2. `python3 scripts/newspic_build.py brief.md`
→ 输出 card_plan.json,每张卡配好 Gemini prompt
3. Claude 按 card_plan.json 里每张卡的 prompt 逐张生图,保存到 ./images/01.png、02.png、...
4. (可选)`python3 scripts/ai_score.py brief.md --mode newspic --threshold 45` 手动预检
5. `python3 scripts/publish.py --account main --type newspic --brief brief.md`
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |