mufeng-wechat-publish-full

Files (4)

• README.md
• SKILL.md
• platforms.md · references/
• upload_github_images.py · scripts/

SKILL.md (first lines)

# Mufeng WeChat Full Publishing Workflow

## Resource Paths

Set the shell variable `SKILL_DIR` to the directory containing the **loaded** `SKILL.md` before running the commands below. Resolve supporting paths from that directory, not the working directory or a fixed user/platform installation path. `$SKILL_DIR` is a shell variable you set, not a host-provided macro.


## Platform Dependencies

Read [references/platforms.md](references/platforms.md) before generating images or publishing. Set `MUFENG_WECHAT_SCRIPT` to the actual `wechat-api.ts` path from an installed `baoyu-post-to-wechat` skill, or use a documented publisher already configured in the host. The variable does not install the publisher. If the dependency or credentials are missing, finish the local article and report that publishing was not executed.

## Overview

End-to-end skill for publishing AI tech blog articles to a WeChat Official Account. Covers every stage: content strategy for platform recommendations, SEO/GEO-friendly Markdown metadata, IP verification, professional visuals, fixed GitHub image hosting, direct Markdown publishing, HTML fallback sanitization, and API draft upload. The default outcome is a verified draft, not public publication. Follow the stages relevant to that outcome; optional backend settings must not block draft upload.

## Core Publishing Rules

- “发布到公众号” defaults to uploading to the selected account's draft box through API. Public publication or mass sending requires an explicit request such as “正式发布” or “群发”; do not infer it from draft upload.
- For article workflows, use API for upload and verification. Do not open the backend, invoke Computer Use, or switch to browser automation unless the user explicitly requests browser operation. An API error is not authorization to switch methods.
- Resolve the account from the user's destination and local EXTEND.md; always pass `--account <alias>` in multi-account setups. For 沐风iOS, use `--account mufeng-ios`. Missing credentials for that account must not silently fall back to another account.
- `wechat-api.ts` calls `draft/add`; it does not submit public publication. Verify the returned `media_id` through `draft/get` on the same account before reporting a verified draft.
- Report local article completion, draft upload, draft read-back verification, and public publication separately. Never claim an unexecuted step succeeded.

- Prefer publishing from the final Markdown file. Do not pre-convert Markdown to HTML unless the user explicitly asks for HTML publishing or the API path is unavailable.
- Every generated or revised Markdown article should have SEO/GEO-friendly YAML frontmatter before publishing.
- Use the fixed image host for article assets:
  - Repository: `mf-blog/blogPictures`
  - Branch: `main`
  - Directory: `images/<article-slug>`
  - Raw URL shape: `https://raw.githubusercontent.com/mf-blog/blogPictures/main/images/<article-slug>/<filename>.png`
- Reuse one canonical `article-slug` across frontmatter, local image folders, GitHub remote paths, and completion reports.
- Use `category`, not the misspelled `categery`.
- Preserve user-authored content. When adding metadata, images, or ending hooks, do not rewrite unrelated article sections.

---

## Stage 0: Content Strategy — AI Tech Blog for Maximum Recommendation (推荐曝光)

The following are editorial suggestions, not verified descriptions of WeChat recommendation algorithms. Do not assert signal weights, guaranteed exposure, or timing benefits without a current, verifiable source. Use account analytics to evaluate reading and engagement.

### Title Formula (标题)

Use a clear title that communicates the article topic and value. For AI tech:

**四种有效结构（四选一）：**
- `[具体工具/场景] + 实测/亲测 + 结论` — e.g., "我用 Claude 做了三个月 AI 助手，说几句真实感受"
- `[反常识结论] + 原因` — e.g., "别急着学提示词，先搞清楚这件事"
- `[数字/量化] + 行动 + 收益` — e.g., "10 个让 Claude Code 效率翻倍的使用习惯"
- `[读者痛点] + 解法` — e.g., "AI 工具用了一年，我踩过的最贵的坑"

数字适合表达真实步骤或清单；是否提升阅读表现，需要用账号数据验证。

**Title rules:**
- 长度：18-26 个汉字（含标点），不超过 30 字
- 避免标题党措辞：不用"震惊""万万没想到""99% 的人不知道""赶紧转"
- AI 技术类关键词前置：Claude、MCP、Agent、Cursor、提示词、大模型等核心词放标题前半段，利于搜索收录
- 优先使用直接表达结论的标题；不声称疑问句会受到算法限制
- 每次输出 3 个标题备选（利益驱动型 / 反常识型 / 代入感型），让作者选择

**Bad → Good examples:**
- ❌ "分享一些 AI 工具使用心得" → ✓ "用了 3 个月 Cursor，整理出这 8 个真正提效的用法"
- ❌ "关于大模型 Prompt 的思考" → ✓ "我的 Prompt 从 3 句话精简到 1 句，效果反而更好——原因在这里"

### Content Structure for High Completion Rate (完读率)

目标：让读者理解内容并愿意读完。完读率可以用于评估文章表现，不声称它具有已知的算法权重。

**Opening (前 150 字，最关键):**
- 第一段必须直接给出"为什么值得读"——一句话说清本文价值
- 不要用背景铺垫开头；不要从历史讲起
- 直接给结论或最有冲击力的发现，再往回解释

**Body structure:**
- 约每 400-600 字考虑一张有信息价值的图；按内容需要调整，不保证降低跳出率
- 段落不超过 4 行（移动端阅读节奏）
- 每个 H2/H3 小标题要能独立成句，让快速浏览者也能获得价值
- 代码块要有上下文说明——纯代码块会造成完读率骤降
- 实测数据 > 理论描述（截图、benchmark、具体数字）

**Ending (结尾 驱动分享/在看):**
- 最后一段给出"行动号召"或总结句，引导点击"在看"
- 不要用"感谢阅读"结尾——用有信息量的总结句
- 可加："如果你也在用 [工具]，欢迎留言你的用法"——激活评论信号

### WeChat Ending Hook

Every generated or revised WeChat article must end with one short topic-specific engagement hook after the substantive conclusion.

- Invite readers to comment with their own experience or use case.
- Mention that the discussion may help other domestic developers/readers when relevant.
- Ask readers to tap `在看` or share if the article was useful.
- Adapt the hook to the article topic. Do not reuse payment/card-declined examples unless the article is actually about payments.
- Do not duplicate an existing hook. Update the existing one if it is weak or off-topic.
- End with this fixed brand follow block:

```markdown
写 AI，写成长，偶尔写投资。
关注沐风，不定期更新，全是干货。
```

### Timing (发布时间)

可把工作日 12:00-13:00 或 20:00-22:00 作为测试时段，并根据账号历史数据调整。这些是经验建议，不是已验证的平台推荐窗口或保证收益。

默认上传草稿不受时段限制。用户要求立即处理时，继续上传；只有用户明确要求定时正式发布时才处理发布时间。

### Cover Image and Shared Layout (封面与统一排版)

Before planning visuals or formatting, read [沐风统一视觉规范](../mufeng-blog-writing/references/visual-style.md). Use the same modern humanistic editorial direction and topic variants as `mufeng-materials-to-wechat-publish`.

- Default to a complete text-free cover, one main relationship and purposeful whitespace. Do not default to a desk/laptop still life or a nearly empty background waiting for a title.
- A separately typeset title is optional. If requested, plan its area before generation; never ask the model to render readable text and then repair it by overpainting.
- Apply the shared layout starting values, prompt records, project-local image storage and thumbnail/crop/mobile checks. Preserve explicit user preferences and report unsupported layout differences.

### Tags & Category (话题标签)

话题标签应贴合内容；不要保证它们会提升搜索权重：
- AI 相关优先选：`#人工智能` `#大模型` `#AI工具` `#程序员` `#Claude` `#ChatGPT` `#Cursor`
- 建议选择 2-3 个相关话题标签，避免无关标签

From ichangyou/mf-ai-skills, MIT.

More from ichangyou/mf-ai-skills