Wjs Publishing Books To X logo

Wjs Publishing Books To X

Community
jianshuo
wjs-publishing-books-to-x

Use when 王建硕 wants to publish his VoiceDrop books (voicedrop.cn/books) to X/Twitter as threads — 列出他写的书、挑没发过的、整本拆成推文串发出。Triggers — "把书发到 X", "发书的 thread", "publish my book to X", "书架的书发推", "/wjs-publishing-books-to-x".

Overview

Publisherjianshuo
Repositoryclaude-skills
Skill namewjs-publishing-books-to-x
Stars
137
Forks
22
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jianshuo on GitHub. Read the source before you install it.

Installation

Install the Wjs Publishing Books To X AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jianshuo/claude-skills/tree/main/wjs-publishing-books-to-x
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jianshuo/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/wjs-publishing-books-to-x .claude/skills/wjs-publishing-books-to-x
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Wjs Publishing Books To X in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Wjs Publishing Books To X on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Wjs Publishing Books To X is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

wjs-publishing-books-to-x

把 VoiceDrop 书架上我写的书,一本一个 thread 发到 X。首条钩子 + 封面图,中间按书的脉络走,最后一条讲这本书是怎么用 VoiceDrop 写出来的。

Core Principle

一本书 = 一个 thread。 书已经是成品,thread 是它的预告片——从章节梗概和正文里抠最硬的内容,不重新构思、不写营销腔。

只发我的书。 书架是社区书架,上面有别的用户写的书,发出去就是替别人代言,绝对不行。

Workflow

Step 1: 列我的书,排除已发过的

mcp__voicedrop__list_books   # 公开书架,免登录
  • hidden 的书(book.json 里 hidden: true)服务端已滤掉,不用再处理。
  • 我的书判定:author == "王建硕" 或为空(早期的书没署名,都是我的)→ 是我的。其他署名(蜜蜡 / Dennis / sissi / …)→ 别人的书,不发。
  • 对照 state/history.jsonl 排除已发过的,列出剩余清单让用户挑。用户点名某本 → 直接用那本。

Step 2: 读书

mcp__voicedrop__read_book <slug>            # 目录 + 每章梗概 + 一句话简介
mcp__voicedrop__read_book_chapter <slug> intro   # 序章;再挑 1-2 个最有料的章读正文

梗概给骨架,正文给 quotable 的细节(数字、比喻、反直觉的断言)。

Step 3: 拆 thread(结构合同)

条内容
1钩子:书的核心断言或问题 + 书名,配封面图 https://voicedrop.cn/books/<slug>/cover.jpg
2 … N-2按书的脉络每条讲透一个点,从梗概/正文里抠。总共 6–10 条
N-1全书免费读:https://voicedrop.cn/books/<slug>/
N(必须)这本书怎么写的:真实过程——在 VoiceDrop 丢了一句什么中心思想(seed),书自己长出来、逐章补齐、不满意的地方一句话修书。落 voicedrop.cn

硬约束:每条加权 ≤280(中文每字算 2),buffer 到 ~120 汉字。王建硕语气:平实、家常比喻。无 hashtag、无 emoji、无 @。链接只出现在 N-1 和 N 两条。盘古之白。

Step 4: 过目

整串列给用户确认(每条标序号 + 字数)。用户说过 --yes 或明确「直接发」才跳过。

Step 5: 发(xurl 链式)

bash
SLUG=<slug>
curl -s -o /tmp/cover.jpg "https://voicedrop.cn/books/$SLUG/cover.jpg"
MEDIA_ID=$(xurl media upload --category tweet_image --media-type image/jpeg /tmp/cover.jpg \
  | grep -oE '"media_id_string":"[0-9]+"' | grep -oE '[0-9]+')
# 注意:不带 --category tweet_image 会按视频处理,media id 无效

# 首条(带图)
resp=$(xurl -X POST -d "$(jq -nc --arg t "$T1" --arg m "$MEDIA_ID" \
  '{text:$t, media:{media_ids:[$m]}}')" /2/tweets)
# X 返回的 text 里有裸换行,jq 会拒;grep 抠 id
PREV=$(printf '%s' "$resp" | grep -oE '"id":"[0-9]+"' | head -1 | grep -oE '[0-9]+')
[[ -n "$PREV" ]] || { echo "POST failed: $resp"; exit 1; }

# 2…N 条依次 reply 上一条,条间 sleep 5
resp=$(xurl -X POST -d "$(jq -nc --arg t "$TN" --arg r "$PREV" \
  '{text:$t, reply:{in_reply_to_tweet_id:$r}}')" /2/tweets)

任何一条失败:停在原地,把已发到第几条 + 失败原文给用户,别跳条继续(断链)。首条 URL:https://x.com/jianshuo/status/<首条id>。

Step 6: 记录

bash
jq -nc --arg date "$(date +%F)" --arg slug "$SLUG" --arg id "$FIRST_ID" --argjson n $N \
  '{date:$date,slug:$slug,thread_first_id:$id,tweets:$n,status:"posted"}' \
  >> ~/.claude/skills/wjs-publishing-books-to-x/state/history.jsonl

收尾告诉用户:thread URL、哪本书、几条、还剩几本没发。

多本连发

一次 session 默认发一本。用户要「把书都发了」→ 每本间隔 ≥4 小时排期(一口气连发多个 thread 会被 X 判刷屏),机制照抄 wjs-tweeting-from-articles 的批量排期模式(队列 + cron 自节流)。

Daily 自动化(已装)

launchd 每天 10:10 跑 daily.sh:自动挑最新一本没发过的(chapters=0 的老书跳过)→ claude -p 按上面结构合同起草 → 校验加权长度 → 链式发出 → 记 history。书发完了自动歇着。

bash
DRY_RUN=1 bash ~/.claude/skills/wjs-publishing-books-to-x/daily.sh   # 起草不发
FORCE_SLUG=<slug> bash .../daily.sh                                  # 指定书
launchctl bootout gui/$(id -u)/com.jianshuo.wjs-publishing-books-to-x  # 停掉

日志:~/Library/Logs/wjs-publishing-books-to-x/。改时间:编辑 ~/Library/LaunchAgents/com.jianshuo.wjs-publishing-books-to-x.plist 后 bootout + bootstrap。

Anti-Patterns

不要原因
发署名是别人的书社区用户的书,不是我的
thread 写成目录(第一章讲X,第二章讲Y…)要抠内容,不是报菜名
每条都塞链接链接只在 N-1、N 两条
最后一条写成 VoiceDrop 广告词讲这本书的真实写作过程,产品是顺带的
jq -r '.data.id' 解析发推返回返回的 text 带裸换行,jq 报 control characters;用 grep
media upload 不带 --category默认按视频处理,图挂不上

File Layout

~/.claude/skills/wjs-publishing-books-to-x/
├── SKILL.md
├── daily.sh                  # launchd 每日入口(挑书→起草→校验→发→记录)
├── com.jianshuo.wjs-publishing-books-to-x.plist.template
├── scripts/
│   ├── pick-next-book.sh     # 下一本没发过的我的书(新→旧)
│   └── fetch-book.py         # 抓书素材(目录梗概+序章+前两章)→ 纯文本
└── state/
    ├── .gitignore            # history.jsonl / today-* 不进公开 repo
    ├── history.jsonl         # 每发一本记一行
    └── today-*.{txt,json,jpg}  # 当天工作文件

Dependencies

  • xurl:xurl whoami 能返回用户名
  • voicedrop MCP:list_books / read_book / read_book_chapter(公开内容,免登录)
  • jq

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Wjs Publishing Books To X AI skill do?

Use when 王建硕 wants to publish his VoiceDrop books (voicedrop.cn/books) to X/Twitter as threads — 列出他写的书、挑没发过的、整本拆成推文串发出。Triggers — "把书发到 X", "发书的 thread", "publish my book to X", "书架的书发推", "/wjs-publishing-books-to-x".

Why use Wjs Publishing Books To X on TypingMind?

Because you install it once and use it with any model. Wjs Publishing Books To X is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Wjs Publishing Books To X in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jianshuo/claude-skills/tree/main/wjs-publishing-books-to-x. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Wjs Publishing Books To X?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Wjs Publishing Books To X?

As many as you like. As long as a model supports skills, you can use Wjs Publishing Books To X with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Wjs Publishing Books To X AI skill free?

Yes. It is published on GitHub by jianshuo under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇