x-publish

Q: How do I install x-publish?

Run npx skills add https://github.com/kangarooking/x-skills --skill x-publish in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/x-publish/ (personal) or .claude/skills/x-publish/ (project).

by kangarookingProductivity & Automation

Publish tweets and threads to X (Twitter) draft using browser automation. Use when user wants to publish content to X, save to drafts, or mentions "publish to X", "post tweet", "x-publish", "发布推文". Supports short tweets and threads. NEVER auto-publish, always saves to draft.

Installs: 87
Last 24h: —
Trending rank: —
Security: Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/kangarooking/x-skills --skill x-publish

01
Install
Run the command in your project. The CLI asks which agents to install for.
02
Describe the task
Ask your agent for something this skill covers. It loads x-publish automatically when relevant.
03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

X Publish

Publish tweets and threads to X draft using Playwright browser automation.

Prerequisites

Playwright MCP for browser automation
User logged into X (Twitter)
Python 3.9+ with dependencies:
- macOS: pip install Pillow pyobjc-framework-Cocoa
- Windows: pip install Pillow pywin32

Critical Rules

NEVER auto-publish - Only save to draft
User must be logged in - Prompt to login if not
Verify content before saving - Double-check tweet text

Content Types

Short Tweet

Single tweet ≤280 characters

Thread

Multiple tweets connected (3-10 tweets)

Scripts

copy_to_clipboard.py

Copy text to system clipboard for paste operation:

# Copy text to clipboard
python scripts/copy_to_clipboard.py text "Tweet content here"

# Copy from file
python scripts/copy_to_clipboard.py text --file /tmp/tweet.txt

Workflow

Short Tweet

Step 1: Prepare Content

# Save tweet to temp file
echo "Tweet content" > /tmp/tweet.txt

# Copy to clipboard
python scripts/copy_to_clipboard.py text --file /tmp/tweet.txt

Step 2: Open Compose

browser_navigate: https://x.com/compose/post

Step 3: Paste Content

browser_snapshot → Find tweet textbox
browser_click: textbox
browser_press_key: Meta+v

Step 4: Save Draft

browser_click: X (close button)
browser_click: "Save" or "保存" in dialog

Step 5: Verify

Report: "Draft saved. Please review at https://x.com/compose/drafts"

Thread

Step 1: Prepare Content Parse thread into individual tweets:

### 1/5
First tweet content...

### 2/5
Second tweet content...

Step 2: Open Compose

browser_navigate: https://x.com/compose/post

Step 3: Add First Tweet

python scripts/copy_to_clipboard.py text "First tweet content"

browser_click: textbox
browser_press_key: Meta+v

Step 4: Add More Tweets For each additional tweet:

browser_click: "Add another post" / "添加" button
browser_press_key: Meta+v (after copying next tweet)

Step 5: Save Draft

browser_click: X (close button)
browser_click: "Save" in dialog

Step 6: Verify

Report: "Thread draft saved ({n} tweets). Review at https://x.com/compose/drafts"

Efficiency Guidelines

Avoid Unnecessary Waits

❌ browser_snapshot after every action
✅ Use action return values for next step

Parallel Preparation

✅ Prepare all tweet content before browser operations
✅ Copy to clipboard while navigating

Sequential Execution

Navigate → Paste first tweet → Add tweet → Paste → ... → Save

Element References

Common elements in X compose:

Element	Description	Typical ref pattern
Tweet textbox	Main input area	textbox with "What's happening"
Add tweet button	"+" or "添加"	button near compose area
Close button	X icon	button top-left
Save draft	In close dialog	"Save" / "保存" button
Drafts link	View saved drafts	link to /compose/drafts

Example Flows

Short Tweet Example

User: /x-publish "Claude 4.5发布了，extended thinking是真正的游戏规则改变者。"

# 1. Copy to clipboard
python scripts/copy_to_clipboard.py text "Claude 4.5发布了，extended thinking是真正的游戏规则改变者。"

# 2. Navigate and paste
browser_navigate: https://x.com/compose/post
browser_snapshot → find textbox
browser_click: textbox
browser_press_key: Meta+v

# 3. Close and save
browser_click: close button (X)
browser_click: "Save" button

# 4. Report
"Draft saved! Review at: https://x.com/compose/drafts"

Thread Example

User: /x-publish (with thread content from x-create)

Thread:
### 1/3
First point about AI...

### 2/3
Second point...

### 3/3
Conclusion...

Execution:

# Prepare all tweets
tweet1="First point about AI..."
tweet2="Second point..."
tweet3="Conclusion..."

# Navigate
browser_navigate: https://x.com/compose/post

# Tweet 1
python copy_to_clipboard.py text "$tweet1"
browser_click: textbox
browser_press_key: Meta+v

# Tweet 2
python copy_to_clipboard.py text "$tweet2"
browser_click: "Add another post" button
browser_press_key: Meta+v

# Tweet 3
python copy_to_clipboard.py text "$tweet3"
browser_click: "Add another post" button
browser_press_key: Meta+v

# Save
browser_click: close button
browser_click: "Save"

# Report
"Thread draft saved (3 tweets). Review at: https://x.com/compose/drafts"

Error Handling

Not Logged In

If login page detected:
→ "Please log in to X first, then run /x-publish again"

Character Limit

If tweet > 280 chars:
→ Split into thread or truncate with warning

Network Error

If page fails to load:
→ Retry once, then report error

Integration

After publishing:

推文已保存到草稿箱！

- 类型: {short/thread}
- 条数: {n}
- 草稿链接: https://x.com/compose/drafts

请手动审核后发布。

Append a machine-readable block for hooks/state ingestion:

PUBLISH_JSON
{
  "schema_version": "x_skills.publish.v1",
  "timestamp": "{timestamp}",
  "draft_saved": true,
  "post_type": "short|thread",
  "count": 1,
  "draft_url": "https://x.com/compose/drafts"
}

(Optional) Append event for feedback loop:

python ~/.claude/skills/x-create/scripts/x_state.py event --event publish.saved_to_draft --payload-json '{"post_type":"short","count":1,"draft_saved":true}'

FAQ

What does the x-publish skill do?

How do I install x-publish?

Run npx skills add https://github.com/kangarooking/x-skills --skill x-publish in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/x-publish/ (personal) or .claude/skills/x-publish/ (project).

Which AI agents can use x-publish?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is x-publish safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains x-publish?

It is published by kangarooking in kangarooking/x-skills. It has 87 recorded installs.

More from kangarooking/x-skills

View all →

x-filter

kangarooking/x-skills

Score and filter topics for X content creation using weighted criteria. Use when user wants to evaluate collected materials, filter topics by score, or mentions "filter topics", "score materials", "x-filter", "选题筛选". Applies 10-point scoring system with customizable weights.

341 installs

x-create

kangarooking/x-skills

Create viral X (Twitter) posts including short tweets, threads, and replies. Use when user wants to write X content, create posts, or mentions "create tweet", "write thread", "x-create", "写推文", "创作推文". Supports 5 post styles with customizable templates, plus a mandatory humanize pass to reduce AI-sounding phrasing. First-time users go through onboarding to set up profile.

Marketing & SEO114 installs

x-collect

kangarooking/x-skills

Collect and research materials for X (Twitter) content creation using multi-round web search strategy. Use when user wants to gather trending topics, research subjects for X posts, or mentions "collect materials", "research topic", "find content for X", "x-collect". Performs 4-round deep research mimicking human research workflow.

Productivity & Automation89 installs

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

Productivity & Automation815.7K installs

lark-base

open.feishu.cn

飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。

Productivity & Automation815K installs

lark-drive

open.feishu.cn

飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。

Productivity & Automation815K installs

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

Productivity & Automation814.8K installs

lark-im

open.feishu.cn

飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。

Productivity & Automation814.1K installs

x-publish

Install

Install

Describe the task

Review the result

SKILL.md

X Publish

Prerequisites

Critical Rules

Content Types

Short Tweet

Thread

Scripts

copy_to_clipboard.py

Workflow

Short Tweet

Thread

Efficiency Guidelines

Avoid Unnecessary Waits

Parallel Preparation

Sequential Execution

Element References

Example Flows

Short Tweet Example

Thread Example

Error Handling

Not Logged In

Character Limit

Network Error

Integration

FAQ

More from kangarooking/x-skills

Popular productivity & automation skills