메뉴
跨X、LinkedIn、Threads和Bluesky的多平台内容分发。使用内容引擎模式根据平台适配内容。从不跨平台发布相同内容。当用户希望跨社交平台分发内容时使用。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | crosspost |
| description | 跨X、LinkedIn、Threads和Bluesky的多平台内容分发。使用内容引擎模式根据平台适配内容。从不跨平台发布相同内容。当用户希望跨社交平台分发内容时使用。 |
| origin | ECC |
将内容分发到多个社交平台，并适配各平台原生风格。
| 平台 | 最大长度 | 链接处理 | 话题标签 | 媒体 |
|---|---|---|---|---|
| X | 280 字符 (Premium 用户为 4000) | 计入长度 | 少量 (最多 1-2 个) | 图片、视频、GIF |
| 3000 字符 | 不计入长度 | 3-5 个相关标签 | 图片、视频、文档、轮播 | |
| Threads | 500 字符 | 独立的链接附件 | 通常不使用 | 图片、视频 |
| Bluesky | 300 字符 | 通过 Facets (富文本) | 无 (使用 Feeds) | 图片 |
从核心想法开始。使用 content-engine 技能来生成高质量草稿：
询问用户或根据上下文确定：
针对每个目标平台，转换内容：
X 平台适配：
LinkedIn 平台适配：
Threads 平台适配：
Bluesky 平台适配：
首先发布到主平台：
x-api 技能处理 X将适配后的版本发布到其余平台：
X 版本：
We just shipped [feature].
[One specific thing it does that's impressive]
[Link]
LinkedIn 版本：
Excited to share: we just launched [feature] at [Company].
Here's why it matters:
[2-3 short paragraphs with context]
[Takeaway for the audience]
[Link]
Threads 版本：
just shipped something cool — [feature]
[casual explanation of what it does]
link in bio
X 版本：
TIL: [specific technical insight]
[Why it matters in one sentence]
LinkedIn 版本：
A pattern I've been using that's made a real difference:
[Technical insight with professional framing]
[How it applies to teams/orgs]
#relevantHashtag
如果使用跨平台发布服务 (例如 Postbridge、Buffer 或自定义 API)，模式如下：
import os
import requests
resp = requests.post(
"https://your-crosspost-service.example/api/posts",
headers={"Authorization": f"Bearer {os.environ['POSTBRIDGE_API_KEY']}"},
json={
"platforms": ["twitter", "linkedin", "threads"],
"content": {
"twitter": {"text": x_version},
"linkedin": {"text": linkedin_version},
"threads": {"text": threads_version}
}
},
timeout=30
)
resp.raise_for_status()
没有 Postbridge 时，使用各平台原生 API 发布：
x-api 技能模式发布前：
content-engine — 生成平台原生内容x-api — X/Twitter API 集成Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support.
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.
Interactive agent picker for composing and dispatching parallel teams