Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.
.claude/skills/affaan-m-crosspost/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 32% | 0% |
| case-22 | ✗→✓ | ▲ Improved | 70% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 39% | 0% |
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 | | LinkedIn | 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：
我们刚刚发布了 [feature]。
[它所实现的某个具体且令人印象深刻的功能]
[链接]LinkedIn 版本：
激动地宣布：我们刚刚在[Company]推出了[feature]。
以下是其重要意义：
[2-3段简短背景说明]
[对受众的核心启示]
[链接]Threads 版本：
刚发布了一个很酷的东西 —— [feature]
[对这个功能是什么的随意解释]
链接在简介里X 版本：
今天学到：[具体技术见解]
[一句话说明其重要性]LinkedIn 版本：
我一直在使用的一种模式，它带来了真正的改变：
[技术见解与专业框架]
[它如何适用于团队/组织]
#相关标签如果使用跨平台发布服务 (例如 Postbridge、Buffer 或自定义 API)，模式如下：
pythonimport 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| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-21 | pass→pass | 15,155 | 10,054 | -34% | 1 | 1 | 0% | 2,840 | 3,256 | +15% | 0 | 0 | — |
case-01 | fail→pass | 14,534 | 11,759 | -19% | 1 | 1 | 0% | 2,253 | 3,140 | +39% | 0 | 0 | — |
case-02 | fail→pass | 16,475 | 12,111 | -26% | 1 | 1 | 0% | 2,292 | 3,014 | +32% | 0 | 0 | — |
case-03 | pass→pass | 14,204 | 13,612 | -4% | 1 | 1 | 0% | 2,538 | 3,764 | +48% | 0 | 0 | — |
case-04 | pass→fail | 19,021 | 17,761 | -7% | 1 | 1 | 0% | 3,023 | 4,480 | +48% | 0 | 0 | — |
case-22 | fail→pass | 7,493 | 5,458 | -27% | 1 | 1 | 0% | 1,252 | 2,131 | +70% | 0 | 0 | — |
case-05 | pass→pass | 22,471 | 19,119 | -15% | 1 | 1 | 0% | 2,960 | 4,232 | +43% | 0 | 0 | — |
case-06 | pass→pass | 13,594 | 12,812 | -6% | 1 | 1 | 0% | 2,107 | 3,279 | +56% | 0 | 0 | — |
case-07 | fail→pass | 15,387 | 13,513 | -12% | 1 | 1 | 0% | 2,370 | 3,377 | +42% | 0 | 0 | — |
case-08 | fail→pass | 11,764 | 8,887 | -24% | 1 | 1 | 0% | 2,227 | 3,105 | +39% | 0 | 0 | — |
case-09 | fail→pass | 13,194 | 10,098 | -23% | 1 | 1 | 0% | 1,992 | 2,842 | +43% | 0 | 0 | — |
case-10 | fail→pass | 13,850 | 12,915 | -7% | 1 | 1 | 0% | 2,136 | 3,313 | +55% | 0 | 0 | — |
case-11 | fail→pass | 15,044 | 13,229 | -12% | 1 | 1 | 0% | 2,300 | 3,558 | +55% | 0 | 0 | — |
case-12 | fail→pass | 17,128 | 12,881 | -25% | 1 | 1 | 0% | 2,454 | 3,442 | +40% | 0 | 0 | — |
case-13 | pass→pass | 16,883 | 14,854 | -12% | 1 | 1 | 0% | 2,503 | 3,674 | +47% | 0 | 0 | — |
case-14 | pass→pass | 14,085 | 10,017 | -29% | 1 | 1 | 0% | 1,880 | 2,598 | +38% | 0 | 0 | — |
case-15 | pass→pass | 11,053 | 7,484 | -32% | 1 | 1 | 0% | 1,664 | 2,476 | +49% | 0 | 0 | — |
case-16 | fail→pass | 8,424 | 9,744 | +16% | 1 | 1 | 0% | 1,335 | 3,015 | +126% | 0 | 0 | — |
case-17 | fail→pass | 12,185 | 11,736 | -4% | 1 | 1 | 0% | 1,815 | 3,379 | +86% | 0 | 0 | — |
case-18 | pass→pass | 15,372 | 14,293 | -7% | 1 | 1 | 0% | 2,203 | 3,642 | +65% | 0 | 0 | — |
case-19 | fail→pass | 16,673 | 16,320 | -2% | 1 | 1 | 0% | 2,562 | 4,004 | +56% | 0 | 0 | — |
case-20 | fail→pass | 12,448 | 3,022 | -76% | 1 | 1 | 0% | 1,938 | 1,885 | -3% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +55 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 8/3/2026 | +9% |
Other measured skills in the registry, with their headline benchmark lift.