social-media by langchain-ai/deepagents
npx skills add https://github.com/langchain-ai/deepagents --skill social-media在撰写任何社交媒体内容之前,你必须委派调研任务:
task 工具并指定 subagent_type: "researcher"task(
subagent_type="researcher",
description="Research [TOPIC]. Save findings to research/[slug].md"
)
示例:
task(
subagent_type="researcher",
description="Research renewable energy trends in 2025. Save findings to research/renewable-energy.md"
)
3. 调研完成后,在撰写内容前阅读调研结果文件
每篇社交媒体帖子必须同时包含内容和图片:
LinkedIn 帖子:
linkedin/
└── <slug>/
├── post.md # 帖子内容
└── image.png # 必需:生成的视觉图
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
Twitter/X 主题帖:
tweets/
└── <slug>/
├── thread.md # 主题帖内容
└── image.png # 必需:生成的视觉图
示例:一篇关于"提示工程"的 LinkedIn 帖子 → linkedin/prompt-engineering/
你必须完成以下两个步骤:
generate_image 生成图片并保存在帖子旁边没有图片的社交媒体帖子是不完整的。
格式:
语气:
结构:
[吸引人的开头 - 1 行引人注目的文字]
[空行]
[背景 - 说明此事为何重要]
[空行]
[主要见解 - 2-3 个短段落]
[空行]
[行动号召或问题]
#话题标签1 #话题标签2 #话题标签3
格式:
主题帖结构:
1/🧵 [吸引人的开头 - 主要见解]
2/ [支持点 1]
3/ [支持点 2]
4/ [示例或证据]
5/ [结论 + 行动号召]
每篇社交媒体帖子都需要一张引人注目的图片。使用 generate_social_image 工具:
generate_social_image(prompt="A detailed description...", platform="linkedin", slug="your-post-slug")
该工具将图片保存到 <platform>/<slug>/image.png。
社交媒体图片需要在拥挤的信息流中以小尺寸有效展示:
包含以下要素:
用于见解/技巧类帖子:
Single glowing lightbulb floating against a deep purple gradient background, lightbulb made of interconnected golden geometric lines, rays of soft light emanating outward. Minimal, striking, high contrast. Square composition.
用于公告/新闻类帖子:
Abstract rocket ship made of colorful geometric shapes launching upward with a trail of particles. Bright coral and teal color scheme against clean white background. Energetic, celebratory mood. Bold flat illustration style.
用于发人深省的内容:
Two overlapping translucent circles, one blue one orange, creating a glowing intersection in the center. Represents collaboration or intersection of ideas. Dark charcoal background, soft ethereal glow. Minimalist and contemplative.
完成前检查:
linkedin/<slug>/post.md 或 tweets/<slug>/thread.md每周安装量
486
代码仓库
GitHub 星标数
17.1K
首次出现
Jan 22, 2026
安全审计
安装于
opencode440
codex432
gemini-cli430
cursor411
github-copilot408
kimi-cli365
Before writing any social media content, you MUST delegate research:
task tool with subagent_type: "researcher"task(
subagent_type="researcher",
description="Research [TOPIC]. Save findings to research/[slug].md"
)
Example:
task(
subagent_type="researcher",
description="Research renewable energy trends in 2025. Save findings to research/renewable-energy.md"
)
3. After research completes, read the findings file before writing
Every social media post MUST have both content AND an image:
LinkedIn posts:
linkedin/
└── <slug>/
├── post.md # The post content
└── image.png # REQUIRED: Generated visual
Twitter/X threads:
tweets/
└── <slug>/
├── thread.md # The thread content
└── image.png # REQUIRED: Generated visual
Example: A LinkedIn post about "prompt engineering" → linkedin/prompt-engineering/
You MUST complete both steps:
generate_image and save alongside the postA social media post is NOT complete without its image.
Format:
Tone:
Structure:
[Hook - 1 compelling line]
[Empty line]
[Context - why this matters]
[Empty line]
[Main insight - 2-3 short paragraphs]
[Empty line]
[Call to action or question]
#hashtag1 #hashtag2 #hashtag3
Format:
Thread Structure:
1/🧵 [Hook - the main insight]
2/ [Supporting point 1]
3/ [Supporting point 2]
4/ [Example or evidence]
5/ [Conclusion + CTA]
Every social media post needs an eye-catching image. Use the generate_social_image tool:
generate_social_image(prompt="A detailed description...", platform="linkedin", slug="your-post-slug")
The tool saves the image to <platform>/<slug>/image.png.
Social images need to work at small sizes in crowded feeds:
Include these elements:
For an insight/tip post:
Single glowing lightbulb floating against a deep purple gradient background, lightbulb made of interconnected golden geometric lines, rays of soft light emanating outward. Minimal, striking, high contrast. Square composition.
For announcements/news:
Abstract rocket ship made of colorful geometric shapes launching upward with a trail of particles. Bright coral and teal color scheme against clean white background. Energetic, celebratory mood. Bold flat illustration style.
For thought-provoking content:
Two overlapping translucent circles, one blue one orange, creating a glowing intersection in the center. Represents collaboration or intersection of ideas. Dark charcoal background, soft ethereal glow. Minimalist and contemplative.
Before finishing:
linkedin/<slug>/post.md or tweets/<slug>/thread.mdWeekly Installs
486
Repository
GitHub Stars
17.1K
First Seen
Jan 22, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode440
codex432
gemini-cli430
cursor411
github-copilot408
kimi-cli365
AI Elements:基于shadcn/ui的AI原生应用组件库,快速构建对话界面
54,900 周安装
OpenAPI 转 TypeScript 工具 - 自动生成 API 接口与类型守卫
563 周安装
Rust Unsafe代码检查器 - 安全使用Unsafe Rust的完整指南与最佳实践
566 周安装
数据库模式设计器 - 内置最佳实践,自动生成生产级SQL/NoSQL数据库架构
565 周安装
Nx 生成器使用指南:自动化代码生成与单体仓库项目搭建
594 周安装
.NET并发编程模式指南:async/await、Channels、Akka.NET选择决策树
725 周安装
韩语语法检查器 - 基于国立国语院标准的拼写、空格、语法、标点错误检测与纠正
586 周安装