social-media
langchain-ai/deepagents
Draft engaging social media posts with research-backed content and generated images for LinkedIn, Twitter/X, and other platforms.
What is social-media?
Creates platform-optimized social media content including posts, threads, hooks, and hashtags, with required companion images. Use when drafting LinkedIn posts, tweets, Twitter/X threads, captions, or repurposing content across social platforms.
- Researches topics via delegated researcher subagent before writing
- Drafts platform-specific posts (LinkedIn, Twitter/X) with hooks and CTAs
- Generates eye-catching social images matched to post content
- Suggests relevant hashtags and thread structures
- Ensures posts meet character limits and platform guidelines
- Creates organized output folders with both content and visuals
How to install social-media
npx skills add https://github.com/langchain-ai/deepagents --skill social-media- Access to researcher subagent for delegated research
- Image generation capability (generate_social_image tool)
- File system access to save posts and images
How to use social-media
- 1.Describe the social media content you want (topic, platform, type)
- 2.The skill delegates research to a researcher subagent and saves findings
- 3.Review the research file created in research/ directory
- 4.The skill drafts platform-optimized content (LinkedIn/Twitter/X format)
- 5.An image is generated automatically and saved alongside the post
- 6.Review the complete output in the appropriate folder (linkedin/ or tweets/)
Use cases
- Writing a LinkedIn post about industry trends with supporting research and visual
- Creating a Twitter/X thread on a technical topic with accompanying image
- Repurposing existing content into platform-specific social posts
- Drafting announcement posts with news hooks and engagement CTAs
- Generating insight posts that share learnings with actionable takeaways
- Content creators and marketers
- Thought leaders sharing industry insights
- Product teams announcing launches or updates
- Professionals building personal brands
- Anyone needing research-backed social content
social-media FAQ
No. The skill automatically delegates research to a researcher subagent before writing. You just describe what you want, and it handles gathering information.
LinkedIn posts and Twitter/X threads are fully supported with platform-specific formatting, character limits, and guidelines. Output structure adapts to each platform.
Yes. Every social media post must include a generated image. The skill creates both the content file and image file in the same folder.
Yes. Provide specific visual direction when requesting the post, and the skill will generate an image matching your description using the generate_social_image tool.
The skill respects platform limits (1,300 chars for LinkedIn, 280 per tweet for Twitter/X). For longer content, it structures Twitter/X threads across multiple tweets with the 1/๐งต format.
Full instructions (SKILL.md)
Source of truth, from langchain-ai/deepagents.
name: social-media description: Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.
Social Media Content Skill
Research First (Required)
Before writing any social media content, you MUST delegate research:
- Use the
tasktool withsubagent_type: "researcher" - In the description, specify BOTH the topic AND where to save:
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"
)
- After research completes, read the findings file before writing
Output Structure (Required)
Every social media post MUST have both content AND an image:
LinkedIn posts:
linkedin/
โโโ <slug>/
โโโ post.md # The post content
โโโ image.png # REQUIRED: Generated visual
Twitter/X threads:
tweets/
โโโ <slug>/
โโโ thread.md # The thread content
โโโ image.png # REQUIRED: Generated visual
Example: A LinkedIn post about "prompt engineering" โ linkedin/prompt-engineering/
You MUST complete both steps:
- Write the content to the appropriate path
- Generate an image using
generate_imageand save alongside the post
A social media post is NOT complete without its image.
Platform Guidelines
Format:
- 1,300 character limit (show more after ~210 chars)
- First line is crucial - make it hook
- Use line breaks for readability
- 3-5 hashtags at the end
Tone:
- Professional but personal
- Share insights and learnings
- Ask questions to drive engagement
- Use "I" and share experiences
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
Twitter/X
Format:
- 280 character limit per tweet
- Threads for longer content (use 1/๐งต format)
- No more than 2 hashtags per tweet
Thread Structure:
1/๐งต [Hook - the main insight]
2/ [Supporting point 1]
3/ [Supporting point 2]
4/ [Example or evidence]
5/ [Conclusion + CTA]
Image Generation
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 Image Best Practices
Social images need to work at small sizes in crowded feeds:
- Bold, simple compositions - one clear focal point
- High contrast - stands out when scrolling
- No text in image - too small to read, platforms add their own
- Square or 4:5 ratio - works across platforms
Writing Effective Prompts
Include these elements:
- Single focal point: One clear subject, not a busy scene
- Bold style: Vibrant colors, strong shapes, high contrast
- Simple background: Solid color, gradient, or subtle texture
- Mood/energy: Match the post tone (inspiring, urgent, thoughtful)
Example Prompts
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.
Content Types
Announcement Posts
- Lead with the news
- Explain the impact
- Include link or next step
Insight Posts
- Share one specific learning
- Explain the context briefly
- Make it actionable
Question Posts
- Ask a genuine question
- Provide your take first
- Keep it focused on one topic
Quality Checklist
Before finishing:
- Post saved to
linkedin/<slug>/post.mdortweets/<slug>/thread.md - Image generated alongside the post
- First line hooks attention
- Content fits platform limits
- Tone matches platform norms
- Has clear CTA or question
- Hashtags are relevant (not generic)
Related skills
More from langchain-ai/deepagents and the wider catalog.
langgraph-docs
Access LangGraph Python documentation to build stateful agents and multi-agent workflows.
web-research
Delegate web research across multiple subagents, synthesize findings, and produce cited reports.
arxiv-search
Search arXiv for preprints and academic papers by topic with abstracts.
blog-post
Write and structure long-form blog posts with SEO optimization and auto-generated cover images.
skill-creator
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) update or modify an existing skill, (8) validate a skill, (9) learn about skill structure, (10) understand how skills work, or (11) get guidance on skill design patterns. Trigger on phrases like \"create a skill\", \"new skill\", \"make a skill\", \"skill for X\", \"how do I create a skill\", or \"help me build a skill\".
query-writing
Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables.