langchain-ai avatar

Social Media

This one handles the full social media workflow: researches your topic first using a subagent, writes platform-specific posts (LinkedIn or Twitter/X threads) with proper hooks and hashtags, then generates a companion image for each post. Everything gets organized into folders with both the content and visual together. The prompts are detailed about what works for social images (bold, simple, high contrast, no text) and include concrete examples like "single glowing lightbulb against deep purple gradient" for insight posts. It enforces the research step and won't let you skip the image generation, which honestly keeps you from publishing half-finished content. Good for when you need to turn ideas into actual posts rather than just jotting down thoughts.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.
8
skills.sh installs
2.7K
GitHub stars
31.2K
last updated
Aug 21, 2026

Install

$ npx -y skills add langchain-ai/deepagents --skill social-media --agent claude-code

Installs into .claude/skills of the current project.

Files

Social Media Content Skill

Research First (Required)

Before writing any social media content, you MUST delegate research:

  1. Use the task tool with subagent_type: "researcher"
  2. 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"
)
  1. 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/
└── <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/

Sponsors

Details

Repository
github.com/langchain-ai/deepagents
Categories
Frontend Development, AI & Agent Building, Marketing & SEO, Video & Audio Editing
First seen
Apr 16, 2026

More from langchain-ai/deepagents

All 12
1supermemoryai avatarsvg-animationssupermemoryai/skillsCreate beautiful, performant SVG animations and illustrations. Use this skill when the user asks to create SVG graphics, icons, illustrations, animated logos, p2.7Kskills.sh installs
2agricidaniel avatarblog-analyzeagricidaniel/claude-blogAudit and score blog posts on a 5-category 100-point scoring system covering content quality, SEO optimization, E-E-A-T signals, technical elements, and AI cita2.7Kskills.sh installs
3copilotkit avatara2ui-renderercopilotkit/copilotkitRender A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via <CopilotKi2.7Kskills.sh installs
4freshtechbro avatarbabylonjs-enginefreshtechbro/claudedesignskillsComprehensive skill for Babylon.js 3D web rendering engine. Use this skill when building real-time 3D experiences, browser-based games, interactive visualizatio2.7Kskills.sh installs
5ognjengt avatarviral-hook-creatorognjengt/founder-skillsCreates viral social media hooks using proven psychological patterns and trigger words. Use when user needs attention-grabbing openings for posts, threads, vide2.7Kskills.sh installs
6thedivergentai avatargodot-masterthedivergentai/gd-agentic-skillsConsolidated expert library for professional Godot 4.7+ game and application development. Orchestrates 92 Domain Skills through architectural workflows, anti-pa2.7Kskills.sh installs