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.
npx skills add https://github.com/langchain-ai/deepagents --skill social-media