social-media
Verifiedby langchain-ai · Updated Apr 16, 2026
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.
See It In Action
Got it — I've read through the skill spec, company info, and internal launch note. Let me create the LinkedIn post and image prompt now.
Now let me verify everything and do a character count on the post:
Everything's ready. Here's what I created at linkedin/social-media-skill-launch/:
post.md — LinkedIn Launch Post
- 1,265 characters (under the 1,300 limit ✓)
- Hook line leads with the real user pain point (68% / 30+ min stat from the launch note)
- Three → bullet differentiators: research-first, mandatory images, platform-aware formatting
- Specific numbers throughout (2 min, 2–3x engagement, 4,200+ users) — matches the doany.ai voice guidelines (no hype, real gains)
- CTA ends with a question to drive comments
- 4 hashtags (within the 3–5 guideline)
image-prompt.md — Image for the 4pm Roundup
Prompt is ready to feed into generate_social_image. It describes a bold geometric speech-bubble with a pencil-and-image icon inside, teal/coral accents on a deep-navy background — minimal, high-contrast, no text, square composition. Matches the "announcement" energy from the skill's prompt examples.
Note: I don't have access to the
generate_social_imagetool in this environment, so I saved the prompt toimage-prompt.md. Whoever runs the 4pm roundup can pass it straight through to generateimage.pngin the same folder.
External Tools
| Tool | Type |
|---|---|
| fal-ai | mcp |
Permissions
| Scope | Description |
|---|---|
| filesystem:read | |
| filesystem:write |
SKILL.md
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/
└── <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:
- 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/🧵 format)
- No more than 2 hashtags per tweet
Thread Structure:
1/🧵 [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)
FAQ
What does social-media do?
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.
When should I use social-media?
Use it when you need a repeatable workflow that produces text report, image output.
What does social-media output?
In the evaluated run it produced text report, image output.
How do I install or invoke social-media?
Ask the agent to use this skill when the task matches its documented workflow.
Which agents does social-media support?
Agent support is inferred from the source, but not explicitly declared.
What tools, channels, or permissions does social-media need?
It uses fal-ai; channels commonly include text, image; permissions include filesystem:read, filesystem:write.
Is social-media safe to install?
Static analysis marked this skill as medium risk; review side effects and permissions before enabling it.
How is social-media different from an MCP or plugin?
A skill packages instructions and workflow conventions; tools, MCP servers, and plugins are dependencies the skill may call during execution.
Does social-media outperform not using a skill?
About social-media
When to use social-media
When you need a LinkedIn post drafted from a topic or research brief. When you want a Twitter/X thread with a clear hook and thread structure. When repurposing ideas into social posts that also need a matching visual asset.
When social-media is not the right choice
When you need publishing or scheduling to social platforms rather than draft creation. When you only want plain text output without generating and saving files or images.
What it produces
Produces text report and image output.
