AGENT SKILLBY EACHLABS

LinkedIn content generation

AT A GLANCE

LinkedIn content generation is a content agent skill from eachlabs. Generate high-impact LinkedIn content graphics using each::sense. It is published in the eachlabs/skills GitHub repository (18 stars), which does not specify a license. Install it with: npx skills add eachlabs/skills --skill linkedin-content-generation

FIG. 01 · CONTENT

SOURCE REPOSITORY: eachlabs/skills (opens GitHub in a new tab)
REPO STARS: SOURCE REPOSITORY
LICENSE: Not specifiedCHECK THE REPO
CATEGORIES: Content
Social
SKILL.MD SIZE: 25.5 KB863 LINES

§03

QUICK ANSWER

WHAT IT IS01: Generate high-impact LinkedIn content graphics using each::sense. The value is a focused slice of social content judgment, useful when several similar skills cover the same ground.
INPUTS02: Context for social content: your goals, audience, constraints, and any source material the skill asks for.
OUTPUT03: A ready-to-use result for social content: the analysis, copy, or recommendations the agent produces.

§04

INSTALL

One command adds this skill from its source repository.

$ npx skills add eachlabs/skills --skill linkedin-content-generation

READ THE SKILL.MD BELOW BEFORE YOU RUN IT. SKILLS INSTRUCT YOUR AGENT.

§05

SKILL.MD

The full file, as published in the source repository. Copy it, download it or open it on GitHub.

Download SKILL.md Open on GitHub View raw markdown

ON THIS PAGE · 18

LinkedIn Content Generation#

Generate high-impact LinkedIn content graphics using each::sense. This skill creates professional images optimized for LinkedIn's formats, audience expectations, and best practices for B2B engagement.

Features#

Post Graphics: Eye-catching images for feed posts and updates
Article Headers: Professional header images for LinkedIn articles
Company Banners: Brand-aligned banners for company pages
Event Promotions: Graphics for webinars, conferences, and events
Thought Leadership: Visuals for industry insights and expertise
Data Visualization: Stats and infographic-style content
Team Announcements: New hire, promotion, and team celebration graphics
Job Postings: Attractive visuals for recruitment posts
Personal Brand: Professional imagery for individual thought leaders

Quick Start#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a LinkedIn post graphic about AI transformation in business, professional and modern style with blue color scheme"}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

LinkedIn Image Formats & Sizes#

Content Type	Aspect Ratio	Recommended Size	Use Case
Feed Post (Single)	1.91:1	1200x628	Standard post images
Feed Post (Square)	1:1	1080x1080	High engagement posts
Feed Post (Portrait)	4:5	1080x1350	Maximum feed presence
Article Header	1.91:1	1200x628	LinkedIn article covers
Company Banner	4:1	1128x191	Company page header
Event Cover	16:9	1600x900	Event page images
Carousel Slide	1:1	1080x1080	Document/carousel posts

Use Case Examples#

1. Professional Post Graphic#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn post graphic about digital transformation. Show a professional in a modern office environment with digital elements and data visualizations floating around. Clean, corporate aesthetic with blue and white tones. Leave space at bottom for text overlay."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

2. Article Header Image#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1200x628 LinkedIn article header image about leadership in remote work. Abstract professional design showing connected people icons, home office elements, and collaboration symbols. Corporate blue gradient background with modern geometric shapes."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

3. Company Page Banner#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a LinkedIn company banner (1128x191 pixels, very wide 4:1 ratio) for a tech consulting firm. Abstract technology-themed design with circuit patterns, subtle gradient from dark blue to teal. Professional and innovative feel. No text, just visual elements."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

4. Event Promotion Graphic#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 16:9 LinkedIn event cover for a virtual leadership summit. Show a professional conference stage setup with modern lighting, screens displaying abstract business graphics, and an audience silhouette. Premium corporate event atmosphere with purple and blue accent lighting."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

5. Thought Leadership Visual#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 thought leadership post image about the future of AI in healthcare. Show an abstract visualization of AI and medical imagery merging - neural network patterns combined with medical symbols, DNA helixes, and healthcare icons. Clean white background with blue and green accents. Professional and innovative."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

6. Data/Stats Visualization Background#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn post background for showcasing business statistics. Abstract data visualization design with subtle chart elements, graph lines, and percentage symbols in the background. Dark professional theme with glowing blue and green data points. Leave large center area for text overlay of actual statistics."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

7. Team Announcement Graphic#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn graphic template for a new team member announcement. Professional celebratory design with confetti elements, welcome banner style, and a prominent circular placeholder area for a profile photo. Corporate colors (blue and gold), warm and welcoming atmosphere."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

8. Job Posting Visual#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 4:5 LinkedIn job posting graphic for a software engineering position. Show a modern tech workspace with developers collaborating, multiple screens with code, bright and energetic office environment. Diverse team, innovative startup atmosphere. Leave top portion for job title text."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

9. Industry Insight Graphic#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1.91:1 LinkedIn post image about fintech industry trends. Abstract financial technology visualization with blockchain nodes, digital currency symbols, and banking icons interconnected. Gradient from navy to electric blue, futuristic but professional. Suitable for a market analysis post."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

10. Personal Brand Content#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 personal brand LinkedIn post image for a business coach sharing advice. Show a professional speaking or presenting, confident pose, modern minimalist office background with motivational elements. Warm, approachable lighting. Space at bottom for quote text overlay."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

Best Practices#

Professional Aesthetics#

Color Palette: Stick to professional colors - blues, grays, white, with accent colors
Clean Design: Avoid clutter; LinkedIn audience prefers polished, minimal designs
Brand Consistency: Maintain consistent visual identity across all content
Text Space: Leave clear areas for headlines, stats, or quotes

Content Guidelines#

Professional Tone: Content should feel business-appropriate
High Resolution: Always generate at recommended sizes for crisp display
Mobile-First: Most LinkedIn users browse on mobile - ensure clarity at smaller sizes
Accessibility: Use good contrast ratios for any overlaid text

Engagement Optimization#

Visual Hierarchy: Guide the eye to key elements
Emotional Connection: Use human elements for higher engagement
Brand Recognition: Include subtle brand elements when appropriate

Prompt Tips for LinkedIn Content#

When creating LinkedIn content, include these details in your prompt:

Format: Specify aspect ratio (1:1, 1.91:1, 4:5, 16:9)
Content Type: Post, article header, banner, event, etc.
Industry: Tech, finance, healthcare, consulting, etc.
Mood: Professional, innovative, warm, authoritative
Color Scheme: Corporate blues, brand colors, etc.
Text Space: Where you need room for copy overlay
Target Audience: Executives, developers, HR, etc.

Example Prompt Structure#

TEXT · 4 LINES

"Create a [aspect ratio] LinkedIn [content type] for [industry/topic].
Show [visual description] with [mood/style].
Color scheme: [colors].
[Additional requirements like text space, brand elements, etc.]"

Mode Selection#

Ask your users before generating:

"Do you want fast & cheap, or high quality?"

Mode	Best For	Speed	Quality
`max`	Final content, important posts, brand materials	Slower	Highest
`eco`	Quick drafts, concept exploration, batch testing	Faster	Good

Multi-Turn Content Iteration#

Use session_id to iterate on LinkedIn content:

bash · 35 LINES

# Initial graphic
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn post about SaaS growth strategies, professional blue theme"}],
    "model": "eachsense/beta",
    "stream": true,
    "session_id": "linkedin-saas-post"
  }'

# Iterate based on feedback
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Make it more dynamic with upward trending graph elements and add some green accent colors for growth theme"}],
    "model": "eachsense/beta",
    "stream": true,
    "session_id": "linkedin-saas-post"
  }'

# Request variation
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create an alternative version with a darker background for A/B testing"}],
    "model": "eachsense/beta",
    "stream": true,
    "session_id": "linkedin-saas-post"
  }'

Carousel Content Generation#

Generate multiple slides for LinkedIn carousel posts:

bash · 25 LINES

# Slide 1 - Cover
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create slide 1 of 5 for a LinkedIn carousel about productivity tips. Cover slide design - bold, attention-grabbing with abstract productivity imagery. 1:1 format, dark blue background with orange accents."}],
    "model": "eachsense/beta",
    "stream": true,
    "session_id": "productivity-carousel",
    "mode": "max"
  }'

# Slide 2 - Content slide
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create slide 2 of 5 maintaining the same visual style. Show time management concept with clock and calendar elements. Leave space for tip text."}],
    "model": "eachsense/beta",
    "stream": true,
    "session_id": "productivity-carousel",
    "mode": "max"
  }'

Batch Content Generation#

Generate multiple variations for content testing:

bash · 35 LINES

# Variation A - Abstract style
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn post about cloud computing - abstract geometric style with cloud and server icons"}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "eco"
  }'

# Variation B - Photo-realistic style
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn post about cloud computing - photo-realistic data center with blue lighting"}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "eco"
  }'

# Variation C - Minimal style
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn post about cloud computing - minimal line art style with simple cloud icon"}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "eco"
  }'

Error Handling#

Error	Cause	Solution
`Failed to create prediction: HTTP 422`	Insufficient balance	Top up at eachlabs.ai
Content policy violation	Prohibited content	Adjust prompt to comply with professional content guidelines
Timeout	Complex generation	Set client timeout to minimum 10 minutes

each-sense - Core API documentation
meta-ad-creative-generation - Meta (Facebook/Instagram) ad creatives
google-ad-creative-generation - Google Ads creatives
product-photo-generation - E-commerce product shots

Supporting file: references/SSE-EVENTS.md#

SSE Event Reference#

Detailed documentation for all Server-Sent Events (SSE) returned by the each::sense /v1/chat/completions endpoint.

Event Format#

Events are wrapped in OpenAI chat.completion.chunk format with an eachlabs extension field:

TEXT

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","choices":[{"delta":{"content":""}}],"eachlabs":{"type":"event_type",...}}\n\n

Stream ends with:

TEXT

data: [DONE]\n\n

Event Types (18 Total)#

thinking_delta#

AI reasoning streamed in real-time. Use this to show users what the AI is thinking.

json · 4 LINES

{
  "type": "thinking_delta",
  "content": "Let me find the best model for portrait generation..."
}

Field	Type	Description
`content`	string	Incremental thinking text

text_response#

Assistant message content (explanations, answers, plans).

json · 4 LINES

{
  "type": "text_response",
  "content": "I'll create a stunning portrait for you with cinematic lighting and a warm mood."
}

Field	Type	Description
`content`	string	Text response content

status#

Current operation being executed. Shows tool usage and parameters.

json · 6 LINES

{
  "type": "status",
  "message": "Searching for image generation models...",
  "tool_name": "search_models",
  "parameters": {"use_case": "text to image portrait"}
}

Field	Type	Description
`message`	string	Human-readable status message
`tool_name`	string	Internal tool being used
`parameters`	object	Tool parameters (optional)

tool_call#

Details of a tool being called. Useful for debugging and transparency.

json · 11 LINES

{
  "type": "tool_call",
  "name": "execute_model",
  "input": {
    "model_name": "flux-2-max",
    "inputs": {
      "prompt": "A beautiful woman portrait...",
      "aspect_ratio": "1:1"
    }
  }
}

Field	Type	Description
`name`	string	Tool name
`input`	object	Tool input parameters

message#

Informational message from the agent.

json · 4 LINES

{
  "type": "message",
  "content": "Your video is being processed. This typically takes 2-3 minutes."
}

Field	Type	Description
`content`	string	Message content

progress#

Progress update with percentage completion.

json · 5 LINES

{
  "type": "progress",
  "message": "Generating image...",
  "percent": 65
}

Field	Type	Description
`message`	string	Progress description
`percent`	number	Completion percentage

generation_response#

Generated media URL (image, video, audio). This is the primary output event.

json · 7 LINES

{
  "type": "generation_response",
  "url": "https://storage.eachlabs.ai/outputs/abc123.png",
  "generations": ["https://storage.eachlabs.ai/outputs/abc123.png"],
  "model": "flux-2-max",
  "execution_time_ms": 8500
}

Field	Type	Description
`url`	string	Primary output URL
`generations`	array	All generated URLs
`model`	string	Model used for generation
`execution_time_ms`	number	Processing time in milliseconds

clarification_needed#

AI needs more information to proceed. Present options to the user.

json · 12 LINES

{
  "type": "clarification_needed",
  "question": "What type of edit would you like to make to this image?",
  "options": [
    "Remove the background",
    "Apply a style transfer",
    "Upscale to higher resolution",
    "Add or modify elements"
  ],
  "context": "I can see you've uploaded an image, but I need to understand what changes you'd like.",
  "requires_response": true
}

Field	Type	Description
`question`	string	The question to ask the user
`options`	array	Suggested options (can be displayed as buttons)
`context`	string	Additional context about the clarification
`requires_response`	boolean	Whether a response is required to proceed

Handling: Display the question and options to the user. Send their response in a follow-up request with the same session_id.

web_search_query#

Web search being executed.

json · 5 LINES

{
  "type": "web_search_query",
  "query": "best AI video generation models 2024",
  "recency": "month"
}

Field	Type	Description
`query`	string	Search query
`recency`	string	Time filter (day, week, month, year)

web_search_citations#

Citations from web search results.

json · 6 LINES

{
  "type": "web_search_citations",
  "citations": [
    {"title": "AI Video Comparison", "url": "https://example.com/ai-video", "snippet": "..."}
  ]
}

Field	Type	Description
`citations`	array	Array of objects with `title`, `url`, `snippet`

workflow_created#

New workflow was created for complex multi-step generation.

json · 6 LINES

{
  "type": "workflow_created",
  "workflow_id": "wf_abc123",
  "version_id": "v1",
  "steps_count": 5
}

Field	Type	Description
`workflow_id`	string	Unique workflow identifier
`version_id`	string	Workflow version
`steps_count`	number	Number of steps in workflow

workflow_fetched#

Existing workflow was loaded (when workflow_id is provided in request).

json · 6 LINES

{
  "type": "workflow_fetched",
  "workflow_name": "Product Video Generator",
  "existing_steps": 3,
  "existing_definition": {}
}

Field	Type	Description
`workflow_name`	string	Name of the workflow
`existing_steps`	number	Number of existing steps
`existing_definition`	object	Current workflow definition

workflow_built#

Workflow definition was constructed.

json · 9 LINES

{
  "type": "workflow_built",
  "steps_count": 4,
  "definition": {
    "version": "v1",
    "input_schema": {},
    "steps": []
  }
}

Field	Type	Description
`steps_count`	number	Number of steps
`definition`	object	Full workflow definition

workflow_updated#

Workflow was pushed to the EachLabs API.

json · 7 LINES

{
  "type": "workflow_updated",
  "success": true,
  "workflow_id": "wf_abc123",
  "version_id": "v1",
  "definition": {}
}

Field	Type	Description
`success`	boolean	Whether update succeeded
`workflow_id`	string	Workflow identifier
`version_id`	string	Version identifier
`definition`	object	Updated definition

execution_started#

Workflow execution has begun.

json · 5 LINES

{
  "type": "execution_started",
  "execution_id": "exec_xyz789",
  "workflow_id": "wf_abc123"
}

Field	Type	Description
`execution_id`	string	Unique execution identifier
`workflow_id`	string	Workflow being executed

execution_progress#

Progress update during workflow execution.

json · 6 LINES

{
  "type": "execution_progress",
  "step_id": "step2",
  "completed_steps": 2,
  "total_steps": 5
}

Field	Type	Description
`step_id`	string	Current step identifier
`completed_steps`	number	Steps completed so far
`total_steps`	number	Total steps in workflow

execution_completed#

Workflow execution finished.

json · 11 LINES

{
  "type": "execution_completed",
  "execution_id": "exec_xyz789",
  "output": "https://storage.eachlabs.ai/outputs/final.mp4",
  "all_outputs": {
    "step1": "https://storage.eachlabs.ai/outputs/step1.png",
    "step2": "https://storage.eachlabs.ai/outputs/step2.png",
    "step3": "https://storage.eachlabs.ai/outputs/final.mp4"
  },
  "total_time_ms": 45000
}

Field	Type	Description
`execution_id`	string	Execution identifier
`output`	string	Final output URL
`all_outputs`	object	All step outputs keyed by step_id
`total_time_ms`	number	Total execution time in milliseconds

complete#

Final event with summary. Always sent when stream completes.

json · 7 LINES

{
  "type": "complete",
  "task_id": "chat_1708345678901",
  "status": "ok",
  "generations": ["https://storage.eachlabs.ai/outputs/abc123.png"],
  "model": "flux-2-max"
}

Field	Type	Description
`task_id`	string	Unique task identifier
`status`	string	Final status (ok, error, clarification_needed)
`generations`	array	All generated output URLs
`model`	string	Primary model used

Status values:

ok - Completed successfully
clarification_needed - Waiting for user clarification
error - An error occurred

error#

An error occurred during processing.

json · 6 LINES

{
  "type": "error",
  "message": "Failed to generate image: Invalid aspect ratio",
  "error_code": "INVALID_INPUT",
  "details": {}
}

Field	Type	Description
`message`	string	Error message
`error_code`	string	Error code identifier
`details`	object	Additional error details

Event Flow Examples#

Simple Image Generation#

TEXT · 7 LINES

thinking_delta → "I'll create a beautiful portrait..."
status → "Searching for models..."
status → "Getting model details..."
text_response → "Here's your generated image..."
generation_response → {url: "https://...", model: "flux-2-max", execution_time_ms: 8500}
complete → {status: "ok", generations: [...]}
[DONE]

Clarification Flow#

TEXT · 4 LINES

thinking_delta → "I see an image, but need to know what edit..."
clarification_needed → {question: "What edit?", options: [...]}
complete → {status: "clarification_needed"}
[DONE]

Workflow Execution#

TEXT · 11 LINES

thinking_delta → "Creating a multi-step workflow..."
status → "Searching for models..."
workflow_created → {workflow_id: "wf_123", steps_count: 5}
execution_started → {execution_id: "exec_456"}
execution_progress → {completed_steps: 1, total_steps: 5}
execution_progress → {completed_steps: 2, total_steps: 5}
execution_progress → {completed_steps: 3, total_steps: 5}
execution_progress → {completed_steps: 4, total_steps: 5}
execution_completed → {output: "https://...", all_outputs: {...}, total_time_ms: 45000}
complete → {status: "ok"}
[DONE]

Web Search#

TEXT · 7 LINES

thinking_delta → "Let me search for current information..."
web_search_query → {query: "best AI models 2024"}
status → "Searching the web..."
web_search_citations → {citations: [{title, url, snippet}, ...]}
text_response → "Based on current information..."
complete → {status: "ok"}
[DONE]

SHOWING THE FIRST PART OF 25.5 KB · THE FULL TEXT IS ON THIS PAGE

§06

FAQ

07 QUESTIONS

01What is the LinkedIn content generation agent skill?

Generate high-impact LinkedIn content graphics using each::sense. It is listed under content and social media in the 100xLab agent skills directory.

02How do I install LinkedIn content generation in Cursor, Claude Code, or Codex?

Run npx skills add eachlabs/skills --skill linkedin-content-generation in the project where you want it, then ask your agent for the skill by name. The --skill flag installs only LinkedIn content generation, not every skill in the repository.

03What does the LinkedIn content generation SKILL.md cover?

The SKILL.md includes sections on Features, Quick Start, LinkedIn Image Formats & Sizes, Use Case Examples, Professional Post Graphic and Article Header Image. Read the full text on this page or in plain markdown at /resources/agent-skills/eachlabs-skills--linkedin-content-generation--15hpkp0/raw.

04Which agents can use LinkedIn content generation?

LinkedIn content generation installs with the cross-agent skills installer (npx skills add), which sets it up for agents such as Claude Code, Cursor and Codex. Each agent loads the SKILL.md when you ask for the skill by name.

05What license is LinkedIn content generation under?

No license was detected on the eachlabs/skills repository, so the license is not specified. Check with eachlabs before you redistribute or build on the skill.

06Is LinkedIn content generation free to use?

Reading and installing LinkedIn content generation costs nothing, because it is published in a public GitHub repository. The repository specifies no license, so ask eachlabs before you reuse or redistribute it.

07Where is the source of LinkedIn content generation?

LinkedIn content generation comes from https://github.com/eachlabs/skills, which has 18 GitHub stars. The SKILL.md is at https://github.com/eachlabs/skills/blob/HEAD/skills/linkedin-content-generation/SKILL.md. The author is eachlabs.

Need an agent workflow built around your stack?

Tell us the workflow you want automated. We reply within 4 working hours (IST).

BOOK A CALL

§09

ATTRIBUTION

LinkedIn content generation was written by its original authors and is published in eachlabs/skills (opens GitHub in a new tab) under no license stated in the repository. All rights stay with the original authors.

100xLab did not write, maintain or endorse this skill. This page lists it for discovery. Repo stars belong to the source repository, not to the skill. Review any skill before you install it.

AGENT SKILLBY EACHLABS

LinkedIn content generation

AT A GLANCE

FIG. 01 · CONTENT

SOURCE REPOSITORY: eachlabs/skills (opens GitHub in a new tab)
REPO STARS: SOURCE REPOSITORY
LICENSE: Not specifiedCHECK THE REPO
CATEGORIES: Content
Social
SKILL.MD SIZE: 25.5 KB863 LINES

§03

QUICK ANSWER

WHAT IT IS01: Generate high-impact LinkedIn content graphics using each::sense. The value is a focused slice of social content judgment, useful when several similar skills cover the same ground.
INPUTS02: Context for social content: your goals, audience, constraints, and any source material the skill asks for.
OUTPUT03: A ready-to-use result for social content: the analysis, copy, or recommendations the agent produces.

§04

INSTALL

One command adds this skill from its source repository.

$ npx skills add eachlabs/skills --skill linkedin-content-generation

READ THE SKILL.MD BELOW BEFORE YOU RUN IT. SKILLS INSTRUCT YOUR AGENT.

§05

SKILL.MD

The full file, as published in the source repository. Copy it, download it or open it on GitHub.

Download SKILL.md Open on GitHub View raw markdown

ON THIS PAGE · 18

LinkedIn Content Generation#

Features#

Post Graphics: Eye-catching images for feed posts and updates
Article Headers: Professional header images for LinkedIn articles
Company Banners: Brand-aligned banners for company pages
Event Promotions: Graphics for webinars, conferences, and events
Thought Leadership: Visuals for industry insights and expertise
Data Visualization: Stats and infographic-style content
Team Announcements: New hire, promotion, and team celebration graphics
Job Postings: Attractive visuals for recruitment posts
Personal Brand: Professional imagery for individual thought leaders

Quick Start#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a LinkedIn post graphic about AI transformation in business, professional and modern style with blue color scheme"}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

LinkedIn Image Formats & Sizes#

Content Type	Aspect Ratio	Recommended Size	Use Case
Feed Post (Single)	1.91:1	1200x628	Standard post images
Feed Post (Square)	1:1	1080x1080	High engagement posts
Feed Post (Portrait)	4:5	1080x1350	Maximum feed presence
Article Header	1.91:1	1200x628	LinkedIn article covers
Company Banner	4:1	1128x191	Company page header
Event Cover	16:9	1600x900	Event page images
Carousel Slide	1:1	1080x1080	Document/carousel posts

Use Case Examples#

1. Professional Post Graphic#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn post graphic about digital transformation. Show a professional in a modern office environment with digital elements and data visualizations floating around. Clean, corporate aesthetic with blue and white tones. Leave space at bottom for text overlay."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

2. Article Header Image#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1200x628 LinkedIn article header image about leadership in remote work. Abstract professional design showing connected people icons, home office elements, and collaboration symbols. Corporate blue gradient background with modern geometric shapes."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

3. Company Page Banner#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a LinkedIn company banner (1128x191 pixels, very wide 4:1 ratio) for a tech consulting firm. Abstract technology-themed design with circuit patterns, subtle gradient from dark blue to teal. Professional and innovative feel. No text, just visual elements."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

4. Event Promotion Graphic#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 16:9 LinkedIn event cover for a virtual leadership summit. Show a professional conference stage setup with modern lighting, screens displaying abstract business graphics, and an audience silhouette. Premium corporate event atmosphere with purple and blue accent lighting."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

5. Thought Leadership Visual#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 thought leadership post image about the future of AI in healthcare. Show an abstract visualization of AI and medical imagery merging - neural network patterns combined with medical symbols, DNA helixes, and healthcare icons. Clean white background with blue and green accents. Professional and innovative."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

6. Data/Stats Visualization Background#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn post background for showcasing business statistics. Abstract data visualization design with subtle chart elements, graph lines, and percentage symbols in the background. Dark professional theme with glowing blue and green data points. Leave large center area for text overlay of actual statistics."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

7. Team Announcement Graphic#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn graphic template for a new team member announcement. Professional celebratory design with confetti elements, welcome banner style, and a prominent circular placeholder area for a profile photo. Corporate colors (blue and gold), warm and welcoming atmosphere."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

8. Job Posting Visual#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 4:5 LinkedIn job posting graphic for a software engineering position. Show a modern tech workspace with developers collaborating, multiple screens with code, bright and energetic office environment. Diverse team, innovative startup atmosphere. Leave top portion for job title text."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

9. Industry Insight Graphic#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1.91:1 LinkedIn post image about fintech industry trends. Abstract financial technology visualization with blockchain nodes, digital currency symbols, and banking icons interconnected. Gradient from navy to electric blue, futuristic but professional. Suitable for a market analysis post."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

10. Personal Brand Content#

bash · 10 LINES

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 personal brand LinkedIn post image for a business coach sharing advice. Show a professional speaking or presenting, confident pose, modern minimalist office background with motivational elements. Warm, approachable lighting. Space at bottom for quote text overlay."}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "max"
  }'

Best Practices#

Professional Aesthetics#

Color Palette: Stick to professional colors - blues, grays, white, with accent colors
Clean Design: Avoid clutter; LinkedIn audience prefers polished, minimal designs
Brand Consistency: Maintain consistent visual identity across all content
Text Space: Leave clear areas for headlines, stats, or quotes

Content Guidelines#

Professional Tone: Content should feel business-appropriate
High Resolution: Always generate at recommended sizes for crisp display
Mobile-First: Most LinkedIn users browse on mobile - ensure clarity at smaller sizes
Accessibility: Use good contrast ratios for any overlaid text

Engagement Optimization#

Visual Hierarchy: Guide the eye to key elements
Emotional Connection: Use human elements for higher engagement
Brand Recognition: Include subtle brand elements when appropriate

Prompt Tips for LinkedIn Content#

When creating LinkedIn content, include these details in your prompt:

Format: Specify aspect ratio (1:1, 1.91:1, 4:5, 16:9)
Content Type: Post, article header, banner, event, etc.
Industry: Tech, finance, healthcare, consulting, etc.
Mood: Professional, innovative, warm, authoritative
Color Scheme: Corporate blues, brand colors, etc.
Text Space: Where you need room for copy overlay
Target Audience: Executives, developers, HR, etc.

Example Prompt Structure#

TEXT · 4 LINES

"Create a [aspect ratio] LinkedIn [content type] for [industry/topic].
Show [visual description] with [mood/style].
Color scheme: [colors].
[Additional requirements like text space, brand elements, etc.]"

Mode Selection#

Ask your users before generating:

"Do you want fast & cheap, or high quality?"

Mode	Best For	Speed	Quality
`max`	Final content, important posts, brand materials	Slower	Highest
`eco`	Quick drafts, concept exploration, batch testing	Faster	Good

Multi-Turn Content Iteration#

Use session_id to iterate on LinkedIn content:

bash · 35 LINES

# Initial graphic
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn post about SaaS growth strategies, professional blue theme"}],
    "model": "eachsense/beta",
    "stream": true,
    "session_id": "linkedin-saas-post"
  }'

# Iterate based on feedback
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Make it more dynamic with upward trending graph elements and add some green accent colors for growth theme"}],
    "model": "eachsense/beta",
    "stream": true,
    "session_id": "linkedin-saas-post"
  }'

# Request variation
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create an alternative version with a darker background for A/B testing"}],
    "model": "eachsense/beta",
    "stream": true,
    "session_id": "linkedin-saas-post"
  }'

Carousel Content Generation#

Generate multiple slides for LinkedIn carousel posts:

bash · 25 LINES

# Slide 1 - Cover
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create slide 1 of 5 for a LinkedIn carousel about productivity tips. Cover slide design - bold, attention-grabbing with abstract productivity imagery. 1:1 format, dark blue background with orange accents."}],
    "model": "eachsense/beta",
    "stream": true,
    "session_id": "productivity-carousel",
    "mode": "max"
  }'

# Slide 2 - Content slide
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create slide 2 of 5 maintaining the same visual style. Show time management concept with clock and calendar elements. Leave space for tip text."}],
    "model": "eachsense/beta",
    "stream": true,
    "session_id": "productivity-carousel",
    "mode": "max"
  }'

Batch Content Generation#

Generate multiple variations for content testing:

bash · 35 LINES

# Variation A - Abstract style
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn post about cloud computing - abstract geometric style with cloud and server icons"}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "eco"
  }'

# Variation B - Photo-realistic style
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn post about cloud computing - photo-realistic data center with blue lighting"}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "eco"
  }'

# Variation C - Minimal style
curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Accept: text/event-stream" \
  -d '{
    "messages": [{"role": "user", "content": "Create a 1:1 LinkedIn post about cloud computing - minimal line art style with simple cloud icon"}],
    "model": "eachsense/beta",
    "stream": true,
    "mode": "eco"
  }'

Error Handling#

Error	Cause	Solution
`Failed to create prediction: HTTP 422`	Insufficient balance	Top up at eachlabs.ai
Content policy violation	Prohibited content	Adjust prompt to comply with professional content guidelines
Timeout	Complex generation	Set client timeout to minimum 10 minutes

each-sense - Core API documentation
meta-ad-creative-generation - Meta (Facebook/Instagram) ad creatives
google-ad-creative-generation - Google Ads creatives
product-photo-generation - E-commerce product shots

Supporting file: references/SSE-EVENTS.md#

SSE Event Reference#

Detailed documentation for all Server-Sent Events (SSE) returned by the each::sense /v1/chat/completions endpoint.

Event Format#

Events are wrapped in OpenAI chat.completion.chunk format with an eachlabs extension field:

TEXT

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","choices":[{"delta":{"content":""}}],"eachlabs":{"type":"event_type",...}}\n\n

Stream ends with:

TEXT

data: [DONE]\n\n

Event Types (18 Total)#

thinking_delta#

AI reasoning streamed in real-time. Use this to show users what the AI is thinking.

json · 4 LINES

{
  "type": "thinking_delta",
  "content": "Let me find the best model for portrait generation..."
}

Field	Type	Description
`content`	string	Incremental thinking text

text_response#

Assistant message content (explanations, answers, plans).

json · 4 LINES

{
  "type": "text_response",
  "content": "I'll create a stunning portrait for you with cinematic lighting and a warm mood."
}

Field	Type	Description
`content`	string	Text response content

status#

Current operation being executed. Shows tool usage and parameters.

json · 6 LINES

{
  "type": "status",
  "message": "Searching for image generation models...",
  "tool_name": "search_models",
  "parameters": {"use_case": "text to image portrait"}
}

Field	Type	Description
`message`	string	Human-readable status message
`tool_name`	string	Internal tool being used
`parameters`	object	Tool parameters (optional)

tool_call#

Details of a tool being called. Useful for debugging and transparency.

json · 11 LINES

{
  "type": "tool_call",
  "name": "execute_model",
  "input": {
    "model_name": "flux-2-max",
    "inputs": {
      "prompt": "A beautiful woman portrait...",
      "aspect_ratio": "1:1"
    }
  }
}

Field	Type	Description
`name`	string	Tool name
`input`	object	Tool input parameters

message#

Informational message from the agent.

json · 4 LINES

{
  "type": "message",
  "content": "Your video is being processed. This typically takes 2-3 minutes."
}

Field	Type	Description
`content`	string	Message content

progress#

Progress update with percentage completion.

json · 5 LINES

{
  "type": "progress",
  "message": "Generating image...",
  "percent": 65
}

Field	Type	Description
`message`	string	Progress description
`percent`	number	Completion percentage

generation_response#

Generated media URL (image, video, audio). This is the primary output event.

json · 7 LINES

{
  "type": "generation_response",
  "url": "https://storage.eachlabs.ai/outputs/abc123.png",
  "generations": ["https://storage.eachlabs.ai/outputs/abc123.png"],
  "model": "flux-2-max",
  "execution_time_ms": 8500
}

Field	Type	Description
`url`	string	Primary output URL
`generations`	array	All generated URLs
`model`	string	Model used for generation
`execution_time_ms`	number	Processing time in milliseconds

clarification_needed#

AI needs more information to proceed. Present options to the user.

json · 12 LINES

{
  "type": "clarification_needed",
  "question": "What type of edit would you like to make to this image?",
  "options": [
    "Remove the background",
    "Apply a style transfer",
    "Upscale to higher resolution",
    "Add or modify elements"
  ],
  "context": "I can see you've uploaded an image, but I need to understand what changes you'd like.",
  "requires_response": true
}

Field	Type	Description
`question`	string	The question to ask the user
`options`	array	Suggested options (can be displayed as buttons)
`context`	string	Additional context about the clarification
`requires_response`	boolean	Whether a response is required to proceed

Handling: Display the question and options to the user. Send their response in a follow-up request with the same session_id.

web_search_query#

Web search being executed.

json · 5 LINES

{
  "type": "web_search_query",
  "query": "best AI video generation models 2024",
  "recency": "month"
}

Field	Type	Description
`query`	string	Search query
`recency`	string	Time filter (day, week, month, year)

web_search_citations#

Citations from web search results.

json · 6 LINES

{
  "type": "web_search_citations",
  "citations": [
    {"title": "AI Video Comparison", "url": "https://example.com/ai-video", "snippet": "..."}
  ]
}

Field	Type	Description
`citations`	array	Array of objects with `title`, `url`, `snippet`

workflow_created#

New workflow was created for complex multi-step generation.

json · 6 LINES

{
  "type": "workflow_created",
  "workflow_id": "wf_abc123",
  "version_id": "v1",
  "steps_count": 5
}

Field	Type	Description
`workflow_id`	string	Unique workflow identifier
`version_id`	string	Workflow version
`steps_count`	number	Number of steps in workflow

workflow_fetched#

Existing workflow was loaded (when workflow_id is provided in request).

json · 6 LINES

{
  "type": "workflow_fetched",
  "workflow_name": "Product Video Generator",
  "existing_steps": 3,
  "existing_definition": {}
}

Field	Type	Description
`workflow_name`	string	Name of the workflow
`existing_steps`	number	Number of existing steps
`existing_definition`	object	Current workflow definition

workflow_built#

Workflow definition was constructed.

json · 9 LINES

{
  "type": "workflow_built",
  "steps_count": 4,
  "definition": {
    "version": "v1",
    "input_schema": {},
    "steps": []
  }
}

Field	Type	Description
`steps_count`	number	Number of steps
`definition`	object	Full workflow definition

workflow_updated#

Workflow was pushed to the EachLabs API.

json · 7 LINES

{
  "type": "workflow_updated",
  "success": true,
  "workflow_id": "wf_abc123",
  "version_id": "v1",
  "definition": {}
}

Field	Type	Description
`success`	boolean	Whether update succeeded
`workflow_id`	string	Workflow identifier
`version_id`	string	Version identifier
`definition`	object	Updated definition

execution_started#

Workflow execution has begun.

json · 5 LINES

{
  "type": "execution_started",
  "execution_id": "exec_xyz789",
  "workflow_id": "wf_abc123"
}

Field	Type	Description
`execution_id`	string	Unique execution identifier
`workflow_id`	string	Workflow being executed

execution_progress#

Progress update during workflow execution.

json · 6 LINES

{
  "type": "execution_progress",
  "step_id": "step2",
  "completed_steps": 2,
  "total_steps": 5
}

Field	Type	Description
`step_id`	string	Current step identifier
`completed_steps`	number	Steps completed so far
`total_steps`	number	Total steps in workflow

execution_completed#

Workflow execution finished.

json · 11 LINES

{
  "type": "execution_completed",
  "execution_id": "exec_xyz789",
  "output": "https://storage.eachlabs.ai/outputs/final.mp4",
  "all_outputs": {
    "step1": "https://storage.eachlabs.ai/outputs/step1.png",
    "step2": "https://storage.eachlabs.ai/outputs/step2.png",
    "step3": "https://storage.eachlabs.ai/outputs/final.mp4"
  },
  "total_time_ms": 45000
}

Field	Type	Description
`execution_id`	string	Execution identifier
`output`	string	Final output URL
`all_outputs`	object	All step outputs keyed by step_id
`total_time_ms`	number	Total execution time in milliseconds

complete#

Final event with summary. Always sent when stream completes.

json · 7 LINES

{
  "type": "complete",
  "task_id": "chat_1708345678901",
  "status": "ok",
  "generations": ["https://storage.eachlabs.ai/outputs/abc123.png"],
  "model": "flux-2-max"
}

Field	Type	Description
`task_id`	string	Unique task identifier
`status`	string	Final status (ok, error, clarification_needed)
`generations`	array	All generated output URLs
`model`	string	Primary model used

Status values:

ok - Completed successfully
clarification_needed - Waiting for user clarification
error - An error occurred

error#

An error occurred during processing.

json · 6 LINES

{
  "type": "error",
  "message": "Failed to generate image: Invalid aspect ratio",
  "error_code": "INVALID_INPUT",
  "details": {}
}

Field	Type	Description
`message`	string	Error message
`error_code`	string	Error code identifier
`details`	object	Additional error details

Event Flow Examples#

Simple Image Generation#

TEXT · 7 LINES

thinking_delta → "I'll create a beautiful portrait..."
status → "Searching for models..."
status → "Getting model details..."
text_response → "Here's your generated image..."
generation_response → {url: "https://...", model: "flux-2-max", execution_time_ms: 8500}
complete → {status: "ok", generations: [...]}
[DONE]

Clarification Flow#

TEXT · 4 LINES

thinking_delta → "I see an image, but need to know what edit..."
clarification_needed → {question: "What edit?", options: [...]}
complete → {status: "clarification_needed"}
[DONE]

Workflow Execution#

TEXT · 11 LINES

thinking_delta → "Creating a multi-step workflow..."
status → "Searching for models..."
workflow_created → {workflow_id: "wf_123", steps_count: 5}
execution_started → {execution_id: "exec_456"}
execution_progress → {completed_steps: 1, total_steps: 5}
execution_progress → {completed_steps: 2, total_steps: 5}
execution_progress → {completed_steps: 3, total_steps: 5}
execution_progress → {completed_steps: 4, total_steps: 5}
execution_completed → {output: "https://...", all_outputs: {...}, total_time_ms: 45000}
complete → {status: "ok"}
[DONE]

Web Search#

TEXT · 7 LINES

thinking_delta → "Let me search for current information..."
web_search_query → {query: "best AI models 2024"}
status → "Searching the web..."
web_search_citations → {citations: [{title, url, snippet}, ...]}
text_response → "Based on current information..."
complete → {status: "ok"}
[DONE]

SHOWING THE FIRST PART OF 25.5 KB · THE FULL TEXT IS ON THIS PAGE

§06

FAQ

07 QUESTIONS

01What is the LinkedIn content generation agent skill?

Generate high-impact LinkedIn content graphics using each::sense. It is listed under content and social media in the 100xLab agent skills directory.

02How do I install LinkedIn content generation in Cursor, Claude Code, or Codex?

03What does the LinkedIn content generation SKILL.md cover?

04Which agents can use LinkedIn content generation?

05What license is LinkedIn content generation under?

No license was detected on the eachlabs/skills repository, so the license is not specified. Check with eachlabs before you redistribute or build on the skill.

06Is LinkedIn content generation free to use?

07Where is the source of LinkedIn content generation?

Need an agent workflow built around your stack?

Tell us the workflow you want automated. We reply within 4 working hours (IST).

BOOK A CALL

§09

ATTRIBUTION

100xLab did not write, maintain or endorse this skill. This page lists it for discovery. Repo stars belong to the source repository, not to the skill. Review any skill before you install it.

LinkedIn content generation

QUICK ANSWER

INSTALL

SKILL.MD

LinkedIn Content Generation#

Features#

Quick Start#

LinkedIn Image Formats & Sizes#

Use Case Examples#

1. Professional Post Graphic#

2. Article Header Image#

3. Company Page Banner#

4. Event Promotion Graphic#

5. Thought Leadership Visual#

6. Data/Stats Visualization Background#

7. Team Announcement Graphic#

8. Job Posting Visual#

9. Industry Insight Graphic#

10. Personal Brand Content#

Best Practices#

Professional Aesthetics#

Content Guidelines#

Engagement Optimization#

Prompt Tips for LinkedIn Content#

Example Prompt Structure#

Mode Selection#

Multi-Turn Content Iteration#

Carousel Content Generation#

Batch Content Generation#

Error Handling#

Related Skills#

Supporting file: references/SSE-EVENTS.md#

SSE Event Reference#

Event Format#

Event Types (18 Total)#

thinking_delta#

text_response#

status#

tool_call#

message#

progress#

generation_response#

clarification_needed#

web_search_query#

web_search_citations#

workflow_created#

workflow_fetched#

workflow_built#

workflow_updated#

execution_started#

execution_progress#

execution_completed#

complete#

error#

Event Flow Examples#

Simple Image Generation#

Clarification Flow#

Workflow Execution#

Web Search#

FAQ

RELATED SKILLS

More from eachlabs

More Content skills

More Social skills

Need an agent workflow built around your stack?

ATTRIBUTION

LinkedIn content generation

QUICK ANSWER

INSTALL

SKILL.MD

LinkedIn Content Generation#

Features#

Quick Start#

LinkedIn Image Formats & Sizes#

Use Case Examples#

1. Professional Post Graphic#

2. Article Header Image#

3. Company Page Banner#

4. Event Promotion Graphic#

5. Thought Leadership Visual#