linkedin-post skill
✓ VerifiedCreate and schedule LinkedIn posts including text, images, videos, and PDF documents via the Publora MCP server.
- GitHub stars
- 68
- Files
- 1
- Last commit
- Nov 10, 2026
- License
- MIT
- Allowed tools
- —
What does the linkedin-post skill do?
linkedin-post creates and schedule LinkedIn posts including text, images, videos, and PDF documents via the Publora MCP server.
Summary generated from the skill's SKILL.md.
About the linkedin-post skill
Publishing and scheduling LinkedIn content through the Publora MCP server allows users to manage professional social media presence directly from an AI agent. This skill is designed for creators and marketers who need to distribute text, multi-image grids, videos, or PDF documents. It provides specific tools to create posts, manage drafts, and handle media uploads via presigned URLs.
When an agent needs to automate social media workflows, it can use this skill to schedule content for a future time or post immediately. The server supports various media formats including MP4 for videos and JPEG or PNG for images, though it does not allow mixing different media types in a single post. Users can also utilize URN syntax for @mentions of people and organizations. This tool is distinct from analytics or engagement tools, focusing strictly on the creation and management of post content and scheduling.
What an agent can do with it
- 1Schedule a future text postCreate a LinkedIn post with specific text and set it to go live at a future UTC datetime.
- 2Share a multi-page PDF documentUpload a PDF to LinkedIn to share swipeable multi-page content with a summary caption.
- 3Post a multi-image gridPublish a post containing up to ten images displayed in a grid layout.
- 4Manage existing post draftsUpdate the content or change the platform for a post that has already been drafted or scheduled.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the linkedin-post skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the linkedin-post skill in Plugin
/plugin marketplace add publora/skills /plugin install publora-skills@publora-skills
Install the linkedin-post skill in Claude Code
~/.claude/skills/linkedin-post/SKILL.md
$ npx degit publora/skills/skills/linkedin-post ~/.claude/skills/linkedin-postInstall the linkedin-post skill in Claude Code (project)
.claude/skills/linkedin-post/SKILL.md
$ npx degit publora/skills/skills/linkedin-post .claude/skills/linkedin-postInstall the linkedin-post skill in Codex
~/.agents/skills/linkedin-post/SKILL.md
$ npx degit publora/skills/skills/linkedin-post ~/.agents/skills/linkedin-postInstall the linkedin-post skill in Gemini CLI
~/.gemini/skills/linkedin-post/SKILL.md
$ npx degit publora/skills/skills/linkedin-post ~/.gemini/skills/linkedin-postInstall the linkedin-post skill in Claude.ai
npx degit publora/skills/skills/linkedin-post linkedin-post && zip -r linkedin-post.zip linkedin-post # claude.ai → Customize → Skills → + → Create skill → Upload a skill → linkedin-post.zip
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the scripts before you let an agent run them. How checks work
- Source repository linked and reachablepublora/skills/skills/linkedin-post is public and reachablegithub.com/publora/skills/tree/HEAD/skills/linkedin-post ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit 2026-11-10github.com/publora/skills/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/publora/skills/blob/HEAD/skills/linkedin-post/SKI ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/publora/skills/blob/HEAD/skills/linkedin-post/SKI ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 183 linesgithub.com/publora/skills/blob/HEAD/skills/linkedin-post/SKI ↗Pass
SKILL.md
View on GitHubLinkedIn Post
Create and schedule LinkedIn posts using the Publora MCP server. Supports text posts, single images, multi-image posts (grid layout), videos, and PDF documents.
Prerequisites
Plans: Works on the free Starter plan. Current limits and pricing: publora.com/pricing.
Getting Started
- Create account at publora.com/register (free)
- Connect LinkedIn via OAuth in Publora Dashboard
- Get an API key at app.publora.com/dashboard/api, only if your agent cannot sign in with OAuth or you will use the REST API fallback below
- Connect your agent to the MCP server at
https://mcp.publora.com/mcp:- Upgrading a manual connection without
/mcp: Claude treatshttps://mcp.publora.comas a different server from the bundled one. Change that existing connection tohttps://mcp.publora.com/mcpin its current scope, preserving its authentication and chosen account; sign in again if requested. Alternatively, verify the bundled connection uses the intended account, then remove only the old manual entry. Do not add a second entry or delete credentials automatically. - Publora tools already available (the
publora-skillsplugin or the Publora connector in Claude): nothing to set up. Claude asks you to sign in to Publora the first time a tool runs. - Agents that support OAuth (Claude Code, Cursor, and the Claude and ChatGPT apps): add the server by URL and sign in, no API key needed. In Claude Code, add it and then run
/mcpto sign in:
- Upgrading a manual connection without
claude mcp add --transport http --scope user publora https://mcp.publora.com/mcp
- Agents without OAuth: send the API key as
Authorization: Bearer sk_YOUR_API_KEY:
claude mcp add --transport http --scope user publora https://mcp.publora.com/mcp \
--header "Authorization: Bearer sk_YOUR_API_KEY"
Claude Desktop, Cursor, Codex, OpenClaw and the claude.ai connector each need a different config file or flow: see client setup for the exact path and snippet.
REST API Fallback
If the MCP server is unavailable or returns errors, use the REST API directly:
Base URL: https://api.publora.com/api/v1
Authentication: Use x-publora-key header (NOT Authorization: Bearer):
# Get your connected platforms
curl -X GET "https://api.publora.com/api/v1/platform-connections" \
-H "x-publora-key: sk_your_api_key"
# Create a post
curl -X POST "https://api.publora.com/api/v1/create-post" \
-H "x-publora-key: sk_your_api_key" \
-H "Content-Type: application/json" \
-d '{
"platforms": ["linkedin-Tz9W5i6ZYG"],
"content": "Your post content here",
"scheduledTime": "2026-03-25T10:00:00Z"
}'
Platform ID Format: linkedin-{id} where {id} is from /platform-connections response.
Example IDs: linkedin-Tz9W5i6ZYG, linkedin-abc123xyz
📖 Full API documentation: docs.publora.com
Platform Limits
| Feature | Limit |
|---|---|
| Characters | 3,000 max |
| Visible before "see more" | First 210 characters |
| Images | Up to 10 (grid layout, not swipeable carousel) |
| Image size | 36,152,320 pixels is the primary gate; 50 MB ceiling |
| Image formats | JPEG, PNG, GIF, WebP (WebP auto-converted) |
| Video duration | 30 minutes |
| Video size | 500 MB max |
| Video format | MP4 only |
Available Tools
create_post
Create a new LinkedIn post or schedule for later.
Parameters:
platforms: Array including your LinkedIn connection ID (e.g.,["linkedin-abc123"])content: Post text (up to 3,000 characters)scheduledTime: ISO 8601 UTC datetime. Optional: omit it and the post is created as a draft. Send a future time to schedule. A time five or more minutes in the past is rejected withSCHEDULED_TIME_IN_PAST, so for immediate posting use the current time plus a minute.mediaUrls: up to 10 public https image or video URLs. Publora downloads them server-side and attaches them before validation, so media and scheduling happen in one call. This is the one-shot alternative to the draft thenget_upload_urlthencomplete_mediaflow. Ingestion is rate-limited to 60 URLs per hour.
get_upload_url
Get a presigned URL to upload media.
Parameters:
postGroupId: The post ID to attach media tofileName: File name (e.g., "chart.png")contentType: MIME type (e.g., "image/jpeg", "video/mp4", "application/pdf")type: "image" or "video"
complete_media
Finalize a file uploaded through get_upload_url, after the presigned PUT succeeds. Optional, because scheduling also finalizes pending media, but calling it early surfaces format and probe errors before publish. Not needed for media attached with mediaUrls.
Parameters:
mediaId: the id returned byget_upload_url
list_connections
List your connected accounts with their platform IDs. Call this first and copy the IDs verbatim; they are never guessable.
list_posts / get_post / update_post / delete_post
Manage scheduled and draft posts. update_post also patches content and platforms on a draft or scheduled post, so fixing a typo or retargeting no longer means delete and recreate. delete_media and prune_media_reference clean up uploaded files.
Mentioning People and Companies
LinkedIn posts support @mentions using URN syntax:
@{urn:li:person:MEMBER_ID|Display Name} # Mention a person
@{urn:li:organization:ORG_ID|Company Name} # Mention a company
Example:
Great insights from @{urn:li:person:4986615|Serge Bulaev} at @{urn:li:organization:107107343|Creative Content Crafts Inc}!
Important: The display name must exactly match the LinkedIn profile name (case-sensitive), including company suffixes like "Inc", "LLC", etc.
Do not hand-write member ids. The linkedin_list_mentionables MCP tool resolves a name to the correct URN; see the linkedin-analytics skill.
Important API Restrictions
-
No organic carousels: Swipeable multi-image carousels are NOT available via API (only for sponsored content). Multi-image posts appear as a grid layout.
-
No mixed media: Cannot combine images with videos or documents in the same post.
-
No rich text: LinkedIn API does not support bold, italic, or other formatting. Use plain text or Unicode characters for emphasis.
-
PDF alternative for carousels: To share multi-page swipeable content, upload a PDF document instead.
Examples
Simple Text Post
Schedule a LinkedIn post for tomorrow at 9 AM:
"We're thrilled to announce the release of our AI writing assistant. After 18 months of development, we're ready to help teams write better content faster."
Post with Mention
Create a LinkedIn post mentioning our CEO:
"Excited to share insights from @{urn:li:person:4986615|Serge Bulaev} on the future of AI in content creation."
Multi-Image Post
Create a LinkedIn post with 4 product screenshots showing our new dashboard features.
Note: Images will appear in a grid layout, not as a swipeable carousel.
PDF Document Post
Share our Q4 report as a PDF on LinkedIn with a summary caption.
This is the best way to share multi-page carousel-like content.
Best Practices
- First line matters: First 210 characters appear before "see more" - make them compelling
- Optimal length: Posts under 1,300 characters tend to perform better
- Posting times: Tuesday-Thursday, 8-10 AM in your audience's timezone
- Hashtags: Use 3-5 relevant hashtags - they're supported as plain text
- Engagement: End with a question to encourage comments
Troubleshooting
| Error | Cause | Solution |
|---|---|---|
| "Account not connected" | LinkedIn OAuth expired | Reconnect in Publora dashboard |
| "MEDIA_ASSET_PROCESSING_FAILED" | File too large or wrong format | Check: images < 5 MB, videos < 500 MB MP4 |
| "Rate limited" (429) | Too many API calls | Wait and retry with backoff |
| "Cannot mix media types" | Images + video in same post | Use only one media type per post |
| MCP unavailable | Server issue | Use REST API fallback (see above) |
Files in this skill
1linkedin-post skill questions
How do I install the linkedin-post skill in Claude Code?
Run npx degit publora/skills/skills/linkedin-post ~/.claude/skills/linkedin-post. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the linkedin-post skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
How do I mention people or companies in my posts?
You must use URN syntax, such as @{urn:li:person:MEMBER_ID|Display Name} for people or @{urn:li:organization:ORG_ID|Company Name} for companies.