Linkedin Analytics logo

Linkedin Analytics

Organization
publora
linkedin-analytics

Analyze LinkedIn performance and manage engagement through Publora. Use when the user asks how a LinkedIn post or account performed (impressions, reach, reactions, comments, reshares, follower growth) or wants to react, comment, reshare or resolve an @mention. Statistics run over the REST API, engagement over MCP tools. Not for creating posts (use linkedin-post).

Overview

Publisherpublora
Repositoryskills
Skill namelinkedin-analytics
Stars
62
Forks
6
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by publora on GitHub. Read the source before you install it.

Installation

Install the Linkedin Analytics AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/publora/skills/tree/main/skills/linkedin-analytics
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/publora/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/linkedin-analytics .claude/skills/linkedin-analytics
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Linkedin Analytics in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Linkedin Analytics on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Linkedin Analytics is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

LinkedIn Analytics

Track impressions, engagement and follower growth for your LinkedIn posts and profile, and interact with posts through reactions, comments and reshares. Statistics come from the REST API; reactions, comments, reshares and mention lookups are MCP tools.

Prerequisites

Plans: Works on the free Starter plan. Current limits and pricing: publora.com/pricing.

Getting Started

  1. Create account at publora.com/register (free)
  2. Connect LinkedIn via OAuth in Publora Dashboard
  3. 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
  4. Connect your agent to the MCP server at https://mcp.publora.com/mcp:
    • Upgrading a manual connection without /mcp: Claude treats https://mcp.publora.com as a different server from the bundled one. Change that existing connection to https://mcp.publora.com/mcp in 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-skills plugin 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 /mcp to sign in:
bash
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:
bash
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):

bash
# Get your connected platforms
curl -X GET "https://api.publora.com/api/v1/platform-connections" \
  -H "x-publora-key: sk_your_api_key"

# Get post statistics
curl -X POST "https://api.publora.com/api/v1/linkedin-post-statistics" \
  -H "x-publora-key: sk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "platformId": "linkedin-abc123",
    "postedId": "urn:li:share:7123456789012345678",
    "queryTypes": "ALL"
  }'

# Get account statistics
curl -X POST "https://api.publora.com/api/v1/linkedin-account-statistics" \
  -H "x-publora-key: sk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "platformId": "linkedin-abc123",
    "queryTypes": "ALL"
  }'

Platform ID Format: linkedin-{id} where {id} is from /platform-connections response.

Example IDs: linkedin-Tz9W5i6ZYG, linkedin-abc123xyz

📖 Full API documentation: docs.publora.com

Analytics Tools (REST only)

LinkedIn analytics are not exposed as MCP tools. The MCP server carries posting, media and LinkedIn engagement tools; statistics live only on the REST API, so call these endpoints directly with the x-publora-key header. Asking an agent for an linkedin_post_stats MCP tool will fail: there is no such tool.

POST /linkedin-post-statistics

Engagement metrics for one post.

Body:

  • platformId: platform connection ID (e.g. linkedin-abc123), from list_connections
  • postedId: post URN (urn:li:share:... or urn:li:ugcPost:...)
  • queryTypes (optional): IMPRESSION, MEMBERS_REACHED, RESHARE, REACTION, COMMENT, or ALL

Returns: impressions, unique impressions (members reached), reactions, comments, reshares, and a cached flag telling you whether the numbers came from cache.

POST /linkedin-account-statistics

Aggregated statistics for the account.

Body: platformId, optional queryTypes, optional aggregation (DAILY or TOTAL, default TOTAL).

POST /linkedin-followers

Follower count or growth over time.

Body: platformId, optional period (lifetime or daily), optional dateRange ({start: {year, month, day}, end: {year, month, day}}).

POST /linkedin-profile-summary

Combined profile overview: followers plus statistics.

Body: platformId, optional dateRange.

bash
curl -X POST "https://api.publora.com/api/v1/linkedin-post-statistics" \
  -H "x-publora-key: sk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"platformId": "linkedin-abc123", "postedId": "urn:li:share:7123456789012345678", "queryTypes": "ALL"}'

Engagement Tools

linkedin_create_reaction

React to a LinkedIn post.

Parameters:

  • postedId: LinkedIn post URN
  • platformId: Platform connection ID
  • reactionType: One of the following:
TypeDescription
LIKEStandard thumbs up
PRAISEClapping hands / applause
EMPATHYHeart / love
INTERESTLightbulb / insightful
APPRECIATIONSupportive
ENTERTAINMENTFunny / laughing

linkedin_delete_reaction

Remove your reaction from a post.

Parameters:

  • postedId: LinkedIn post URN
  • platformId: Platform connection ID

linkedin_create_comment

Post a comment on a LinkedIn post (max 1,250 characters).

Parameters:

  • postedId: LinkedIn post URN
  • platformId: Platform connection ID
  • message: Comment text (max 1,250 characters)
  • parentComment (optional): Comment URN for nested replies

linkedin_delete_comment

Remove a comment you made.

Parameters:

  • postedId: LinkedIn post URN
  • commentId: Comment URN or numeric ID
  • platformId: Platform connection ID

linkedin_create_reshare

Reshare an existing post, with optional commentary.

Parameters:

  • platformId: platform connection ID
  • parent: the post to reshare, as a share URN (urn:li:share:... or urn:li:ugcPost:...). Note the name: this tool takes parent, not postedId like the reaction and comment tools.
  • commentary (optional): your text above the reshare, up to 3,000 characters
  • visibility (optional): PUBLIC or CONNECTIONS, default PUBLIC. CONNECTIONS is for personal accounts.

Note: a LinkedIn feed URL carries an activity id, which is not always the same as the share id. Use the postedId returned by get_post, not a hand-converted activity id.

linkedin_list_mentionables

Resolve names to the URNs that @mentions need, so you never hand-write a member id.

Parameters:

  • q (optional): the name to search for
  • limit (optional): how many results to return

Both are optional, and this tool takes no platformId: it searches across the account rather than one connection.

Example Prompts

Weekly Performance Review

Analyze my LinkedIn performance for the last 7 days.
Show me:
1. Which posts performed best
2. My engagement rate trends
3. Follower growth
4. Recommendations for improvement

Post Analysis

Get detailed stats for my last 5 LinkedIn posts and identify patterns in what content resonates with my audience.

Engagement Campaign

React with PRAISE to my colleague's post about their promotion (urn:li:share:123456) and add a congratulatory comment.

Follower Tracking

Show my LinkedIn follower growth for the last 30 days. How many new followers did I gain each week?

Metrics Reference

MetricDescription
IMPRESSIONTotal times content appeared in feeds
MEMBERS_REACHEDUnique LinkedIn members who saw the post
RESHARENumber of reposts/shares
REACTIONTotal reactions (all types combined)
COMMENTNumber of comments

Engagement Rate Benchmarks

Average LinkedIn engagement rates by follower count:

FollowersGood Engagement Rate
< 5K3-5%
5K-50K2-3%
50K+1-2%

Good performing posts typically have:

  • 2x your average impressions
  • Comment-to-reaction ratio above 10%
  • Engagement rate above your baseline

Important Notes

  1. Analytics delay: LinkedIn analytics may take up to 24 hours to fully populate. Querying immediately after posting returns partial data.

  2. URN formats: LinkedIn URLs use urn:li:activity:xxx but the API requires urn:li:share:xxx or urn:li:ugcPost:xxx. Use the postedId from Publora's get_post response for accurate URNs.

  3. Caching: Analytics responses may be cached. The response includes a cached field indicating if data came from cache.

  4. Rate limits: LinkedIn has approximately 200+ API calls per hour. Implement backoff on 429 errors.

Troubleshooting

ErrorCauseSolution
"Platform ID not found"Invalid connection IDRun list_connections to get valid IDs
"Post not found"Wrong URN formatUse urn:li:share: or urn:li:ugcPost: format
429 Too Many RequestsRate limitedWait and retry with exponential backoff
"message cannot exceed 1250 characters"Comment too longShorten comment to under 1,250 chars

Frequently asked questions

What does the Linkedin Analytics AI skill do?

Analyze LinkedIn performance and manage engagement through Publora. Use when the user asks how a LinkedIn post or account performed (impressions, reach, reactions, comments, reshares, follower growth) or wants to react, comment, reshare or resolve an @mention. Statistics run over the REST API, engagement over MCP tools. Not for creating posts (use linkedin-post).

Why use Linkedin Analytics on TypingMind?

Because you install it once and use it with any model. Linkedin Analytics is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Linkedin Analytics in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/publora/skills/tree/main/skills/linkedin-analytics. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Linkedin Analytics?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Linkedin Analytics?

As many as you like. As long as a model supports skills, you can use Linkedin Analytics with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Linkedin Analytics AI skill free?

Yes. It is published on GitHub by publora under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇