linkedin-analytics skill
✓ VerifiedAnalyze LinkedIn post performance and manage engagement through reactions, comments, reshares, and mention lookups.
- GitHub stars
- 68
- Files
- 1
- Last commit
- Nov 10, 2026
- License
- MIT
- Allowed tools
- —
What does the linkedin-analytics skill do?
linkedin-analytics analyzes LinkedIn post performance and manage engagement through reactions, comments, reshares, and mention lookups.
Summary generated from the skill's SKILL.md.
About the linkedin-analytics skill
Monitoring LinkedIn post performance and managing social engagement is what this skill enables for content creators and social media managers. It allows an agent to track impressions, reach, reactions, comments, reshares, and follower growth by accessing statistics through a REST API. While analytics data is retrieved via API calls, active engagement is handled through specific MCP tools.
Users can instruct an agent to interact with content by applying various reaction types like LIKE, PRAISE, or EMPATHY, posting comments up to 1,250 characters, or performing reshares with optional commentary. The skill also includes a mention lookup tool to resolve names into the URNs required for @mentions. This toolset is designed for analysis and interaction rather than creating new posts, which requires a different specialized skill.
What an agent can do with it
- 1Analyze weekly post performanceRequest a summary of your best performing posts and follower growth trends over the last seven days.
- 2Automate social engagementAsk the agent to react to a specific colleague's post with praise and leave a congratulatory comment.
- 3Track follower growth metricsGet a report on how many new followers your account has gained on a weekly basis over the past month.
- 4Resolve user mentionsFind the correct URN for a specific person to ensure an @mention works correctly in a comment.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the linkedin-analytics 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-analytics skill in Plugin
/plugin marketplace add publora/skills /plugin install publora-skills@publora-skills
Install the linkedin-analytics skill in Claude Code
~/.claude/skills/linkedin-analytics/SKILL.md
$ npx degit publora/skills/skills/linkedin-analytics ~/.claude/skills/linkedin-analyticsInstall the linkedin-analytics skill in Claude Code (project)
.claude/skills/linkedin-analytics/SKILL.md
$ npx degit publora/skills/skills/linkedin-analytics .claude/skills/linkedin-analyticsInstall the linkedin-analytics skill in Codex
~/.agents/skills/linkedin-analytics/SKILL.md
$ npx degit publora/skills/skills/linkedin-analytics ~/.agents/skills/linkedin-analyticsInstall the linkedin-analytics skill in Gemini CLI
~/.gemini/skills/linkedin-analytics/SKILL.md
$ npx degit publora/skills/skills/linkedin-analytics ~/.gemini/skills/linkedin-analyticsInstall the linkedin-analytics skill in Claude.ai
npx degit publora/skills/skills/linkedin-analytics linkedin-analytics && zip -r linkedin-analytics.zip linkedin-analytics # claude.ai → Customize → Skills → + → Create skill → Upload a skill → linkedin-analytics.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-analytics is public and reachablegithub.com/publora/skills/tree/HEAD/skills/linkedin-analytic ↗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-analytic ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/publora/skills/blob/HEAD/skills/linkedin-analytic ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 245 linesgithub.com/publora/skills/blob/HEAD/skills/linkedin-analytic ↗Pass
SKILL.md
View on GitHubLinkedIn 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
- 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"
# 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), fromlist_connectionspostedId: post URN (urn:li:share:...orurn:li:ugcPost:...)queryTypes(optional):IMPRESSION,MEMBERS_REACHED,RESHARE,REACTION,COMMENT, orALL
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.
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 URNplatformId: Platform connection IDreactionType: One of the following:
| Type | Description |
|---|---|
LIKE |
Standard thumbs up |
PRAISE |
Clapping hands / applause |
EMPATHY |
Heart / love |
INTEREST |
Lightbulb / insightful |
APPRECIATION |
Supportive |
ENTERTAINMENT |
Funny / laughing |
linkedin_delete_reaction
Remove your reaction from a post.
Parameters:
postedId: LinkedIn post URNplatformId: Platform connection ID
linkedin_create_comment
Post a comment on a LinkedIn post (max 1,250 characters).
Parameters:
postedId: LinkedIn post URNplatformId: Platform connection IDmessage: 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 URNcommentId: Comment URN or numeric IDplatformId: Platform connection ID
linkedin_create_reshare
Reshare an existing post, with optional commentary.
Parameters:
platformId: platform connection IDparent: the post to reshare, as a share URN (urn:li:share:...orurn:li:ugcPost:...). Note the name: this tool takesparent, notpostedIdlike the reaction and comment tools.commentary(optional): your text above the reshare, up to 3,000 charactersvisibility(optional):PUBLICorCONNECTIONS, defaultPUBLIC.CONNECTIONSis 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 forlimit(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
| Metric | Description |
|---|---|
IMPRESSION |
Total times content appeared in feeds |
MEMBERS_REACHED |
Unique LinkedIn members who saw the post |
RESHARE |
Number of reposts/shares |
REACTION |
Total reactions (all types combined) |
COMMENT |
Number of comments |
Engagement Rate Benchmarks
Average LinkedIn engagement rates by follower count:
| Followers | Good Engagement Rate |
|---|---|
| < 5K | 3-5% |
| 5K-50K | 2-3% |
| 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
-
Analytics delay: LinkedIn analytics may take up to 24 hours to fully populate. Querying immediately after posting returns partial data.
-
URN formats: LinkedIn URLs use
urn:li:activity:xxxbut the API requiresurn:li:share:xxxorurn:li:ugcPost:xxx. Use thepostedIdfrom Publora'sget_postresponse for accurate URNs. -
Caching: Analytics responses may be cached. The response includes a
cachedfield indicating if data came from cache. -
Rate limits: LinkedIn has approximately 200+ API calls per hour. Implement backoff on 429 errors.
Troubleshooting
| Error | Cause | Solution |
|---|---|---|
| "Platform ID not found" | Invalid connection ID | Run list_connections to get valid IDs |
| "Post not found" | Wrong URN format | Use urn:li:share: or urn:li:ugcPost: format |
| 429 Too Many Requests | Rate limited | Wait and retry with exponential backoff |
| "message cannot exceed 1250 characters" | Comment too long | Shorten comment to under 1,250 chars |
Files in this skill
1linkedin-analytics skill questions
How do I install the linkedin-analytics skill in Claude Code?
Run npx degit publora/skills/skills/linkedin-analytics ~/.claude/skills/linkedin-analytics. 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-analytics 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 format a LinkedIn post ID for the API?
You must use the URN format, specifically urn:li:share: or urn:li:ugcPost:. Do not use the activity ID found in a LinkedIn feed URL.
How long does it take for LinkedIn analytics to update?
There can be a delay of up to 24 hours before LinkedIn analytics are fully populated.