One export (plus an older one to compare) becomes report.md with top posts, weekday medians, follower gains, quadrants, tag results and audience match, plus posts.csv, weekly.csv and SVG charts.
Who it is for: Founder, consultant, CA, recruiter or freelancer who posts on LinkedIn 2-5 times a week to win clients and wants to know what is working without a monthly LinkedIn tool.
Format: Claude skill pack · Version: 1.0.0 · Tested on: Python 3.13.5 (standard library only)
What it does
It reads the .xlsx directly (no Excel needed). From DISCOVERY it takes impressions and members reached, from ENGAGEMENT the daily impressions and engagements (rolled into Monday-start weeks), and from FOLLOWERS the total and daily new followers. The two side-by-side TOP POSTS lists are merged per post URL. Each post gets an engagement rate (engagements / impressions) and a weekday. Weekdays are ranked by median impressions, and only days with 3+ posts count. Posts are placed in quadrants around the median reach and rate. New followers in the 3 days from each post are summed (timing, not proof). Your url,tag file compares formats and topics by median. Your ideal-customer terms are matched against content (or audience) demographics. An earlier export gives the percentage change for each headline number.
What you need
- Claude.ai with code execution switched on (or Claude Code, or just Python 3.10+)
- Your own LinkedIn analytics export (desktop: Analytics > Content analytics > Export)
5-minute setup
- Claude.ai: open Settings → Capabilities → Skills, click Upload skill and pick
claude-ai-upload/linkedin-analytics-report-pro.zip. - Claude Code: copy the folder
skills/linkedin-analytics-report-prointo~/.claude/skills/. - Start a new chat. Attach your file and say: "Use linkedin-analytics-report-pro. Here are my last two quarterly LinkedIn exports and my post tags; what should I post more of, and on which days?".
- Claude runs the script and gives you the files listed under Outputs. Check them before you act on them.
Try it with the sample
Run the sample (two fictional quarterly exports for an accounting founder, plus post tags):
python3 skills/linkedin-analytics-report-pro/scripts/core.py samples/AggregateAnalytics_sample_Aug-Oct-2026.xlsx --previous samples/AggregateAnalytics_sample_May-Jul-2026.xlsx --tags samples/post-tags.csv --icp "founder,accountant,accounting,bengaluru" --charts --out out
You should see 89,189 impressions (+28% on the previous quarter) and 33 posts. Wednesday and Tuesday come out as the strongest days, the follower total is 4,880 (+309), and 17% of viewers are founders or accountants.
Settings you can change
| Option | Default | What it is |
|---|---|---|
export |
(required) |
Your LinkedIn analytics export (.xlsx) |
--previous |
(optional) |
An earlier export to compare with |
--tags |
(optional) |
CSV of url,tag (format or topic; ; for several) |
--icp |
(optional) |
Comma-separated job titles, industries or locations you want to reach |
--charts |
(off) |
Write SVG charts |
--follow-window |
3 |
Days after a post to count new followers |
--min-posts-per-day |
3 |
Posts needed on a weekday to rank it |
--date-order |
mdy |
mdy or dmy for dates like 03/04/2026 |
--out |
out |
Output folder |
What goes in and what comes out
Inputs: Your LinkedIn creator analytics export (.xlsx, Content analytics > Export; up to 365 days); Optional: an earlier export, a url,tag CSV for format/topic, the job titles or industries you want to reach
Outputs: report.md; posts.csv (date, weekday, impressions, engagements, rate, quadrant, followers after); weekly.csv; weekly-impressions.svg and weekday-impressions.svg
AI disclosure and limits
This product does not call an AI model at run time. It was built by Oarsman AI's AI agents and checked by the automated tests shipped with it.
Limits: - Reads only your own exported file; LinkedIn's export lists at most 50 posts per ranking and has no post times or text. - Follower gains after a post are timing, not proof of cause. - Personal profile exports only, not LinkedIn Page exports.
Not tested by us: - LinkedIn Page (company) analytics exports, which have a different layout - exports in languages other than English - the desktop post-performance CSV
Files
- oarsman-linkedin-analytics-report-pro-v1.0.0.zip
- CHANGELOG.md
- QA-REPORT.json
- README.md
- SPEC.md
- SUPPORT.md
- TROUBLESHOOTING.md
- VERSION
- VIDEO-SCRIPT.md
- claude-ai-upload
- diagram.mmd
- diagram.png
- preview.png
- samples
- skills
- tests
Help
Self-serve: see TROUBLESHOOTING.md (fixes and FAQ). There is no call, chat or email support. Fixes ship as new versions at your download link. Refund: 14 days, works as described, through the checkout platform.