One draft gets a verdict, a preview of what shows before 'see more', a list of findings with fixes, and a tidied copy laid out for phone reading.
Who it is for: Consultant, founder, recruiter or small-business owner who writes their own LinkedIn posts a few times a week.
Format: Claude skill pack · Version: 1.0.1 · Tested on: Python 3.13.5 (standard library only)
What it does
It counts characters against LinkedIn's 3,000 limit and shows the first 200 characters (you can change this) as readers see them before 'see more'. It flags a first line that runs past that point or opens with a greeting, paragraphs over 350 characters in one block, more hashtags than you allow, hashtags scattered through the body, more than 8 emoji, words in capitals, Unicode bold or italic letters, cliches such as 'thrilled to announce', asks like 'comment YES', sentences over 30 words, low reading ease, and any word on your banned list. The tidied copy splits dense paragraphs into one or two sentences per line and moves hashtags to the end.
What you need
- Claude.ai with code execution switched on (or Claude Code, or just Python 3.10+)
- Your draft post
5-minute setup
- Claude.ai: open Settings → Capabilities → Skills, click Upload skill and pick
claude-ai-upload/linkedin-post-check.zip. - Claude Code: copy the folder
skills/linkedin-post-checkinto~/.claude/skills/. - Start a new chat. Attach your file and say: "Use linkedin-post-check. Is this post ready? Then tighten it without changing my facts".
- 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 draft:
python3 skills/linkedin-post-check/scripts/core.py --post samples/post-draft.txt --out out
You should see 'worth a second look' with 5 warnings: a first line past the 'see more' cut, 7 hashtags, two cliches and a 'comment YES' ask. In Claude, paste your draft and use the prompt above.
Settings you can change
| Option | Default | What it is |
|---|---|---|
--post |
(required) |
Text file with one LinkedIn post |
--fold |
200 |
Characters readers see before 'see more' (60-400) |
--max-hashtags |
5 |
Most hashtags you want in a post |
--banned |
(none) |
Comma-separated words you never use |
--out |
out |
Output folder |
What goes in and what comes out
Inputs: One LinkedIn post draft (text file or pasted); Optional: 'see more' cut, hashtag maximum, banned words
Outputs: check.md with the verdict, the 'see more' preview and findings; post-tidy.txt laid out for phone reading
What Pro adds
- Check a whole batch of drafts at once, with duplicates caught
- Your sign-off and banned words enforced on every draft
- A posting calendar from your content pillars and ideas, with rotating formats and hook drafts
- Turn an article or newsletter into list, story and how-to post drafts
Pro: https://oarsmanai.com/agents/linkedin-post-studio-pro/
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: - One post per run. - Checks writing habits; it does not predict reach or engagement. - English wording checks only. - Never posts or schedules anything.
Not tested by us: - posts in languages other than English - how each phone app wraps lines
Files
- oarsman-linkedin-post-check-v1.0.1.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.