# AI use cases for Linkedin Agent Skill (Jakeschincariol/linkedin-agent-skill) Repo: [Jakeschincariol/linkedin-agent-skill](https://github.com/Jakeschincariol/linkedin-agent-skill) | Use cases: 5 | Page: https://dedupedai.com/use-cases/jakeschincariol-linkedin-agent-skill/ A set of eleven free Claude skills that write LinkedIn posts, comments, replies, profile edits, weekly plans and audits, with a local humanizer that cleans and scores drafts before you post them by hand. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Turn one idea into a LinkedIn post you approve: https://dedupedai.com/use-cases/jakeschincariol-linkedin-agent-skill/draft-linkedin-post-from-one-idea/ - Strip AI tells from a draft and score it before posting: https://dedupedai.com/use-cases/jakeschincariol-linkedin-agent-skill/humanize-draft-before-posting/ - Score your LinkedIn profile and fix the weakest parts first: https://dedupedai.com/use-cases/jakeschincariol-linkedin-agent-skill/score-and-fix-linkedin-profile/ - Plan a week of LinkedIn posts and 10 engagement targets: https://dedupedai.com/use-cases/jakeschincariol-linkedin-agent-skill/plan-linkedin-week-and-engagement/ - Find which of your past posts actually worked: https://dedupedai.com/use-cases/jakeschincariol-linkedin-agent-skill/audit-past-linkedin-posts/ ## How to turn one idea into a LinkedIn post you approve with Linkedin Agent Skill Repo: [Jakeschincariol/linkedin-agent-skill](https://github.com/Jakeschincariol/linkedin-agent-skill) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Write a full post from a single idea, with three hook options and a humanized draft. **Who it is for:** A founder or consultant with a rough idea and 15 minutes who wants to publish a post this week without a blank page. **The problem:** Starting from nothing takes too long, and generic AI drafts read as slop to the people you are trying to reach. **The outcome:** A copy-ready post with three hook options from the 21 formulas, one full draft that has been humanized, and a block you paste yourself. ### Steps 1. Run `git clone https://github.com/Jakeschincariol/linkedin-agent-skill.git` in a terminal. 2. Run `cp -r linkedin-agent-skill/skills/li-* ~/.claude/skills/` to install the skills globally. 3. Run `cp templates/voice.md ~/.claude/linkedin/voice.md` from inside the cloned repo, then fill in the file or ask Claude to write it from three of your posts. (inferred, check the README) 4. In Claude Code, type `/li-post` and give it one idea in a sentence or two. 5. Pick one of the three hooks, read the full draft, and post it yourself on LinkedIn. ### Prompt to paste into your agent ```text Install the skills from https://github.com/Jakeschincariol/linkedin-agent-skill, fill in voice.md from the three posts at , then run /li-post on the idea: . Expected output: three hook options and one full draft with no em dashes and no invented numbers. Verify that any figure you did not supply appears as {{your number}}. ``` ### Caveat The skills write drafts only, so you must copy each post into LinkedIn yourself, and the quality depends on how well voice.md describes you. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-linkedin-agent-skill/draft-linkedin-post-from-one-idea/ ## How to strip AI tells from a draft and score it before posting with Linkedin Agent Skill Repo: [Jakeschincariol/linkedin-agent-skill](https://github.com/Jakeschincariol/linkedin-agent-skill) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README Clean invisible characters and stock phrases from any draft, then get a five-check human score. **Who it is for:** A writer or marketer who already has a draft from any source and wants a local check before it goes public. **The problem:** Drafts often carry invisible characters, em dashes and stock words like delve or leverage that make them read as machine-written. **The outcome:** A cleaned draft with a report of every change, plus a five-check score that shows what still needs a human rewrite. ### Steps 1. Run `git clone https://github.com/Jakeschincariol/linkedin-agent-skill.git` in a terminal. 2. Run `cp -r linkedin-agent-skill/skills/li-* ~/.claude/skills/` if you want the skill inside Claude as well. 3. Save your draft as draft.txt, then run `python3 humanize.py draft.txt --report` from the li-human folder. 4. Run `python3 detect.py draft.txt` to see the five-check score and the verdict. 5. Rewrite any flagged structures by hand, save as after.txt, then run `python3 detect.py before.txt after.txt` to see the delta. ### Prompt to paste into your agent ```text Use the li-human scripts in https://github.com/Jakeschincariol/linkedin-agent-skill on . Run humanize.py with --report, then detect.py, and return the cleaned text, the change report and the HUMAN SCORE. Verify that the score is shown for both the original and the cleaned file. ``` ### Caveat The five checks are local heuristics and not a guarantee against GPTZero, Originality or any other detector, so the score is a guide for rewriting, not a pass certificate. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-linkedin-agent-skill/humanize-draft-before-posting/ ## How to score your LinkedIn profile and fix the weakest parts first with Linkedin Agent Skill Repo: [Jakeschincariol/linkedin-agent-skill](https://github.com/Jakeschincariol/linkedin-agent-skill) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Get a 100-point profile score and a rewrite ordered by what loses the most points. **Who it is for:** A job seeker or founder whose LinkedIn profile is out of date and who wants a clear fix order before a campaign or application push. **The problem:** A profile that is vague or incomplete loses visitors, and it is hard to know which section to fix first. **The outcome:** A score out of 100 against a 12-part rubric and a rewrite in fix-first order, using only facts you supply. ### Steps 1. Run `git clone https://github.com/Jakeschincariol/linkedin-agent-skill.git` in a terminal. 2. Run `cp -r linkedin-agent-skill/skills/li-* ~/.claude/skills/` to install the skills. 3. Paste your current headline, about section and experience into Claude Code. 4. Type `/li-profile` and let it score you against the 12-part rubric. 5. Apply the rewrites in the order given, replacing any {{your number}} placeholder with a real figure you can back up. ### Prompt to paste into your agent ```text Using the li-profile skill from https://github.com/Jakeschincariol/linkedin-agent-skill, score the profile text I paste from and return the total out of 100 plus rewrites in fix-first order. Verify that no metric, client or outcome appears unless I supplied it. ``` ### Caveat The score follows the repo's own rubric, so it measures completeness and clarity against that rubric rather than LinkedIn's ranking of your profile. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-linkedin-agent-skill/score-and-fix-linkedin-profile/ ## How to plan a week of LinkedIn posts and 10 engagement targets with Linkedin Agent Skill Repo: [Jakeschincariol/linkedin-agent-skill](https://github.com/Jakeschincariol/linkedin-agent-skill) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Get a weekly plan of what to post, when to post it, and who to comment on. **Who it is for:** A marketer or founder who posts irregularly and wants a fixed weekly plan with named people to engage with. **The problem:** Posting without a plan leads to gaps, and engagement without targets is hard to keep up. **The outcome:** A plan saved as ~/.claude/linkedin/plan.md with the posts for the week, timing, and 10 people to engage with. ### Steps 1. Run `git clone https://github.com/Jakeschincariol/linkedin-agent-skill.git` in a terminal. 2. Run `cp -r linkedin-agent-skill/skills/li-* ~/.claude/skills/` to install the skills. 3. Make sure ~/.claude/linkedin/voice.md exists, then type `/li-plan` in Claude Code. 4. Review ~/.claude/linkedin/plan.md and move the posts into your own calendar. 5. Use `/li-comment` on the people in the plan before you publish your own posts. ### Prompt to paste into your agent ```text Run the li-plan skill from https://github.com/Jakeschincariol/linkedin-agent-skill for the week of , using my voice file and the topics: . Expect a plan written to ~/.claude/linkedin/plan.md with posts, timing and 10 engagement targets. Verify that the file exists and that no target was invented without my input. ``` ### Caveat The plan is a draft for you to act on, since the skills do not post or message anyone on LinkedIn for you. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-linkedin-agent-skill/plan-linkedin-week-and-engagement/ ## How to find which of your past posts actually worked with Linkedin Agent Skill Repo: [Jakeschincariol/linkedin-agent-skill](https://github.com/Jakeschincariol/linkedin-agent-skill) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Rank your published posts by engagement rate and reach multiple, not raw impressions. **Who it is for:** A creator who has posted for months and wants to know which topics and formats are worth repeating. **The problem:** Impressions alone hide which posts earned real engagement, so it is easy to repeat the wrong formats. **The outcome:** A ranked post-mortem of what you already published, judged by engagement rate and reach multiple. ### Steps 1. Run `git clone https://github.com/Jakeschincariol/linkedin-agent-skill.git` in a terminal. 2. Run `cp -r linkedin-agent-skill/skills/li-* ~/.claude/skills/` to install the skills. 3. Paste the text and the engagement numbers you can see for your recent posts into Claude Code. 4. Type `/li-audit` and ask for the ranking. 5. Use the top-ranked formats as input for your next `/li-post` run. ### Prompt to paste into your agent ```text Use the li-audit skill from https://github.com/Jakeschincariol/linkedin-agent-skill on the post data I paste from . Expect a ranking by engagement rate and reach multiple, with a short note on each. Verify that every number in the output comes from the data I supplied. ``` ### Caveat The audit can only rank the numbers you paste in, and the README does not say where those numbers should come from. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/jakeschincariol-linkedin-agent-skill/audit-past-linkedin-posts/