The LinkedIn agent skill
A set of Claude skills that run a LinkedIn account: posts from hook formulas, comments, replies, profile scoring and a humanizer that strips AI tells
Medium risk
We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.
Why this level
- Runs local Python scripts over your text
- Prepares public text that you then post yourself
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/the-linkedin-agent-skillDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Run one by one in the Claude Code chat
/plugin marketplace add jakeschincariol/linkedin-agent-skill
/plugin install linkedin-agent@linkedin-agent-skillInstall the plugin: /plugin marketplace add Jakeschincariol/linkedin-agent-skill, then /plugin install linkedin-agent. Fill in voice.md with your voice before the first post.
Other ways from the author
/plugin marketplace add Jakeschincariol/linkedin-agent-skill
/plugin install linkedin-agentAfter install, fill in voice.md with your voice.
This is third-party code. Review the repository files before installing.
What it does
The plugin adds eleven skills for working with LinkedIn. One writes a post from an idea using hook formulas, another comments on other people's posts, another sorts the replies under your post, and one scores your profile against a rubric and rewrites the weak parts. A separate humanizer skill strips invisible characters, typographic tells and stock vocabulary from a draft, then scores it against five checks. The skills only prepare text; you do the posting.
Who it is for. For people who run their own LinkedIn: marketers, sales professionals and personal-brand authors.
Good fit when
- You want to build a post from an idea with hook options
- You want to handle comments and replies under posts
- You want to clean a draft of machine-text tells before posting
Not a fit when
- You want full auto-posting without manual control
- You do not work in Claude and will not install the skills
Example request
Draft a LinkedIn post from this idea: give three hook options and one draft, cleaned of AI tellsLimitations
The skills prepare text but never post or connect to LinkedIn; publishing stays with you. The humanizer is two dependency-free Python scripts that run locally and upload nothing. LinkedIn itself is not reachable from Russia without a VPN, which is worth noting separately. For your own voice you fill in a voice.md file, otherwise the text comes out impersonal.
How to disable. Remove the plugin via /plugin in Claude Code or delete the li-* folders from ~/.claude/skills.
Security check
- Runs local Python scripts over your text
- Prepares public text that you then post yourself
README in short
The README describes eleven Claude skills for running LinkedIn: a post from an idea via hook formulas, comments, replies, profile scoring, a weekly plan and a humanizer. Nothing is posted without your decision; the skills write and you post. Installation is via /plugin marketplace add and /plugin install or by copying the li-* folders into the skills directory. The humanizer runs two local Python scripts with no data upload. It suggests filling in voice.md with your own voice. MIT licensed.
FAQ
Do the skills post on their own?
No. They only write text and prepare drafts; you publish manually.
What does the humanizer do?
It removes invisible characters, em dashes, curly quotes and stock vocabulary, then scores the text against five naturalness checks.
Related
A skill that strips AI writing tells from text using Wikipedia's list, without adding invented facts
Marketing Skills for AI agents
Marketing Skills for AI Agents
About fifty skills for CRO, copywriting, SEO, analytics, ads and launches, built for coding agents
SendPulse MCP server
SendPulse MCP
SendPulse's official remote MCP server: statistics, campaigns and user data through an agent chat
Yandex Direct MCP generated from a machine-readable schema
yandex-direct-mcp
An MCP server and CLI covering all 113 Yandex Direct API v5 methods generated from WSDL, exposing 9 read tools by default and writes only on demand