Run a LinkedIn account with eleven free Claude skills and a local humanizer
An open-source MIT repository by Jake Schincariol packages eleven Claude skills for drafting LinkedIn posts, comments, replies, DMs and weekly plans. A bundled local humanizer cleans AI-style text and scores each draft before the user posts it by hand.
The problem
Drafting LinkedIn content with a language model tends to produce text with recognisable tells: stock vocabulary, em dashes and invisible Unicode characters. Posting automatically through the site risks account restrictions, and there is no official API for personal-profile posting without an approved partner app. Managing posts, comments, replies, DMs and profile upkeep by hand also takes steady effort.
Steps
- Install the repo as a Claude Code skill set by cloning it and copying the li-* skill folders into ~/.claude/skills/, or add it via the plugin marketplace.
- Alternatively, paste the repo URL into Claude and ask it to install the skill and confirm /li-post works.
- Copy templates/voice.md to ~/.claude/linkedin/voice.md and fill in your voice profile, or have Claude write it from three of your own posts.
- Run a command such as /li-post to turn one idea into three hook options and a humanized draft.
- Optionally run humanize.py and detect.py locally on a draft to clean it and score it on five checks.
- Review the copy-ready output and paste it into LinkedIn yourself.
From the official docs
python3 humanize.py draft.txt --report
python3 detect.py draft.txt
python3 detect.py before.txt after.txtResults
- In the author's example run on a deliberately poor draft, the human score rose from 24.8 (FLAGGED) to 69.7 (REVIEW) after humanize.py, a change of +44.9.
- The author states the five checks are local heuristics, not calls to detectors such as GPTZero or Turnitin, and cannot promise their verdicts.
- As reported by the repository README, the lexicon holds 113 stock terms and the kit includes 21 hook formulas.
As reported by the source (GitHub repository README (Jakeschincariol/linkedin-agent-skill)); AgentGid did not measure these figures.
This suits solo creators or small teams already comfortable with Claude Code and the terminal, plus a few minutes to write a voice file. Claude Code needs a paid plan ($20/mo), and the humanizer scores are the author's own local heuristics, not real detector results. If you'd rather avoid a subscription, Pi (Free, OSS) is a cheaper terminal option, though the skills are built for Claude.
The agent used here
Similar use cases
Run a YouTube channel with eleven Claude skills for scripts, edits and retention
An open-source MIT pack of eleven Claude skills helps a YouTube creator draft scripts, package titles and thumbnails, cut edits, read retention data and plan a week of content. It…
The pack bundles eleven skills and six dependency-free Python tools, including a hook scorer, title and thumbnail linter, dead-air detector, chapter …
Run an Instagram account with thirteen open-source Claude skills
A developer published a free, MIT-licensed set of thirteen Claude skills that help plan, write, lint and audit Instagram content, including Reels, captions, carousels and DMs. The…
The author tested the hook scorer on 74 real short-form hooks (YouTube Shorts, not Reels): AUC 0.83 against ten deliberately bad hooks, but only AUC …
Make continuous-take product launch films with the onetake agent skill
The onetake repository is a Claude Agent Skill that lets a coding agent produce product launch films, teasers and feature demos as one continuous camera take. An automated oracle …
The README lists ten example films across concept ads, launch films, app promos and feature demos, each with a finished film and a breakdown document…
Guides
Claude Code Deploys: 6 Open-Source Repos for a Containment System, Checked
A viral post says GitHub Actions, Argo CD, Argo Rollouts, Prometheus, Sentry and OpenTelemetry turn Claude Code deploys into a containment system. We checked each: role, license, what needs Kubernetes, and what Claude Code's own permissions add.
How to Cut Token Usage in Claude Code and Cursor (2026)
Practical ways to spend fewer tokens with Claude Code and Cursor: measure first, keep context small, match the model to the task, filter what the agent reads, and the open-source tools that help.
Sonnet Builds, Opus Reviews, Haiku Reads: Does the Claude Code Advisor Save Money?
A viral post says running Sonnet, Haiku and Opus together in Claude Code gives better code for fewer tokens. We checked it against Anthropic's docs and prices: when the advisor pays off, when it costs more, and why a ready project kit matters more than the model mix.
JEV for Claude Code: A Second Opinion on Every Command, Checked
A viral post says jev-axi screens every command your Claude Code agent runs for a fraction of a cent. We read the repo, TypeSafe's docs and privacy policy: what runs locally, what is sent, how it fails, and how it compares with auto mode.