Draft and audit LinkedIn content with LinkedIn Skills
Use LinkedIn Skills when an agent needs to draft posts, comments, replies, audits, profile rewrites, or content plans while preserving explicit approval before publishing.
npx skills add agentskillexchange/skills --skill draft-and-audit-linkedin-content-with-linkedin-skills
LinkedIn Skills is an open SKILL.md bundle for agent-assisted LinkedIn marketing work. It includes workflows for writing posts, drafting comments and replies, auditing drafts, extracting hooks, planning content, optimizing profiles, monitoring engagement, employee advocacy, repurposing content, and humanizing text. Optional Apify and Publora integrations add read-side data access and scheduled publishing, while the documented workflow keeps approval before anything is posted.
What this skill actually does
Invoke this instead of using LinkedIn or a social scheduler directly when the operator wants an agent to work from campaign context, URLs, pasted content, or audience notes and return reviewable drafts before any external action. The scope boundary is LinkedIn workflow execution inside SKILL.md-compatible agents; it is not a general LinkedIn product listing, not a scraping service listing, and not an autoposter without human review.
Inputs and prerequisites: Claude Code, Codex, OpenClaw, Hermes, or another SKILL.md-compatible agent; optional Apify token for read-side LinkedIn data; optional Publora API credentials for scheduled publishing.
Setup notes: For Codex CLI, run codex plugin marketplace add sergebulaev/linkedin-skills and codex plugin add linkedin-skills@linkedin-skills. For Claude Code, run /plugin marketplace add sergebulaev/linkedin-skills and /plugin install linkedin-skills@linkedin-skills. For generic SKILL.md agents, run npx skills add sergebulaev/linkedin-skills or clone the repository and point the agent at the skills directory.
Source and verification boundary: use https://github.com/sergebulaev/linkedin-skills as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.