⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
linkedin-posting
Write, review, and publish LinkedIn posts from an OpenClaw agent. Use when asked to create a LinkedIn post, write LinkedIn content, draft a post for review, or publish to LinkedIn. Posts are drafted first and sent to Discord for human review before publishing — never auto-post. Supports AM/PM cadence, brand voice guidance, hashtag strategy, and the P.S. pattern for AI/builder brand posts. Configure: set BRAND_NAME, PROJECTS, DISCORD_WEBHOOK_URL, and optional CRON_SCHEDULE in CONTEXT.md.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
LinkedIn API Client
Reverse-engineered LinkedIn API client in Python. Posts, messages, engagement, feed, search, and jobs via a Python library or REST API.
Use it directly in Python or serve it as a FastAPI backend.
Install
pip install linkedin-api
Or from source:
git clone https://github.com/tylerdotai/linkedin-skill.git
cd linkedin-skill/linkedin_api
pip install -e .
Quick Start
Set your vault key:
export LINKEDIN_VAULT_KEY="your-vault-passphrase"
Authenticate and post:
from linkedin_api.core.auth import authenticate
from linkedin_api.capabilities.posting import post_text
authenticate("you@example.com", "your-password")
result = post_text("Hello from the LinkedIn API!")
print(result["post_url"])
authenticate() uses patchright to open a real Chromium browser, log in interactively, and capture session cookies. The cookies are stored encrypted with AES-256-GCM in ~/.config/linkedin_api/vault.enc. You only need to call it once per session.
For AI Agents
To install:
git clone https://github.com/tylerdotai/linkedin-skill.git
cd linkedin-skill/linkedin_api
pip install -e .
Required env var: LINKEDIN_VAULT_KEY (any passphrase — encrypts your session).
FlareSolverr must be running on localhost:8191.
Usage:
from linkedin_api.capabilities.posting import post_text
post_text("Your post here")
Features
- Post text (with optional image upload)
- Send direct messages
- Like and comment on posts
- Fetch your feed
- Search people and profiles
- Search and bookmark jobs
- Connection requests
- Post analytics (views, likes, comments, shares)
Architecture Highlights
- FlareSolverr proxy browser (bypasses Cloudflare)
- AES-256-GCM encrypted vault for session cookies
- FastAPI REST server available
- Python 3.11+, no official LinkedIn API needed
Documentation
See linkedin_api/README.md for:
- Full API endpoints reference
- Authentication and Vault details
- Architecture deep-dive
- Current limitations
- Project structure
Related
- linkedin_api/ — Python package source
- SKILL.md — OpenClaw agent skill (separate workflow)
- FlareSolverr — Cloudflare bypass proxy
License
MIT
// HOW IT'S BUILT
KEY FILES