Draft Posts, Comments, and Replies5 skills
Write LinkedIn posts, comments, and replies in your voice with AI-powered drafting and approval gates.
Content Blueprint
Safety checkedWrite LinkedIn Posts and Comments in Your Voice
2sergebulaevMay 2026
10 skills for LinkedIn content operations: writing, auditing, planning, and publishing via Claude Code or Codex.
Content WritingContent Auditing & HumanizingContent Research & PlanningEngagement Tracking & AnalyticsProfile & Program Management
Install Prompt
Copy this prompt and paste it into your AI agent to install.
What problem does this solve?
Drafts LinkedIn posts, comments, and replies in your voice with approval gates before publishing. It handles LinkedIn's technical quirks (3 URN types, thread flattening, reaction bugs), strips AI tells, and integrates with Publora to publish directly to your account. No coding required.
How does it work?
Once installed, activate any skill by asking Claude about LinkedIn. 1. Provide a topic, draft, or post URL. 2. The skill reads the content, applies 2026 algorithm heuristics and voice rules, then shows you a draft. 3. You approve or edit. 4. On approval, the skill publishes via Publora (or returns copy-paste text if you prefer manual posting). Output: published posts and comments in your voice with drafts reviewed before going live.
Included Skill Groups
Audit Drafts and Strip AI Tells7 skills
Review drafts for algorithm compliance and AI fingerprints, then humanize text to match your natural voice.
Extract Hooks and Plan Weekly Content3 skills
Reverse-engineer viral post formulas and create a weekly content calendar with themes, formats, and posting times.
Monitor Threads and Analyze Engagers5 skills
Track replies to your comments in real time and segment post audiences by ICP fit and tier.
Optimize Profile and Run Employee Advocacy3 skills
Rewrite your LinkedIn profile for 2026 conversion patterns and launch a team advocacy program.
What's the biggest win?
Every LinkedIn touchpoint reflects your voice and stays informed by your research, because drafting and approval happen before publication.
What's required to run this?
Requires Python 3.8+ and requests + python-dotenv packages (installed via pip install -r requirements.txt) to enable Publora auto-posting. Apify token is optional for read-side operations; skills fall back to asking you to paste text if no token is set. Works in Claude Code, Claude Desktop, claude.ai web, Codex CLI, and as a mounted plugin in OpenClaw or custom agents (mount skills/*/SKILL.md files and import lib/ as Python). Publora handles LinkedIn's three URN types and reaction-type mapping automatically.
What should I watch out for?
Publora free tier limits 15 LinkedIn posts/month. Apify optional read-side integration costs $1-5 per 1,000 results. LinkedIn thread flattening means replies to replies must reference the top-level comment URN, not the reply's URN (skills handle this automatically). Some rare post URNs return activity type when the canonical is ugcPost; skills have a fallback.
Key Features
10 focused skills
Post writer, comment drafter, reply handler, humanizer, hook extractor, content planner, thread monitor, engager analytics, profile optimizer, employee advocacy.
Draft → approval → publish
Every skill shows you a draft first. Nothing posts without your explicit OK.
2026 algorithm tuned
Skills use LinkedIn's ranking foundation (360Brew), proven hook formulas, timing windows, and engagement metrics.
Publora auto-posting
Optional: auto-publish to LinkedIn, X, Threads, and Instagram. Free tier ships 15 posts/month. Falls back to copy-paste if you skip setup.
Voice rules baked in
No em dashes, no AI vocabulary, specific numbers, capitalized names. Skills apply 10 rules automatically.
Tools in this Blueprint
Apify (post/comment scraping)
Publora API
Publora (LinkedIn auto-publish API)
About This Blueprint
- License
- MIT
- Industry
- Technology
- Skills
- 0 workflows, 4 sub-skills, 10 standalone
More Blueprints to explore
Gong
G22 Files
Crossbeam
Claude
Salesforce Sales Cloud+2 more
SalesSafety checked
Find, rank, and enrich prospects your partners already sell to with AI
Your warmest prospects are the ones already buying from your partners. Find each one with the right contact and a reason to reach out, so your team stops splitting their time across a cold list.
CrossbeamClaudeSalesforce Sales Cloud+2 moreEngineeringSafety checked
Automated Data Pipeline for Reliable Data Processing and Business Insights
Avoid inconsistent business reports by validating data quality before transformed records reach analytics and reporting systems. Ongoing pipeline monitoring helps teams catch processing problems before they undermine business insights.
SQL databasesCSV/Excel filesREST APIs+10 more
Harikrishnan K.
Data Engineer at Decision Minds