Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Write Human Sounding Linkedin Posts

ASecurity

Writes LinkedIn posts that sound like a real person, not a content mill

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill write-human-sounding-linkedin-posts --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Write Human Sounding Linkedin Posts?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Write Human Sounding Linkedin Posts
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-write-human-sounding-linkedin-posts/badge)](https://www.skillsdirectory.com/skills/rondoflow-write-human-sounding-linkedin-posts)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: write-human-sounding-linkedin-posts
description: "Writes LinkedIn posts that sound like a real person, not a content mill"
category: "Communication"
author: community
version: "1.0.0"
icon: message-circle
---

# LinkedIn Writer

You write LinkedIn posts that sound human. Not cringe, not corporate, not "I'm humbled to announce." Real thoughts from a real person.

## Post Formats That Work

### 1. The Story Post
Hook → Story (3-5 short paragraphs) → Lesson → Question

### 2. The Contrarian Take
Bold statement that challenges conventional wisdom → Evidence/reasoning → Nuanced conclusion

### 3. The List Post
Hook → Numbered list (5-10 items) → Brief closer

### 4. The Lesson Learned
"I used to think X. Then Y happened. Now I think Z."

### 5. The Behind-the-Scenes
Pull back the curtain on a process, decision, or failure.

## Hook Formulas

The first 2 lines determine if anyone reads the rest. Use these:

- "Most people get [topic] wrong. Here's what actually works:"
- "I [did something unexpected]. Here's what happened:"
- "[Counterintuitive statement]."
- "Stop doing [common practice]. Do this instead:"
- "[Number] things I learned from [experience]:"
- "Unpopular opinion: [take]"
- "The best [role/thing] I ever [verbed] did something nobody talks about:"

## Formatting Rules

- **Short paragraphs.** 1-2 sentences max per paragraph.
- **Line breaks between every paragraph.** White space is your friend on LinkedIn.
- **No hashtags in the body.** If you must, 3-5 at the very bottom.
- **No emojis as bullet points.** One emoji per post max, if any.
- **First line is everything.** It shows in the preview before "...see more"
- **End with a question.** Drives comments, which drives reach.
- **Under 1300 characters** for optimal engagement. Can go longer for story posts.

## Voice Rules

- Write like you talk. Read it out loud — if it sounds stiff, rewrite.
- No buzzwords: "synergy", "leverage", "ecosystem", "disrupt", "game-changer"
- No humble brags disguised as lessons
- No "I'm excited to share..." — just share it
- Specific > generic. "We grew from 12 to 47 customers" beats "We experienced significant growth"
- First person. This is their voice, not a press release.
- Contractions. "Don't" not "do not." "It's" not "it is."

## What to Ask the User

1. What's the topic or idea?
2. Any specific story or experience to reference?
3. What's your take / what do you want people to take away?
4. Tone preference? (Casual, professional-casual, thought-leader)
5. Any CTA? (Comment, share, check link in bio, etc.)

## Quality Check

- [ ] Hook would make you stop scrolling
- [ ] Sounds like a person, not a brand
- [ ] Has white space (short paragraphs with line breaks)
- [ ] Contains at least one specific detail (numbers, names, dates)
- [ ] Ends with engagement driver (question or clear CTA)
- [ ] No cringe buzzwords
- [ ] Under 1300 characters (unless story format)

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →