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
  • 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.

Back to skills

Linkedin Post

ASecurity

Use when the user wants to write a LinkedIn post from an idea, a link, a project win, or a lesson. Produces three variants in the user's voice with hooks that don't sound like every other post.

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agents

Works with

cli

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rickbauer327-cell/solo-stack-starter --skill linkedin-post --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Linkedin Post?

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

Security grade badge for Linkedin Post
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rickbauer327-cell-linkedin-post/badge)](https://www.skillsdirectory.com/skills/rickbauer327-cell-linkedin-post)

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

Download Zip
Files
SKILL.md
---
name: linkedin-post
description: Use when the user wants to write a LinkedIn post from an idea, a link, a project win, or a lesson. Produces three variants in the user's voice with hooks that don't sound like every other post.
---

# LinkedIn Post

Write posts that sound like the user, not like LinkedIn. Three variants so they can pick, not edit.

## Step 1 — Load context
Read `.solo/business.md` for tone, services, and who the audience is (ideal clients — posts should be useful to *them*, not to peers).

## Step 2 — Get the seed
One of: an idea, a link/article (fetch and read it), a project outcome, a mistake and lesson, a question the user keeps getting asked. If the seed is vague ("post about AI"), ask for the one specific thing they believe that others might not.

## Step 3 — Write three variants
Save to `content/linkedin/<YYYY-MM-DD>-<slug>.md`. Each variant:
- **Hook** (first line, before "see more"): a specific claim, number, or moment. Under 12 words. No questions like "Ever wondered…?", no "Unpopular opinion:", no "I've been thinking a lot about…".
- **Body:** 80–180 words. Short paragraphs (1–2 lines). One idea. Concrete example from the user's work if the seed allows.
- **Close:** either a plain takeaway or a real question the user wants answered. No "Agree?" No "Thoughts?"
- **No hashtags** unless business.md says to use them. Max 3 if so.

Variant angles:
- **A — Story:** what happened, what it taught. Past tense, first person.
- **B — Contrarian/insight:** the thing most people get wrong, and the better way.
- **C — Practical:** a numbered mini-how-to (3–5 steps) the audience can use today.

After the three, add a `## Notes` line: which variant you'd post and why, in one sentence.

## Tone rules
- Match business.md tone. If it says "no buzzwords", remove: game-changer, leverage, unlock, journey, thrilled, humbled, delve.
- Write like a person talking to one reader.
- No emojis unless the tone section says so.
- No fake vulnerability, no "I failed 100 times" unless it's true and specific.

## Do not
- Do not write engagement-bait (polls, "comment YES", "repost if you agree").
- Do not exceed 200 words per variant.
- Do not fabricate results or client stories.

Attribution

rickbauer327-cellrickbauer327-cell
View sourceMore from rickbauer327-cell →
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. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 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', ...

686011 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.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 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 →