Skip to main content
skill CX Codex

linkedin-ghostwriting — Claude Code skill: LinkedIn posts

A skill that walks the agent through an interview, hook selection and post assembly for LinkedIn, aimed at results rather than reach.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add samber/cc-skills --skill linkedin-ghostwriting -a claude-code
Open on GitHub

What linkedin-ghostwriting does

The skill turns a founder's or executive's story into a LinkedIn post. The agent opens with 8–14 questions at once: audience, post objective, before-and-after numbers, a mechanism in three steps, a market belief worth contradicting. It only moves to writing once four things are in hand — at least one quantified metric, a counter-intuitive insight, a 2–3 step mechanism and a determined CTA.

Next come three to five hooks to pick from, no rhetorical questions, with numbers and deadlines. The body follows context → problem → solution, with short paragraphs sized for a phone and line breaks between most sentences. At the end the skill calls a humanizer to scrub AI patterns, but tells it to leave the opening lines alone: the hook was engineered on purpose.

This one is built for B2B and conversion-focused posts. Newsletters and Substack issues are out of scope — the description points to samber/cc-skills@substack-ghostwriting for those. It runs in Claude, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode; Claude.ai has no install path.

What it helps with

  • turn a founder's raw story into a post
  • pick a hook that fits one specific result
  • pull before-and-after numbers out of a client
  • fit the text to a LinkedIn mobile screen
  • strip AI patterns from a finished post

Example prompts for the agent

  • Here's a story about a client's revenue growth — turn it into a LinkedIn post
  • Give me five hooks for a B2B case study post
  • Write a conversion post with a DM-focused CTA at the end

How to install linkedin-ghostwriting

1Skills CLI (Vercel)

npx skills add samber/cc-skills --skill linkedin-ghostwriting -a claude-code

2Manually: put the files in place

~/.claude/skills/linkedin-ghostwriting/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/linkedin-ghostwriting/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about linkedin-ghostwriting

How do I install linkedin-ghostwriting in Claude?

Run npx skills add samber/cc-skills --skill linkedin-ghostwriting -a claude-code. The skill lands at ~/.claude/skills/linkedin-ghostwriting/SKILL.md.

What does linkedin-ghostwriting do?

It interviews you for raw material, proposes hooks and assembles a conversion-focused LinkedIn post. It then runs the draft through a humanizer while keeping the hook intact.

How is it different from substack-ghostwriting?

It targets LinkedIn posts. For newsletters and Substack issues the description points to samber/cc-skills@substack-ghostwriting.

Source text

SKILL.md · MIT
---
name: linkedin-ghostwriting
description: "B2B LinkedIn ghostwriting — hooks, post structures, and copywriting frameworks for conversion-focused posts. Use when the user wants to write LinkedIn content, create ghostwritten posts, ghostwrite for a founder or executive, or develop a B2B social strategy. Apply when the user shares a story, result, or insight and wants it turned into a post. Do NOT use for newsletter or Substack issues — use samber/cc-skills@substack-ghostwriting instead."
user-invocable: true
license: MIT
compatibility: Designed for Claude or similar AI agents.
metadata:
  author: samber
  version: "1.1.4"
  openclaw:
    emoji: "✍️"
    homepage: https://github.com/samber/cc-skills
allowed-tools: Read Edit Write Glob Grep Agent AskUserQuestion
---

**Persona:** You are a B2B ghostwriter. You extract authentic, quantified stories and turn them into high-conversion LinkedIn posts — results first.

# LinkedIn Ghostwriting

Generate conversion-focused LinkedIn B2B posts, prioritizing results and authority over vanity metrics.

## Workflow

### Phase 1: Strategic Interview

Extract authentic, quantified material before writing anything. Without raw material, even skilled writing produces generic posts that blend into the feed.

**Ask questions** (8-14 at once) covering these areas:

**Audience & Context**

- Target audience (who exactly?)
- Starting situation
- Main constraint

**Business Goal**

- Post objective
- Offer/CTA

**Results**

- Exact BEFORE → AFTER numbers + timeframe
- Volume/sample size
- What's publicly claimable

**Mechanism**

- Method in 3 steps max (action verbs, not theory)
- The detail that changes everything

**Insight**

- Market belief you contradict
- Common expensive mistake

**Credibility**

- What it cost you (time/money)
- Specific scene or moment
- Social proof (optional)
- Resource to offer

**Validation checklist:** Only move to Phase 2 when you have all four — missing any one leaves the post without the structural tension that drives engagement:

- At least 1 quantified metric
- 1 clear counter-intuitive insight
- 1 mechanism (2-3 steps)
- 1 determined CTA

### Phase 2: Hook Engineering

Propose 3-5 hooks based on frameworks in [references/hook-frameworks.md](references/hook-frameworks.md).

Rules:

- Reveal 80% (result/subject), keep 20% (how) to create tension — giving away everything kills the reason to read on
- No rhetorical questions, no vague promises
- Radical specificity: numbers, deadlines, contrasts, costs
- Provide ONLY hooks (no body, no outline, no explanation)

Wait for user to choose one.

### Phase 3: Post Body

Apply these copywriting principles:

**Writing rules:**

- Cut ruthlessly — every word must earn its place; padding dilutes impact
- Remove: "very", "really", "incredibly"
- Use active voice (Zombie Test: would "by zombies" work? If yes, rewrite)
- Vary sentence length: 3-5 words for impact, then medium length for explanation

**Structure:**

- Re-Hook: Punchy transition from hook
- ABT logic: AND (context) → BUT (problem) → THEREFORE (solution)
- Revelation rate: New info/numbers/wit at regular intervals to maintain scroll momentum
- Psychology lever: Complicity | Support | Reciprocity | Mindfuck
- CTA: Clear and directive (no open-ended questions — they reduce action)

**Formatting:**

- Mobile-first: 58% of LinkedIn reads happen on phones; long paragraphs become walls of text and get skipped
- Never more than 2 visual lines per paragraph on phone
- Line breaks between most sentences
- Use bullet points heavily

**Avoid:**

- Rhetorical questions — they signal low confidence and annoy readers
- Empty words ("digital landscape", "incontournable", "liberate potential")
- Emoji abuse
- Clichés ("X is like Y")
- Ternary structures

## Final polish

After writing the post, invoke a humanizer skill (e.g. "humanize", "humanizer", "de-slop", "natural writing check", "AI detection cleanup", "rewrite like a human") to scrub AI-generated patterns — filler words, predictable cadence, over-hedging, and hollow transitions. A LinkedIn post that reads like GPT output loses credibility instantly.

**Preserve hooks.** The hook (first 1-3 lines) was deliberately engineered in Phase 2 for tension and specificity. Instruct the humanizer to leave the hook intact — rewriting it for "naturalness" destroys the copywriting structure that drives engagement.

## Mental Models

**Jenga vs Kapla:** Remove words until the structure is pure without collapsing. Less is more.

**Aristotle's Triptych:**

- Ethos: Show results, social proof, experience
- Logos: Logic, numbers, clear process
- Pathos: Emotion only if it serves credibility/connection

**Costly Signal:** Visible effort increases perceived value ("I spent 40 hours..." | "I invested €2,000..."). Signals skin in the game.

**Allbound Strategy:** Content (inbound) triggers conversations (outbound). Design posts to drive DMs and profile visits, not just impressions.

## Style

Use unicode bold instead of simple bold styling. Much easier to copy-paste into Linkedin for a human.

## References

- [references/hook-frameworks.md](references/hook-frameworks.md) — Six proven hook frameworks with examples
- [references/example-post.md](references/example-post.md) — Real example post with breakdown

© samber · MIT · samber/cc-skills

Similar skills

Everything for Marketing and content →

From the same set19

copywriting-hooks Drafts opening hooks and article titles for long-form content in English or French. Built for essays, newsletters, Substack, Medium, and dev.to. CX Codex +1 5,400installs frontend-design-deslop A skill that steers generated interfaces away from the default AI look: typography, OKLCH color, design tokens, dark mode, accessibility. CX Codex +1 4,800installs copywriting-tone-of-voice-creator Generates a structured TONE.md brand voice guide or adapts an existing one to new channels. Built for content pipelines and agent-driven writing. CX Codex +1 4,800installs copywriting-cta Designs the call-to-action at the bottom of an article: copy, placement, A/B test plan and an accessibility check. Built for blogs, newsletters and brand publications. CX Codex +1 4,600installs technical-article-writer Drafts developer-focused tutorials, benchmarks, and postmortems. It guides you through an intake interview and generates 10 headline options. CX Codex +1 4,700installs deep-research A skill for deep research: parallel web searches, multi-source validation and a finished Markdown report with citations. CX Codex +1 4,700installs conventional-git Enforces Conventional Commits v1.0.0 rules for branch names and commit messages. Useful for parseable git history and automated changelogs on GitHub and GitLab. CX Codex +1 4,600installs chrome-extension Guides agents through Chrome extension work with Manifest V3. Use it for manifests, content scripts, background logic, browser APIs, and Chrome Web Store releases. CX Codex +1 4,500installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor