Claude Skill

write-linkedin-post

Write or develop a LinkedIn post. Use ALWAYS for LinkedIn content - writing, drafting, developing ideas into drafts, or editing.

LLM Mart · 0 points · 0 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download techwolf-ai-ai-first-toolkit-plugins_content-studio_skills_write-linkedin-post-2ee7841.zip · 2 KB

techwolf-ai/ai-first-toolkit 129 5 forks MIT Updated 2d ago

Part of techwolf-ai/ai-first-toolkit — 20 skills

Install

skills CLI

npx skills add https://github.com/techwolf-ai/ai-first-toolkit/tree/main/plugins/content-studio/skills/write-linkedin-post

Claude Code

claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install techwolf-ai-ai-first-toolkit@llmmart

Git git clone https://github.com/techwolf-ai/ai-first-toolkit.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole techwolf-ai/ai-first-toolkit collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Write LinkedIn Post

You are helping write a LinkedIn post for the author.

Before Writing (MANDATORY)

You MUST complete these steps before writing ANY content:

Run ./scripts/print-published.sh linkedin-post to read ALL published posts in one call
- This is critical to avoid repeating topics or angles already covered
- Note the core insights and data points already used
- Identify opportunities to reference or build on previous posts
- Pay attention to recent patterns (last 5-10 posts) to avoid repetitive structures, hooks, or phrases
Read guidelines/linkedin.md for style rules
Read references/professional-profile.md for background

If developing an idea-stage post: Check if the idea's core insight or data points overlap with published posts. If so, either:

Find a genuinely different angle
Explicitly build on the previous post ("In my last post I discussed X. Here's the flip side...")
Recommend against developing the idea

Avoid Repetitive Patterns

When reading recent posts, actively note and vary:

Hooks: If recent posts start with similar patterns, try a different structure Sentence patterns: Vary rhythm - don't always use short punchy sentences or always use longer flowing ones Closing lines: Don't repeat formulas Transition phrases: Rotate between "Here's what...", "The pattern...", "This matters because...", etc. Structure: If recent posts all use problem-solution-takeaway, try a different arc

The goal is a consistent voice with varied execution. Each post should feel fresh while still sounding like the author.

Style Requirements

Target word count per guidelines/linkedin.md (typically 150-250 words)
Personal hook first (under 210 characters before "see more")
Specific > abstract
Conversational tone
No hype words ("revolutionary", "game-changing")

Hook Priority

Personal anecdote
Company experience
Surprising outcome
Counterintuitive framing

Process

If given a topic, develop it into a draft
If given an existing idea file (search with ./scripts/search-posts.sh), develop the content
Always check word count against target
Save to content/posts/ with type: linkedin-post, stage: 02-drafts

Validation

After saving the draft, run the word count checker:

scripts/check-word-count.sh <yaml-file>

Adjust the content if the word count is outside the 150-250 target.

Sub-Agent Review

Before presenting the final draft, spawn a sub-agent to review with fresh eyes. The reviewer should:

Check voice consistency against guidelines/linkedin.md
Verify the hook works in the first 210 characters
Flag any overlap with recently published posts
Check for hype words or generic phrasing

Incorporate the reviewer's feedback before finalizing.

Creating New Files

Get timestamp first:

date -u +"%Y%m%d-%H%M%S"  # For slug
date -u +"%Y-%m-%dT%H:%M:%S.000Z"  # For created/lastUpdated

Files (ai-first-toolkit)

scripts

check-word-count.sh 958 B

#!/bin/bash
# Validates LinkedIn post word count is within target range (150-250 words).
# Usage: check-word-count.sh <yaml-file>

FILE="$1"
if [ -z "$FILE" ]; then
  echo "Usage: check-word-count.sh <yaml-file>"
  exit 1
fi

if [ ! -f "$FILE" ]; then
  echo "FAIL: File not found: $FILE"
  exit 1
fi

# Extract content field (everything after "content: |-" until next top-level key or EOF)
CONTENT=$(sed -n '/^content: |-/,/^[a-zA-Z]/{ /^content: |-/d; /^[a-zA-Z]/d; p; }' "$FILE")

if [ -z "$CONTENT" ]; then
  echo "FAIL: No content field found in $FILE"
  exit 1
fi

WORD_COUNT=$(echo "$CONTENT" | wc -w | tr -d ' ')

if [ "$WORD_COUNT" -lt 150 ]; then
  echo "WARN: $WORD_COUNT words (target: 150-250). Too short by $((150 - WORD_COUNT)) words."
  exit 1
elif [ "$WORD_COUNT" -gt 250 ]; then
  echo "WARN: $WORD_COUNT words (target: 150-250). Too long by $((WORD_COUNT - 250)) words."
  exit 1
else
  echo "PASS: $WORD_COUNT words (target: 150-250)"
fi

SKILL.md 3.1 KB

---
name: write-linkedin-post
description: Write or develop a LinkedIn post. Use ALWAYS for LinkedIn content - writing, drafting, developing ideas into drafts, or editing.
---

# Write LinkedIn Post

You are helping write a LinkedIn post for the author.

## Before Writing (MANDATORY)

**You MUST complete these steps before writing ANY content:**

1. Run `./scripts/print-published.sh linkedin-post` to read ALL published posts in one call
   - This is critical to avoid repeating topics or angles already covered
   - Note the core insights and data points already used
   - Identify opportunities to reference or build on previous posts
   - **Pay attention to recent patterns** (last 5-10 posts) to avoid repetitive structures, hooks, or phrases
2. Read `guidelines/linkedin.md` for style rules
3. Read `references/professional-profile.md` for background

**If developing an idea-stage post:** Check if the idea's core insight or data points overlap with published posts. If so, either:
- Find a genuinely different angle
- Explicitly build on the previous post ("In my last post I discussed X. Here's the flip side...")
- Recommend against developing the idea

## Avoid Repetitive Patterns

When reading recent posts, actively note and vary:

**Hooks:** If recent posts start with similar patterns, try a different structure
**Sentence patterns:** Vary rhythm - don't always use short punchy sentences or always use longer flowing ones
**Closing lines:** Don't repeat formulas
**Transition phrases:** Rotate between "Here's what...", "The pattern...", "This matters because...", etc.
**Structure:** If recent posts all use problem-solution-takeaway, try a different arc

The goal is a consistent voice with varied execution. Each post should feel fresh while still sounding like the author.

## Style Requirements

- Target word count per `guidelines/linkedin.md` (typically 150-250 words)
- Personal hook first (under 210 characters before "see more")
- Specific > abstract
- Conversational tone
- No hype words ("revolutionary", "game-changing")

## Hook Priority

1. Personal anecdote
2. Company experience
3. Surprising outcome
4. Counterintuitive framing

## Process

1. If given a topic, develop it into a draft
2. If given an existing idea file (search with `./scripts/search-posts.sh`), develop the content
3. Always check word count against target
4. Save to content/posts/ with type: linkedin-post, stage: 02-drafts

## Validation

After saving the draft, run the word count checker:
```bash
scripts/check-word-count.sh <yaml-file>
```
Adjust the content if the word count is outside the 150-250 target.

## Sub-Agent Review

Before presenting the final draft, spawn a sub-agent to review with fresh eyes. The reviewer should:
- Check voice consistency against `guidelines/linkedin.md`
- Verify the hook works in the first 210 characters
- Flag any overlap with recently published posts
- Check for hype words or generic phrasing

Incorporate the reviewer's feedback before finalizing.

## Creating New Files

Get timestamp first:
```bash
date -u +"%Y%m%d-%H%M%S"  # For slug
date -u +"%Y-%m-%dT%H:%M:%S.000Z"  # For created/lastUpdated
```