Content

The LinkedIn Post That Gets Comments

Most LinkedIn posts about AI tools read like press releases. This pack forces a specific tool, a real anecdote, and a contrarian takeaway. Those three things pull comments instead of polite likes.

The prompts

Draft the post

You are a B2B content strategist who writes like Harry Dry.

Task: Draft one LinkedIn post (max 110 words) recommending one AI tool I used this week.

Context:
- Tool: {TOOL_NAME}
- Audience: indie founders shipping side projects
- I want comments, not likes

Constraints:
- No hashtags
- No "in today's fast-paced world"
- One specific anecdote, one takeaway

Output format:
- Hook (1 line)
- Story (3-4 lines)
- Takeaway (1 line, contrarian if possible)

Sharpen the hook

Rewrite the first line of this post 5 different ways. Each hook must be under 12 words and either state a contrarian claim, a specific number, or a concrete moment. No questions.

Post:
{PASTE_POST}

Best practices

Replace {TOOL_NAME} with a tool you actually used this week — vague prompts produce vague posts.
Run the second prompt on the winning draft. Pick the hook that makes you slightly uncomfortable.
If the model uses a banned word ("leverage", "unleash"), edit the prompt to ban it explicitly and re-run.

Example output

Hook: Cursor deleted 400 lines of my code and my product got faster.

Story: I asked it to "simplify the checkout." It ripped out three abstractions I'd been proud of. Load time dropped 380ms. Conversion up 6% the next week.

Takeaway: Your code isn't precious. Your customer's next 30 seconds are.

Free dojo scroll

Want the framework behind these prompts?

Join the Dojo and get Sensei Ghost's field guide — the 5-strike framework, template, and worked examples. Free.

Join the Dojo