Agentman LinkedIn Post Generator

Drafts and rewrites LinkedIn posts for Agentman in its accessible-expert, challenger voice.

Use this skill freeTry it in Claude

Free plan: up to 10 private skills and 3 members, no credit card.

What this skill does

Generate highly converting, on-brand LinkedIn posts for Agentman.ai using the Agentman brand voice (accessible expert + challenger).

  • linkedin
  • copywriting
  • growth
  • agentman
  • brand-voice
  • thought-leadership

SKILL.md

Use this skill when

  • Creating a new LinkedIn post for Agentman (company page or founder voice).
  • Turning a raw idea, lesson, metric, or launch note into a high-performing post.
  • Rewriting an existing draft to improve hook, clarity, structure, and conversion.

Always follow the Agentman voice

  • Be an accessible expert: explain like a sharp operator, not a lecturer.
  • Be a battle-tested authority: ground claims in production experience, numbers, and specific examples.
  • Be a practical visionary: focus on what works now.
  • Be honest about struggle: include what failed and what changed.
  • Carry a challenger edge: respectfully call out bad defaults (demo-ware, black boxes, vibe coding-only).

Hard rules:

  • Avoid hype, fake scarcity, vague superlatives.
  • Prefer concrete proof (timeframes, counts, deltas, before/after).
  • Use short paragraphs and lots of white space.
  • End with a clear, low-friction CTA.

Inputs to collect (lightweight)

If the user didn’t specify, infer reasonable defaults and proceed.

  1. Post goal: awareness / consideration / decision.
  2. Topic: what the post is about in one sentence.
  3. Audience: who it’s for (e.g., CX leaders, ops, founders, RevOps, devs).
  4. Proof: at least one of:
    • a metric (%, $, time saved, volume)
    • a production lesson ("24 months in prod taught us…")
    • a concrete example (workflow, integration, constraint)
  5. Offer/CTA: what to do next (comment keyword, ask a question, book a demo, grab a template, see a doc).
  6. Angle (choose one): contrarian take / tactical playbook / story + lesson / teardown / launch.
  7. Length: short (120–180 words), standard (250–450), long (500–700).

Output requirements

Produce 3 variations in one response:

  • V1: Contrarian Challenger (opinion + proof)
  • V2: Tactical Playbook (framework + steps)
  • V3: Story With Battle Scars (what broke + what fixed it)

For each variation, include:

  • A hook (1–2 lines) optimized for scroll-stopping.
  • A body with heavy white space (1–3 lines per paragraph).
  • A credibility spine: time-in-production, number of deployments, failure mode, or metric.
  • A single CTA (one action).
  • Optional: 1–3 hashtags max, only if they’re genuinely relevant.

Also produce:

  • One top comment to pin (adds extra proof or a resource link placeholder).
  • Two reply comments for common reactions (skeptic + curious).

Conversion-first structure library

Pick one structure per version (do not mix too many).

A) Problem → Wall → Insight → Framework → CTA

  • Describe the familiar pain.
  • Name the wall that shows up in production.
  • Share the insight (what changed).
  • Give a mini-framework.
  • Invite one next step.

B) Myth → Reality → Proof → How-to → CTA

  • Call out the myth.
  • Replace with a specific reality.
  • Drop proof.
  • Give a “do this next” list.

C) Teardown (Why X fails) → Fix → Proof → CTA

  • List 3 failure modes.
  • Provide the fix (structured scripting, control flow, guardrails, observability).
  • Show evidence.

Hook generator (choose 5, use the best 1)

Generate 5 hook options, then select the strongest for each version.

Hook patterns (Agentman-style):

  • "Vibe coding gets you 80%. Then production humbles you."
  • "Most AI agents fail for one boring reason: ______."
  • "After 24 months in production, we stopped doing ______."
  • "If your agent needs 30 prompts to behave, it’s not an agent."
  • "Salesforce just announced ______. We shipped it 2 years ago. Here’s what we learned."
  • "The uncomfortable truth about MCP servers: ______."
  • "A reliable agent looks less like a prompt and more like a script."
  • "Here’s the fastest way to cut support costs without hiring."

CTA generator (choose 1 per version)

Keep CTAs low pressure and specific.

  • "Comment ‘SCRIPT’ and I’ll share the checklist."
  • "Want the template? Reply ‘TEMPLATE’ and I’ll send it."
  • "If you’re debugging agent reliability, tell me what’s breaking—happy to point you to a fix."
  • "Want to see an example workflow? I’ll drop a sanitized one in the comments."
  • "Curious if this fits your stack? Tell me your tools (Shopify/HubSpot/Salesforce/etc.)."

Language guardrails

  • Prefer: "agents", "production", "structured scripting", "plain English", "deploy in minutes".
  • Avoid: "revolutionary", "game-changing", "unprecedented", "don’t miss out".
  • If technical terms appear (RAG, MCP), explain in plain language the first time.

Quality checklist before finalizing

  • Does the hook create tension or curiosity in <2 lines?
  • Can the post be skimmed in 10 seconds and still make sense?
  • Is there at least one proof point that a skeptic can’t ignore?
  • Is the takeaway actionable (a framework, steps, or a clear lesson)?
  • Is the CTA one action, low friction, non-pushy?

Default assumptions (if missing info)

  • Goal: awareness.
  • Audience: ops + CX leaders at scaling SMBs.
  • Proof: "24 months in production" + one realistic metric placeholder.
  • CTA: ask a question at the end to drive comments.

A skill is a written procedure, not a prompt. Add it to your library and it is yours to edit in plain language.

Nearby skills

Others that solve nearby problems

  • LinkedIn Post Generator

    Writes LinkedIn thought-leadership posts in the Agentman brand voice using set post frameworks.

  • Agentman Social Media

    Guides Agentman social content across LinkedIn, X, Instagram and Facebook, with LinkedIn as the main channel.

  • Agentman Image Generator

    Generates on-brand diagrams, carousels, covers and thumbnails guided by the Agentman brand voice.

In your Agentman library

A skill you keep, not a prompt you paste

  • Versioned, not pasted

    Edit a skill once and every agent using it follows the new version.

  • Shared with your team

    One library with per-skill access control and a record of who did what.

  • One connection

    A single MCP link works across Claude, ChatGPT, Cursor and Agentman agents.

How Agent Skills work
Questions

Using a skill

What is a skill?

A skill is a written procedure an AI assistant reads before it does a task: the steps, the judgement calls, the standards and what "done" looks like. It lives in a SKILL.md file, sometimes with reference files beside it. A prompt is typed again each time; a skill is versioned and runs the same way for everyone who uses it.

How do I use this skill in Claude, ChatGPT or Agentman?

Create a free Agentman account and add the skill to your library. One MCP connection then makes your library available in Claude, ChatGPT, Cursor and Agentman agents, so you set it up once. To see it work before you sign up, use "Try it in Claude" on this page, which opens a chat that reads the public SKILL.md.

Can I edit the skill after I add it?

Yes. Cloning a skill puts a copy in your workspace that is yours to edit in plain language. Skills are versioned: edit one once and every agent using it follows the new version. The free plan covers up to 10 private skills and 3 members, no credit card.

Make it yours

Add Agentman LinkedIn Post Generator to your library, edit it to match how your team works, and use it from Claude, ChatGPT or an Agentman agent. The free plan covers up to 10 private skills and 3 members, no credit card.

Or try it in ChatGPT first.

Use this skill free