Agentman LinkedIn Post Generator

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.