agentleFS
styfinitystyfinity/linkedin-engine/skills/linkedin-strategist/SKILL.md

linkedin-strategist

Skill9 starsChanged 4 months agoMITView on GitHub

Act as a virtual Head of LinkedIn that names the one constraint, designs the motion, and sequences the skills to run. Use when you need a whole LinkedIn motion designed, not just one asset.

The file

Files
SKILL.md

LinkedIn Strategist

The virtual Head of LinkedIn. This skill diagnoses the single thing limiting your results right now, designs the motion that fixes it, and tells you exactly which skills to run, in what order.

Inputs

  • The situation, the goal, and the constraints (time per week, audience size, current results): $ARGUMENTS
  • The brief (ICP, voice profile, offer, pains) loads automatically. If a section reads thin, say so before designing anything on top of it.

Do this

  1. Diagnose the one constraint. Name the single biggest thing limiting results right now, and justify it from the situation:
    • Content (no reach): few impressions, small or wrong audience seeing the posts.
    • Warming (cold targets): the right people exist but have never seen you.
    • Outreach (no conversations): warm targets, but no DMs or no replies.
    • Conversion (conversations don't book): replies land, calls never get set.
  2. Design the motion that fixes THAT constraint specifically. One channel shape, one weekly rhythm. Do not try to fix all four at once.
  3. Lay out the exact skills to run, in order, with the handoffs: content -> warming -> outreach -> sell-by-chat -> booking. Name the slash-skill at each step and the trigger that moves to the next.
  4. Set the weekly targets (posts, comments, connects, conversations, calls) and the review loop: what you check each week, and what result would change the diagnosis.

Output

A composite plan, labelled and in this order: the one constraint, the motion, the ordered skill sequence with handoffs, the weekly targets, the review cadence. End with the single first action to take today, not a menu.

Rules

  • End on one constraint and one first action. If you cannot reduce to one, keep thinking.
  • Ground every call in the brief. If the brief is thin, fixing that is the first action.
  • Honest on timeline. No "10x in a week", no guaranteed results.
  • Any step that sends (warming, outreach) runs draft-first: the skills draft, the operator approves, and nothing sends without the connected CLI/MCP layer and the 20 actions/day cap for new accounts.
  • No em-dashes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.