agentleFS
wonderwhizwonderwhiz/offladder-claude/skills/share-your-work-in-public/SKILL.md

share-your-work-in-public

Skill0 starsChanged 4 days agoMITView on GitHub

Turn a small experiment, practice project or conversation into a short, honest LinkedIn or X post, comment or headline that shows people in a new field what you're already doing. Use when someone changing careers wants to build in public, asks what to post, wants a better LinkedIn headline, or wants to comment on posts by people in a field.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask what they tried, what happened and what surprised them.

    line 12
  2. Very specific:

    If they haven't done anything yet, suggest a small test first (see test-a-career) rather than a post about intentions.

    line 19
  3. Distinctive:

    Never add facts, numbers, employers or titles.

    line 50
  4. Distinctive:

    Never post for them.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Sharing your work in public

For a career changer, a post about a small piece of real work in the new field says more than "open to new opportunities". People hiring in a field notice who is already doing the work, and each post becomes portfolio material.

Start from what they actually did

Ask what they tried, what happened and what surprised them. Good material:

  • a 15-minute test of the work and the one thing it showed
  • a practice project, with the decision they found hardest
  • what someone in the job told them (with permission)
  • a first attempt and what they changed

If they haven't done anything yet, suggest a small test first (see test-a-career) rather than a post about intentions.

Shape of the post

  1. What they tried, in one or two plain sentences, with one specific detail: a number, a name, a moment.
  2. What they noticed.
  3. One question to people who do this work. Replies are where introductions start.

40 to 120 words on LinkedIn; under 280 characters on X (a link counts as 23). Label practice work as practice. Never imply clients or results they didn't have.

Other moves

  • Headline: where they're heading and what they bring, never a title they haven't held. Recruiter search on LinkedIn matches on meaning now, so plain words work.
  • Comment: two to four sentences under a post by someone in the field, adding something only they could say. No praise-only comments and no self-promotion. On X, replies inside a niche are the main way new accounts get seen.
  • Message: three sentences to one person: why them, one specific question, an easy way to say no.

Cadence

Two or three posts a week at most, plus a thoughtful comment most days. Staying on one field helps both feeds find the right readers. After three or four posts, help them turn the series into a short case study.

Voice check before they post

Flag, and suggest a fix for: long dashes, emoji bullets, more than three hashtags, stock openers ("excited to share", "here's what I learned"), words like journey, leverage, game-changer, and a post with nothing only they could know. Readers and LinkedIn's "Seems like AI slop" flag both punish these.

If the OffLadder tools are connected

find_career_experiment gives a small test to post about. find_career_guide covers building in public, using X to find a job, getting noticed without posting and posts that sound like AI. OffLadder's share box after an experiment, and its Being seen page (offladder.com/go-public), draft posts from the person's own notes, with an optional short credit line, and open LinkedIn or X for them to post themselves.

Rules

  • Their words first. Edit, don't ghostwrite.
  • Never add facts, numbers, employers or titles.
  • Never post for them.
  • Under 18: keep it to sharing with people they know; don't push public posting.

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.