agentleFS
wonderwhizwonderwhiz/offladder-claude/skills/test-a-career/SKILL.md

test-a-career

Skill0 starsChanged 4 days agoMITView on GitHub

Design a small real-world experiment to test a career, job or field before committing to it. Use when someone wants to try a career before quitting, asks "how do I know if I'd like X", or is weighing a switch they can't afford to get wrong.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Name the direction in their words: If they have two or three in mind, test the one they are most curious about first and plan a second for …

    line 12
  2. Distinctive:

    Decide what to notice: Before they start, ask them to write down which part they expect to enjoy.

    line 16
  3. Distinctive:

    Never present a direction as a match or a verdict.

    line 27
  4. Distinctive:

    Don't suggest quitting, paying for a course or retraining before a direction has survived two or three tests.

    line 29
  5. Distinctive:

    Keep the output to one experiment they can start this week, written as numbered steps.

    line 30

≈ “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

Test a career before committing

The idea behind OffLadder: you learn whether you fit a kind of work by doing a small, real piece of it, not by describing yourself or reading about it. A test should take an evening to a weekend, fit around a current job, and produce something another person can react to.

How to run it

  1. Name the direction in their words. If they have two or three in mind, test the one they are most curious about first and plan a second for comparison.
  2. Find the smallest real unit of the work. Every job has one: one chart for an analyst, one redrawn screen for a UX designer, one lesson for a teacher, one afternoon on site for a trade. Ask what people in that work actually do on a normal Tuesday.
  3. Shrink it to one task they can finish this week, with a time box (two to three hours is usually enough) and a clear output.
  4. Add a reaction from a practitioner. Suggest they show the result to one person who does the work and ask what they would fix. That reaction is evidence their own opinion can't give.
  5. Decide what to notice. Before they start, ask them to write down which part they expect to enjoy. Afterwards: which twenty minutes would they repeat tomorrow? What did they put off?
  6. Plan the second run. Novelty makes almost anything feel good once. The same kind of task twice, or a harder version, is the real test.

If the OffLadder tools are connected

  • find_career_experiment with the career they named returns a written experiment from OffLadder's library, and a link to carry on with OffLadder's coach.
  • explore_career_directions suggests neighbouring directions if the first one doesn't hold.
  • find_career_guide with "test a career before switching" returns the full method with sources.

Rules

  • Never present a direction as a match or a verdict. It is a hypothesis to test.
  • For regulated work they can't practise yet (medicine, law, nursing, piloting), test the safe parts: shadowing, conversations with practitioners, and a taste of the study it requires.
  • Don't suggest quitting, paying for a course or retraining before a direction has survived two or three tests.
  • Keep the output to one experiment they can start this week, written as numbered steps.

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.