plan-a-career-change
Skill0 starsChanged 4 days agoMITView on GitHub
Plan a career change step by step at any age (in your 20s, 30s, 40s, 50s or later) without quitting first or retraining blindly. Use for "how do I change careers", "is it too late to change careers at 45", "career change with no experience" or "switch careers without a pay cut".
In this repository17 other files it gives its agents.
- after-a-layoffSkill
- answer-application-questionsSkill
- choose-a-path-as-a-studentSkill
- find-career-directionsSkill
- follow-up-on-applicationsSkill
- future-proof-against-aiSkill
- go-public-after-a-layoffSkill
- informational-interviewsSkill
- negotiate-a-job-offerSkill
- prepare-for-interviewSkill
- return-to-work-after-a-breakSkill
- share-your-work-in-publicSkill
- start-a-new-jobSkill
- tailor-cv-to-jobSkill
- test-a-careerSkill
- update-linkedin-for-a-career-changeSkill
- write-cover-letterSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
Keep, drop or adjust: after each test. Write down what they avoided.
- Distinctive: line 34
Don't recommend quitting before there is evidence and runway.
- Distinctive: line 35
Never promise an outcome or a salary.
≈ “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.
Files
Plan a career change
A career change is a series of small tests, not one decision made in advance. The plan below keeps income steady while evidence builds.
The plan
- Write down the constraints first: months of runway (accessible money divided by essential monthly spending), income floor, hours available each week, anything that can't move.
- Pick two or three directions that reuse most of what they already do well. Change one variable at a time: the craft, the domain or the setting. (See the
find-career-directionsskill if they have none yet.) - Test each within a fortnight with a small real piece of the work: a project with a real user, a paid side task, a shadow day, two conversations with practitioners. (See
test-a-career.) - Keep, drop or adjust after each test. Write down what they avoided; it is usually the most honest answer.
- Build one piece of proof in the direction that holds: a finished project someone used beats a list of courses.
- Choose a route in: a bridge role that uses their old experience in the new field, an internal move, freelance work, or an entry role with a clear step up.
- Retrain only after a direction has survived two or three tests, and only for the specific gap employers name.
- Rewrite the CV and story for the new field (see
tailor-cv-to-jobandprepare-for-interview).
Give the plan as dated steps for the next four weeks, not a five-year roadmap.
"Is it too late?"
Answer with evidence, not reassurance. If the OffLadder tools are connected, check_career_change_facts returns exact quotes from the U.S. Bureau of Labor Statistics on how many jobs people hold and how long they stay, with links. Then point out that experience is a head start: the move that works later in a career usually keeps the domain or the people and changes the craft, or the reverse.
If the OffLadder tools are connected
find_career_guidecovers career changes at 30, 35, 40 and 50, without going back to school, with no experience, without a pay cut, and after a layoff.read_career_guidereturns any guide in full.find_career_experimentgives a first test for a named field.
Rules
- Don't recommend quitting before there is evidence and runway.
- Never promise an outcome or a salary.
- Financial, legal or immigration questions go to a qualified adviser.
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
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.

