career-mapping
Skill2 starsChanged 7 days agoMITView on GitHub
Map experience evidence to adjacent, cross-industry and hybrid career paths, with sourced market checks and explicit blockers. Use for career exploration or pivots, not vacancy claims or resume writing.帮助用户发现新的工作机会。
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- application-assistantSkill
- career-discoverySkill
- document-exportSkill
- interview-coachSkill
- job-analysisSkill
- job-searchSkill
- learning-plannerSkill
- resume-builderSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Very specific: line 12
Read the complete experience index and relevant constraints, then inspect details for promising evidence.
- Distinctive: line 15
Read current public vacancies or official occupation sources as needed.
≈ “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
Career mapping
This is the default bridge from experience discovery to preference-led job search: identify transferable abilities the user may overlook and explain their value in viable role families. Check actual gates and entry routes; age, prior title or one rejection does not set a career ceiling.
On first use, default to python -m oriward onboarding status and the full experience index; targets may remain open. Reuse saved choices, ask only what changes the mapping, and save topic/next action with onboarding topic. Channel preference is optional and does not enable a connector.
- Read the complete experience index and relevant constraints, then inspect details for promising evidence. Use
$career-discoveryto recover overlooked actions when helpful; do not require an exhaustive interview. Reuse stated preferences and ask only for a missing constraint that changes the mapping. - Map
experience ID -> action -> transferable ability -> possible deliverable/direction; distinguish interest and inference without forcing occupational categories. - For options, show supporting IDs, counterevidence, gates, feasible entry proof, risks and search terms.
- Read current public vacancies or official occupation sources as needed; retain exact URLs and checked dates. Without market evidence, keep the direction a hypothesis. Never invent openings, demand, salaries or offer probabilities.
- Save directions using references/career-contract.md and
career add; inspectcareer list. Hand preferences, direction IDs, evidence, constraints and terms to$job-search; unselected directions remain hypotheses.
Career Twin Core contract
- Each direction becomes a
career_hypothesis(subject:career:<slug>,predicate:direction_hypothesis,source_type:model_inference), withsupportsandcontradictslinks. - Cite the assertion ID for any confirmed hard-constraint conflict. A user-chosen pursuit uses
goal addwithowner:user; agent exploration usesowner:agentand must not drive priority ordering. - Record recommended direction/validation choices and later reassessment through the decision contract. Shared privacy and external-action rules remain in
AGENTS.md.
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.

