job-title-discovery
Skill139 starsChanged 4 months agoMITView on GitHub
Research credible related job titles from a person's career context and job-board evidence, then return reviewable suggestions without changing saved preferences. Use when someone wants to explore possible target roles; use job-search for actual openings.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-workflowsSkill
- account-setupSkill
- answer-memorySkill
- application-setupSkill
- job-applySkill
- job-preferencesSkill
- job-searchSkill
- job-workspaceSkill
- saved-jobsSkill
The file
Files
Job Title Discovery
Use answer-memory to resolve the plugin root and inspect only relevant canonical profile and resume facts. Read current search preferences with node "<plugin-root>/apps/companion/command.mjs" store profile-inspect; treat the current resume title as history, not a required future target. Include the owner's role interests, seed titles, seniority limits, and exclusions when supplied. Ask only for a missing constraint that materially changes the research.
Read discovery workflow before browser research. Use the host's visible browser to inspect LinkedIn job-board results where available. Never invent postings or promote generic brainstorming as observed evidence. If the source is logged out, blocked, unavailable, or empty, report that exact state and a safe next step.
Return one JSON result packet as specified in result format. Group evidence-backed suggestions into core, adjacent, and stretch roles, each with a reason and inspectable source. The examples Principal ML Engineer, Senior/Staff/Principal Forward Deployed Engineer, and Director of AI are possible outcomes only when the person's interests and observed evidence support them; they are not defaults.
Discovery is read-only. Do not write private Store files, modify resume facts, or call preferences-set. Companion must let the owner review an exact title set before its canonical, revision-checked save. If the owner asks to save approved titles in chat, hand that explicit set to job-preferences; then job-search may use the saved targetTitles. A discovery packet alone never authorizes a preference write.
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.

