job-search-brief
Skill12 starsChanged 4 days agoMITView on GitHub
Turn a CV, experience summary and stated preferences into an evidence-based job-search brief. Use when the user wants to choose target roles, focus a job hunt or revise search criteria; it does not perform a vacancy search.
In this repository5 other files it gives its agents.
- company-briefSkill
- fit-reviewSkill
- job-researchSkill
- linkedin-search-planSkill
- shortlist-reviewSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Search keywords and exclusions that follow from those choices.
≈ “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
Job Search Brief
Build the brief in the conversation. Read an attached CV with the host's available attachment tools; when the user has no CV, use their experience summary. Do not require a document merely to start planning. Ask only for missing information that materially changes the search, together where practical.
Separate three things: facts the user supplied, role suggestions derived from that evidence, and unresolved preferences. Preserve the user's chosen direction even when proposing adjacent roles. Choose role level from demonstrated scope, responsibilities and relevant experience rather than a rigid years-to-title ladder. Never infer work authorization, nationality, protected characteristics or a salary floor from the CV.
Return a compact brief containing:
- Candidate strengths supported by CV lines or the user's statements.
- Primary and adjacent target titles with the evidence for each; label untested title suggestions.
- Stated geography, remote preferences, work-authorization or sponsorship constraints, salary floor/currency/period if supplied, and deal-breakers.
- Search keywords and exclusions that follow from those choices.
- Unknowns that would change the search, without presenting them as failed requirements.
Do not claim that a title has abundant current vacancies unless a live search established that. Do not invent employers, achievements, years of experience or target companies. If the user says to proceed without more questions, use labeled assumptions for ordinary search choices and leave sensitive/legal eligibility unknown.
If Scout is connected, translate the brief into two minimal objects. Search parameters are role titles, locations, workplace, recency and result/spending caps. Local ranking uses stated skills, target titles and logistics; newer contracts accept explicit experience_years, target_seniority, remote_from_country and domains. Scout v0.3 additionally accepts is_student, degree_completed, graduation_year, fields_of_study, placement_year_available, completed_study_years and grade_classification. Distinguish actual experience from desired role level and search location from the country the candidate will work remotely from. Leave unstated facts unset and inspect discovered schemas before using newer fields. Do not put CV text, names, email, phone, past employers or credentials into an Apify search request. No separate model API key is needed.
For student/intern searches, pass enrollment, degree completion, graduation year and subject only when the CV or user statements establish them. A future expected graduation year does not prove how many study years are completed, permit a placement year, establish a grade classification or rule out an earlier degree. Leave those facts unknown unless explicitly supported. Academic projects and competitions demonstrate skills and scope; they are not commercial employment at a sponsor or partner organization. A junior target may include internships when the stated target titles include them.
Show the brief and continue with the user's requested next action in the same chat. This skill does not authorize a paid search, application, message or background monitoring beyond the user's request. Never ask for an API token in conversation; initial secrets belong in the host's protected configuration.
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.

