job-seeker-helper
Skill0 starsChanged 7 months agoMITView on GitHub
End-to-end job search application workflow for resumes, CVs, cover letters, recruiter messages, interview prep, follow-ups, and job trackers.
In this repository4 other files it gives its agents.
- cover-letterSkill
- interview-coachSkill
- job-application-trackerSkill
- resume-optimizerSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 9 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill when the user wants help applying to a job, improving a resume/CV for a specific job description, writing a cover letter, …
- Very specific: line 13
If evidence is missing, use a clearly labeled placeholder such as [add metric if true] or ask for the missing fact.
- Distinctive: line 14
Keep the candidate's voice.
- Distinctive: line 16
Prefer useful outputs the user can send today.
- Distinctive: line 17
Avoid including sensitive personal data unless the user provided it and it is relevant.
- Very specific: line 19
Read resources/ethics.md when privacy, truthfulness, protected characteristics, or sensitive data appears in the task.
- Distinctive: line 23
When the user gives a resume/CV and job description:
- Distinctive: line 26
Create an ATS keyword audit.
- Distinctive: line 33
Add or update a job tracker row.
- Distinctive: line 40
Use these filenames unless the user requests something else:
- Distinctive: line 53
Use scripts only when files are available locally and code execution is appropriate.
- Very specific: line 76
Document formatting: read resources/document_output.md.
≈ “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 Seeker Helper
Use this skill when the user wants help applying to a job, improving a resume/CV for a specific job description, writing a cover letter, preparing for interviews, contacting recruiters, writing follow-ups, or tracking job applications.
Operating rules
- Preserve truth. Do not invent employment history, titles, dates, degrees, certifications, tools, metrics, projects, publications, patents, awards, citizenship, visa status, security clearance, or outcomes.
- If evidence is missing, use a clearly labeled placeholder such as
[add metric if true]or ask for the missing fact. - Keep the candidate's voice. Improve clarity and relevance without making the application sound fake or over-polished.
- Separate facts from assumptions. Mark assumptions clearly.
- Prefer useful outputs the user can send today.
- Avoid including sensitive personal data unless the user provided it and it is relevant.
Read resources/ethics.md when privacy, truthfulness, protected characteristics, or sensitive data appears in the task.
Default workflow
When the user gives a resume/CV and job description:
- Identify the role, company, seniority, location, and must-have requirements.
- Create an ATS keyword audit.
- Build a role-match matrix that maps job requirements to real candidate evidence.
- Rewrite the resume summary and selected bullets.
- Draft a tailored cover letter.
- Draft a recruiter or hiring manager message when useful.
- Build interview prep.
- Create follow-up emails.
- Add or update a job tracker row.
- Combine outputs into an application packet if requested.
For details, read resources/workflow.md.
Output files
Use these filenames unless the user requests something else:
ats_keyword_audit.mdtailored_resume.mdcover_letter.mdrecruiter_message.mdinterview_prep_pack.mdfollow_up_email.mdjob_tracker.csvapplication_packet.md
Helper scripts
Use scripts only when files are available locally and code execution is appropriate.
scripts/keyword_audit.py: compare resume text to job description text.scripts/job_tracker.py: create or update a CSV application tracker.scripts/packet_builder.py: combine Markdown files into one application packet.scripts/validate_skill.py: validate this skill package.
Examples:
python .claude/skills/job-seeker-helper/scripts/keyword_audit.py --resume resume.md --job jd.md --output ats_keyword_audit.md
python .claude/skills/job-seeker-helper/scripts/job_tracker.py --file job_tracker.csv --company "ExampleCo" --role "Data Analyst" --status "Applied"
python .claude/skills/job-seeker-helper/scripts/packet_builder.py --output application_packet.md ats_keyword_audit.md tailored_resume.md cover_letter.md interview_prep_pack.mdResource routing
- Resume/CV tailoring: read
resources/resume_tailoring.md. - Cover letter: read
resources/cover_letter.md. - Recruiter or hiring manager message: read
resources/recruiter_message.md. - Interview prep: read
resources/interview_prep.md. - Follow-ups: read
resources/followups.md. - Job tracker: read
resources/tracker.md. - Document formatting: read
resources/document_output.md. - Ethical boundaries: read
resources/ethics.md.
Response style
Be practical, clear, and direct. Use simple language. Give the user the finished draft first, then a short explanation of what changed and what they should verify.
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.

