job-search-setup
Skill0 starsChanged 23 days agoMITView on GitHub
Set up a private job-search workspace or connect an existing search to these skills. Use for onboarding and source mapping.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- kevinmmiddleton/recruiter-bfftheir own version, first seen Oct 17, 2026
- nattarw-tech/AI-job-search-systemtheir own version, first seen Jul 29, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- kevinmmiddleton/recruiter-bff★ 3same name
- nattarw-tech/AI-job-search-system★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- job-applicationSkill
- job-inboxSkill
- job-interviewSkill
- job-offerSkill
- job-pipeline-reviewSkill
- job-researchSkill
- job-resumeSkill
- job-search-scheduleSkill
- recruiting-outreachSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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
- Distinctive: line 19
Call supporting skills when needed.
- Distinctive: line 23
Use the user's chosen private folder, outside the public package and installed skill folders.
- Very specific: line 31
Keep sourced, dated facts and corrections in references/profile.md.
- Distinctive: line 37
Start with one application tracker and one outreach record.
- Distinctive: line 41
Check links, ownership and corrections, then report what's ready and the next useful action.
≈ “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
Set up a job search
Give the search a home, then get to work. Standalone coaching can start from supplied context without a workspace, interview invitation or offer.
Start with a request
Let users ask naturally:
- Find and Apply to Jobs —
job-research - Find and Request Referrals —
recruiting-outreach - Interview Coach —
job-interview - Offer Negotiator —
job-offer
Call supporting skills when needed. Resume tailoring belongs inside the application workflow; users need not manage every handoff.
Choose the workspace
Use the user's chosen private folder, outside the public package and installed skill folders. For an existing search, read its instructions and map its sources. Preserve names, storage services, records and owners; don't create a competing tracker.
For a new search, use ordinary file tools to copy the blank workspace from assets/workspace/ into that folder, preserving subfolders. Rename gitignore.template to .gitignore. Check destination paths first; never overwrite existing files. No installation script is required.
Learn what matters
Reuse the resume and confirmed answers. Ask only for missing targets, level, locations/work rights, working languages, constraints and immediate priorities. Optional unknowns can wait. Collect sensitive identifiers or legal declarations only when an authorized application needs them.
Keep sourced, dated facts and corrections in references/profile.md; keep choices and workflow limits in references/preferences.md. Confirm the scheduling timezone when needed. Don't infer work rights from residence or timezone, or generalize an employer-specific declaration. Leave permissions unset unless granted.
Keep one source for each thing
Adapt the private AGENTS.md to map installed skills and sources. The template routes all ten skills; load only what's needed. Follow recordkeeping when choosing fields and owners.
Start with one application tracker and one outreach record. Keep shortlist choices separate from employer stages; “pursue” alone doesn't authorize submission. Reuse valid grants within scope. Add separate lanes only when needed, with clear ownership.
Reuse resume templates and inventory; preserve submitted versions and receipts. Interview, offer, inbox and schedule notes support the live records. Leave unused templates blank. Dashboards read these sources rather than duplicating stages.
Check links, ownership and corrections, then report what's ready and the next useful action. Keep personal data out of the distributable package. Setup sends no messages, submits no applications and schedules nothing.
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.

