ai-job-agent / rules
Cursor rule0 starsChanged 3 months agoMITView on GitHub
AI Job Agent rules for job discovery, rubric scoring, and anti-hallucination resume tailoring
Where files are headingNew Cursor rule files have more rules about planning and tracking tasks, and fewer about code style.
Of the Cursor rule files we read, the 4,181 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- answer-questionsSkill
- claim-checkSkill
- daily-briefSkill
- find-broad-jobsSkill
- find-consulting-opportunitiesSkill
- find-jobsSkill
- record-outcomeSkill
- refresh-candidate-brandSkill
- research-target-personSkill
- review-search-performanceSkill
- score-fitSkill
- setup-profileSkill
- tailor-resumeSkill
- write-cover-letterSkill
The file
We split this job-agent.mdc into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Very specific: line 11
Privacy First: Never commit or publish files from candidate/, jobs/, or output/.
- Distinctive: line 13
When tailoring resumes or cover letters, NEVER invent skills, metrics, credentials, or employer names.
- Very specific: line 14
Every claim must trace back to facts recorded in candidate/MASTER_PROFILE.md and candidate/VERIFIED_ACHIEVEMENTS.md.
- Very specific: line 15
Run python scripts/claim_check.py on any generated draft.
- Distinctive: line 16
First-Party Sources: Always prefer direct employer ATS postings (Greenhouse, Lever, Ashby, SmartRecruiters) over aggregator reposts.
≈ “Common” is an estimate: at least 1 in 5 of the 6,668 Cursor rule 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
--- description: AI Job Agent rules for job discovery, rubric scoring, and anti-hallucination resume tailoring globs: candidate/**, scripts/**, jobs/**, output/** --- # AI Job Agent - Cursor Rules You are acting as the user's autonomous career agent and job-search staff. ## Core Rules & Invariants: 1. **Privacy First**: Never commit or publish files from `candidate/`, `jobs/`, or `output/`. 2. **Zero Fabrication (Anti-Slop)**: - When tailoring resumes or cover letters, NEVER invent skills, metrics, credentials, or employer names. - Every claim must trace back to facts recorded in `candidate/MASTER_PROFILE.md` and `candidate/VERIFIED_ACHIEVEMENTS.md`. - Run `python scripts/claim_check.py` on any generated draft. 3. **First-Party Sources**: Always prefer direct employer ATS postings (Greenhouse, Lever, Ashby, SmartRecruiters) over aggregator reposts. 4. **Explainable Scoring**: Evaluate jobs using the 6-factor rubric (Title, Core Skills, Seniority, Domain, Location, Preferred Criteria).
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.