score-fit
Skill0 starsChanged 3 months agoMITView on GitHub
Score candidate fit against target jobs using an explainable 6-factor rubric with explicit strength and gap analysis.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/job-agent.mdcCursor rule
- 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
- setup-profileSkill
- tailor-resumeSkill
- write-cover-letterSkill
The file
Files
score-fit
Evaluates candidate fit against job postings using transparent, weighted criteria rather than arbitrary LLM percentages.
Rubric Factors
- Title & Role Relevance (25%): Title overlap, level, target keyword alignment.
- Core Required Skills (25%): Proven candidate technologies vs requirements.
- Seniority & Experience (15%): Years of experience and level expectations.
- Domain & Industry Fit (15%): Alignment with candidate domain expertise.
- Location & Work Mode (10%): Remote / hybrid / onsite compatibility.
- Preferred Qualifications (10%): Transferable skills and nice-to-haves.
Output Breakdown
- Score: 0 to 100
- Recommendation:
APPLY(>=80),CONSIDER(65-79),SKIP(<65) - Proven Matches: Specific overlapping technical competencies
- Material Gaps: Specific requirements candidate profile lacks
- Hard Disqualifiers: Immediate blockers (clearance, visa, company blacklist)
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.