resume-fit-scorer
Skill1 starsChanged 6 months agoMITView on GitHub
Scores how well a resume fits a specific job description on a 0–10 scale across 6 weighted dimensions (JD match, achievement strength, targeting, ATS-parseability, red flags, language), returns a brutally honest critique, and emits structured prioritized fixes. Distilled from "Resumes For Dummies" (AI-era ed.). Built for automated pipelines (e.g. JobHunter) as the verifier in a write→score→revise loop.
In this repository21 other files it gives its agents.
- ai-context-engineeringSkill
- ai-context-engine-productionSkill
- ai-context-engineSkill
- ai-dataset-engineeringSkill
- ai-evaluationSkill
- ai-finetuningSkill
- ai-foundation-modelsSkill
- ai-inference-optimizationSkill
- ai-multi-agent-mcpSkill
- ai-production-architectureSkill
- ai-prompt-engineeringSkill
- ai-rag-and-agentsSkill
- ai-rag-defenseSkill
- ddia-architectureSkill
- ddia-batch-stream-processingSkill
- ddia-data-ethicsSkill
- ddia-data-modelingSkill
- ddia-replication-shardingSkill
- ddia-transactions-consistencySkill
- job-description-analyzerSkill
- resume-content-writerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 55
Read guidelines.md — it routes from your task/symptom to the right files.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
resume-fit-scorer
Judges a resume against one job — harshly, on a 0–10 scale — and explains exactly why. It scores 6 weighted dimensions, detects red flags, computes must-have coverage, and returns a critique plus impact-ordered fixes that the writer can act on. Built from "Resumes For Dummies" (AI-era ed.), chapters 1, 2, 3, 5, 6, 10, 15, 16, 18.
Role in the JobHunter pipeline
job-description-analyzer → resume-content-writer → [resume-fit-scorer] → (revise loop)
TargetProfile ResumeContent FitScore ──┐
▲ │ prioritized_fixes
└──────────────────────────────┘It accepts a resume (plain text or resume-content-writer output) + a TargetProfile, and returns a FitScore. See workflows/score-resume-against-jd.md for the full I/O contract and the rubric.
Default rubric (overridable via weights)
| Dimension | Weight |
| JD match | 30% |
| Achievement strength | 25% |
| Targeting & focus | 15% |
| ATS parseability | 10% |
| Red flags | 10% |
| Language | 10% |
Verdicts use threshold comparisons on the real-valued overall, not integer-rounded bands.
| Overall | Verdict |
< 3.0 | Trash |
>= 3.0 and < 5.0 | Weak |
>= 5.0 and < 7.0 | OK |
>= 7.0 and < 9.0 | Strong |
>= 9.0 | Excellent |
Calibrated harshly: a generic, untargeted resume should land 3–5, not 7.
Quick Start
- Read
guidelines.md— it routes from your task/symptom to the right files. - For an end-to-end score, follow
workflows/score-resume-against-jd.md. - Load only the reference files the guidelines point to.
- Compute the weighted overall, apply red-flag/missing-must-have ceilings, and return actionable fixes.
Contents
References
| Category | Files | Purpose |
references/scoring-rubric/ | knowledge, rules, examples | The 6 dimensions, weights, 0–10 bands, weighted formula, calibration |
references/jd-match/ | knowledge, rules, examples | The 30% dimension: ATS + glance + decision-maker screening, coverage |
references/red-flags/ | smells, checklist | Red-flag catalog + fast scan / auto-reject criteria |
Workflows
| Task | Workflow |
| Score a resume against a JD (0–10 + critique + fixes) | workflows/score-resume-against-jd.md |
Guidelines
See guidelines.md for task/symptom-based file selection, a decision tree, the full file index, and common combinations.
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.