Resume to Standardized Matrix Scorer

    1

    Standardize resume evaluation with weighted, evidence-based scoring and bias-reduction filters.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Resume to Standardized Matrix Scorer

    Example session with this skill installed

    Analyze these three resumes against the Senior Backend Engineer JD. Score them using the standard matrix and generate a comparison summary.

    • Read your context and instructions
    • Compiled the resume to standardized
    • Generated the data export

    I have processed the three resumes against the Senior Backend Engineer requirements. The evidence has been normalized, sensitive attributes excluded, and scoring applied based on the 100-point matrix.

    Screening Summary

    Candidate IDTotal ScoreMatch LabelMust-HavesTop Evidence
    CAND-882192STRONG_MATCHMET8yrs Go/Kubernetes, Distributed Systems
    CAND-330974POTENTIAL_MATCHMETPython/Django expert, missing AWS cert
    CAND-551258NEEDS_REVIEWUNCLEARStrong frontend, Backend experience limited

    Candidate Scorecard: CAND-8821

    Weighted Scoring Breakdown:

    • Required Skills (35/35): Extensive evidence of Go, Postgres, and Microservices.
    • Relevant Experience (25/25): 8 years in high-scale backend environments.
    • Role Responsibilities (12/15): Clear history of system architecture design.
    • Preferred Skills (10/10): Active Kubernetes contributor; GraphQL experience.
    • Education/Certs (5/10): Degree confirmed; missing specific Cloud Architect cert.
    • Evidence Quality (5/5): Metrics-driven bullet points provided.

    Review Queue Status:

    • CAND-5512 flagged for manual review: "Distributed Systems" experience is ambiguous; requires interview clarification.

    Next steps

    1. Review the manual_review_queue.csv for specific questions to ask Candidate 5512.
    2. Import candidate_matrix.csv into your ATS or tracking spreadsheet.
    3. Schedule interviews for the STRONG_MATCH candidates.

    This scorecard standardizes resume evidence against job-related criteria. It should support—not replace—human review, interviews, and lawful recruiting practices.

    manual_review_queue.csv

    CSV · data export

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Resumes vary wildly in format, making fair comparison across a candidate pool difficult. This skill transforms unstructured resumes and job descriptions into a standardized, evidence-based scoring matrix. It eliminates manual data entry and ensures every candidate is evaluated against the same weighted criteria.

    What it does

    • Evidence Extraction identifies specific work history and technical skills directly linked to the job description.
    • Blind Scoring excludes protected attributes like age, gender, and ethnicity to focus solely on job-related qualifications.
    • Matrix Generation builds a 100-point scoring system based on requirements, experience, and responsibilities.
    • Status Mapping flags must-have requirements as Met, Not Met, or Unclear for rapid screening.
    • Artifact Creation produces CSV matrices, JSON scorecards, and a manual review queue for ambiguous cases.

    How it works

    1. Analyze Requirements by parsing the job description to define core criteria and weights.
    2. Process Resumes using text extraction to pull candidate data into a normalized format.
    3. Apply Matrix to score each candidate based on documented evidence and preferred skills.
    4. Export Results into structured files including a screening summary and manual review queue.

    Frameworks & tools

    The skill is designed for data-driven recruiting workflows. It utilizes pypdf for text extraction and outputs standard CSV, JSON, and Markdown formats compatible with ATS platforms or spreadsheets.

    Why this beats prompting it yourself

    Generic prompts often hallucinate qualifications or inadvertently include bias from demographic proxies. This skill enforces a strict non-discrimination rule set and a weighted scoring logic that maintains consistency across hundreds of documents.

    Use cases

    • Screening large applicant pools for specific technical requirements.
    • Standardizing candidate data for presentation to hiring managers.
    • Building a blind recruitment pipeline to reduce unconscious bias.
    • Identifying gaps in candidate documentation for follow-up interviews.

    Known limitations

    Requires high-quality text extraction from PDFs. OCR-based inputs are flagged with lower confidence and require manual verification. It does not make final hiring decisions.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for HR & Recruiting.

    Text extraction confidence drops for image-heavy or complex PDF layouts. Ambiguous requirements are flagged for manual review rather than auto-resolved.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Software
    Python

    Permissions

    Terminal / Shell
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill uses a blind scoring layer that automatically strips demographic indicators and proxy data before evaluation, ensuring the matrix is built solely on evidence-linked skills and work history.

    The skill delivers a structured package including the 100-point scoring matrix in CSV/JSON formats, a Markdown summary of evidence for each candidate, and a 'Manual Review' queue for ambiguous entries.

    It is designed to be agent-agnostic, requiring only a file-processing environment with Python capabilities to handle text extraction and structured data output.

    While the skill handles most standard PDF and text resumes, it will flag low-confidence OCR scans (like photos of resumes) for manual verification to ensure data integrity.

    Yes, the skill allows you to define core criteria and specific weights during the 'Analyze Requirements' phase to align the scoring matrix with your specific hiring priorities.

    New in HR & Recruiting

    Free