More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Medical Records Documentation Quality Auditor

    1

    Audit medical record documentation for completeness, consistency, and administrative quality using structured rubrics.

    $19.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Medical Records Documentation Quality Auditor

    Medical Records Documentation Quality Auditor

    Example session with this skill installed

    Audit these three de-identified admission records (REF001, REF002, REF003) against the standard Admission Policy requiring: Patient Consent (M), Admitting Provider (M), and Referral Source (C).

    • Read your context and instructions
    • Compiled the medical records documentation

    The audit of three de-identified admission records against the Admission Policy is complete. Significant gaps were identified in conditional field reporting and provider metadata.

    Medical Records Documentation Quality Audit

    1. Executive Summary

    The audit revealed a 66% completeness rate for mandatory fields. The primary issue is the consistent omission of Admitting Provider metadata in late-shift entries and missing Referral Source documentation where indicated.

    2. Documentation Completeness Audit

    Record RefPatient Consent (M)Admitting Provider (M)Referral Source (C)Status
    REF001PresentPresentN/AComplete
    REF002PresentMissingMissing (Triggered)Incomplete
    REF003PresentPresentMissing (Triggered)Incomplete

    3. Missing Information Register

    Record ReferenceField NameRequirementOperational ImpactRecommended Owner
    REF002Admitting ProviderMandatoryBilling delay; lack of accountabilityAdmissions Clerk
    REF002Referral SourceConditionalMarketing data loss; intake trackingAdmissions Clerk
    REF003Referral SourceConditionalMarketing data loss; intake trackingAdmissions Clerk

    4. Record Consistency Findings

    REF002: Entry timestamp (23:15) lacks an associated provider ID, suggesting a workflow bypass during shift change.

    • REF003: Record indicates "Transfer" status but the Referral Source field remains null.

    5. Documentation Quality Score

    • Completeness: 60/100 (Weight 35%)
    • Consistency: 80/100 (Weight 25%)
    • Organization: 90/100 (Weight 15%)
    • Traceability: 50/100 (Weight 15%)
    • Timeliness: 70/100 (Weight 10%)
    • Weighted Total Score: 68.5%

    6. Improvement Checklist

    • Update Admission Form to make Admitting Provider a hard-stop field in the UI.
    • Conduct training for night-shift staff on referral source documentation for transfers.
    • Implement a weekly reconciliation report for incomplete admission records.

    Next steps

    1. Route the Missing Information Register to the Admissions Department head for immediate remediation.
    2. Review the Admission Form UI logic to ensure conditional fields toggle to mandatory when "Transfer" is selected.
    3. Schedule a follow-up audit for REF-series records in 30 days.

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

    About this skill

    Inconsistent medical recordkeeping leads to administrative friction, denied claims, and audit failures. This skill systematizes documentation quality reviews by identifying gaps, inconsistencies, and traceability issues in de-identified record samples. It provides a structured framework for assessing record integrity without compromising privacy or safety.

    What it does

    • Documentation completeness audit compares records against policies to identify missing mandatory or conditional fields.
    • Missing information identification generates a prioritized register of gaps with operational impact analysis.
    • Record consistency checks flags chronological errors, mismatched identifiers, and conflicting status transitions.
    • Organization and traceability evaluation assesses version control, author metadata, and document categorization.
    • Documentation quality scoring calculates a weighted score based on completeness, consistency, and timeliness.

    How it works

    1. Define scope by providing record types, review periods, and the governing documentation policy or form standard.
    2. Provide data in the form of de-identified record samples, field-level extracts, or metadata tables.
    3. Analyze records through automated checks for mandatory field presence and internal data logic.
    4. Review findings via a structured audit report including a missing information register and quality score.

    Frameworks & tools

    This skill utilizes specialized templates for medical record audits and a standardized documentation quality rubric. It is designed to work with de-identified CSV extracts, YAML audit templates, and Markdown-based policy documents.

    Why this beats prompting it yourself

    General purpose prompts often fail to distinguish between "not applicable" and "missing" data or may hallucinate values to fill gaps. This skill enforces strict privacy rules, uses a transparent weighted scoring rubric, and prevents unauthorized record "corrections" by strictly adhering to administrative audit workflows.

    Use cases

    • Audit department-level records for completeness before internal governance reviews.
    • Identify recurring documentation errors to inform staff training and form redesign.
    • Validate the integrity of record handoffs between different facility departments.
    • Assess the quality of metadata and version control in digital health information systems.

    Known limitations

    Does not perform clinical diagnoses or legal compliance certification. Requires de-identified data; users must remove direct identifiers before sharing. Cannot assess storage system security.

    Requires de-identified data. Does not certify legal compliance or perform clinical diagnoses. Cannot assess physical or digital storage security.

    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 any payment.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 8 days ago

    Permissions

    No special permissions declared or detected

    Listed8 days ago

    What's inside

    Frequently Asked Questions

    The skill functions by comparing your de-identified record samples against your specific documentation policies or form standards, flagging gaps, chronological errors, and metadata inconsistencies using a weighted scoring rubric.

    To maintain privacy and security, this skill requires data to be fully de-identified before processing; it does not accept files containing Protected Health Information (PHI) or direct identifiers.

    Yes, you can customize the audit by providing your own record types, review periods, and governing policy documents to ensure the analysis aligns with your facility's specific standards.

    Upon purchase, you receive the AI agent skill configuration, a set of YAML audit templates, a standardized documentation quality rubric, and a guide for preparing your de-identified data.

    This skill is compatible with most major AI platforms that support file uploads or data extraction, specifically those capable of processing CSV, Markdown, and YAML file formats.

    Unlike a standard prompt, this skill uses a structured framework that distinguishes between 'not applicable' and 'missing' data, preventing the AI from 'hallucinating' or filling in gaps with invented information.

    New in Business & Operations