Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Reference Check Pro

    1

    Plan job-related reference checks with candidate consent, consistent questions, verified identity, and careful notes.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Reference Check Pro

    Reference Check Pro

    Example session with this skill installed

    Create a reference-check guide for a senior product designer. Include questions that verify work without seeking confidential information.

    • Read your context and instructions
    • Compiled the reference check pro

    Reference Check Pro: practical plan

    Reference-check guide

    Before the call

    Confirm candidate consent, reference identity and relationship. Explain the role and limit questions to job-related work. Do not request confidential information from a former employer.

    Consistent questions

    1. What was the candidate’s role and scope?
    2. How did they approach user research and design tradeoffs?
    3. Can you describe a project outcome and the candidate’s contribution?
    4. How did they collaborate with engineering and product partners?
    5. What environment helps them do their strongest work?
    6. Would you work with them again in a similar role, and why?

    Notes

    Separate direct observations from opinion, capture examples, and avoid irrelevant personal details. Do not treat one reference as definitive.

    Fairness and privacy

    Use a consistent process for candidates, store notes securely and follow retention rules. Avoid questions about protected characteristics, health, family or other unrelated matters.

    Decision use

    Treat references as one input alongside structured interviews and work evidence. Human reviewers document how evidence relates to role criteria.

    Measurement and review

    Record the baseline, source, date range, denominator and owner. Use one primary measure plus quality guardrails; compare like-for-like cohorts and disclose missing data. Treat estimates as scenarios, not observed outcomes.

    Risks and controls

    Check relevance, consent, disclosure, workload and downside before scaling. Keep an evidence trail, obtain human review for material commitments, and pause if trust, quality or compliance signals deteriorate.

    Next steps

    1. Confirm the goal, audience and available capacity.
    2. Gather the minimum evidence for a first test.
    3. Assign an owner, budget and review date.
    4. Run a small pilot, record outcomes and decide whether to iterate, expand or stop.

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

    About this skill

    Create a practical, evidence-led Reference Check Pro workflow. Plan job-related reference checks with candidate consent, consistent questions, verified identity, and careful notes. Distinguish observations from assumptions, request missing inputs, give actionable recommendations with owners and measurable outcomes, and flag uncertainty. Avoid fabricated metrics, unsupported guarantees, deceptive tactics and unnecessary personal data.

    Requires user-provided candidate data and referee feedback. Does not perform background checks or contact references. Human review is required for all hiring decisions.

    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 1 month ago

    Permissions

    No special permissions declared or detected

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Reference Check Pro eliminates vague, subjective feedback by using the REVM-12 model to extract specific claims from resumes and generate targeted, evidence-based questions for referees.

    This skill is designed for use within major AI chat interfaces and generates outputs formatted for easy upload into standard ATS (Applicant Tracking Systems) and HRIS platforms.

    You receive the full Reference Check Pro skill configuration, including the structured evidence-capture templates and the multi-source synthesis reporting framework.

    No, the skill is a decision-support tool; you must input the candidate's resume and the feedback provided by references for the AI to analyze and synthesize.

    The skill is built with a neutral, evidence-seeking architecture that avoids leading questions, helping your team maintain high compliance with anti-discrimination principles.

    Simply upload the job description, the candidate's resume, and any interview notes to the AI agent to begin generating your tailored verification plan.

    New in HR & Recruiting