More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    🤝 Human Handoff Detector

    1

    Separate information gaps from authority, emotional, safety, and consequence reasons for human takeover, then prepare a compact handoff packet.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    🤝 Human Handoff Detector

    🤝 Human Handoff Detector

    Example session with this skill installed

    A customer asks for a person after two failed identity-verification loops and a looming travel deadline.

    • Read your context and instructions
    • Compiled the human handoff detector

    verdict: immediate_handoff
    confidence: limited
    observations: [directly supplied facts]
    alternative_explanations: [at least one]
    recommended_action: reversible next step
    human_review: explicit when stakes or authority require it

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

    About this skill

    Know when an agent should stop, why a person is needed, and what that person needs to pick up without making the customer start over. Human Handoff Detector gives support, moderation, operations, and conversational-agent builders designing escalation paths. a bounded, structured review built around observable evidence, calibrated inference, alternative explanations, missing context, and stable verdicts. Its specific rubric covers explicit human request, authority limit, repeated failure, stakes, emotional complexity, safety signal, missing information. It refuses emotional-leverage optimization, diagnosis, protected-trait inference, retaliation, and non-consensual disclosure. High-stakes or irreversible cases receive an explicit human-review recommendation. The package performs no network request, publication, message delivery, purchase, account change, or claim to know another person's inner state.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    • It recommends a handoff but cannot route a real conversation.
    • It does not determine staffing, service levels, or legal escalation duties.
    • Broad rules can over-escalate; narrow organization policy should be supplied.

    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

    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 3 months ago

    Permissions

    File Scopes

    No
    filesystem
    access
    required;
    user-supplied
    prompt
    context
    only

    The skill is an instruction package. Its bundled test script is for package maintainers and is not required during normal use.

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    No. It separates observations from calibrated hypotheses and alternative explanations.

    No. It refuses diagnosis and does not turn communication patterns into claims about a person.

    No. It returns decision support or a draft only and performs no external action.

    It lowers certainty, avoids authorization, and recommends an accountable qualified human when appropriate.

    No. The contract requires proportionality and includes benign regressions specifically to prevent reflexive handoff.

    No. They verify package and safety contracts, not human reaction, legal sufficiency, or semantic perfection.