More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    ⏸️ Should This Be Automated?

    1

    Classify a consequential people-facing action as suitable for automation, revision, delay, human review, human delivery, or no automation.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    ⏸️ Should This Be Automated?

    ⏸️ Should This Be Automated?

    Example session with this skill installed

    A billing agent plans to publicly flag a disputed account and freeze access without an appeal path.

    • Read your context and instructions
    • Compiled the should this be

    verdict: do_not_automate
    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

    Before an agent sends, rejects, suspends, accuses, publishes, or escalates, check whether a machine should be doing it at all. Should This Be Automated? gives agent developers, operations teams, support leaders, and policy owners before a people-facing action is automated. a bounded, structured review built around observable evidence, calibrated inference, alternative explanations, missing context, and stable verdicts. Its specific rubric covers irreversibility, vulnerability, power imbalance, appealability, factual dispute, recipient preference, public exposure. 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 does not authorize an action or establish legal compliance.
    • It cannot verify facts or infer a recipient's mental state.
    • Organizations remain responsible for policy, appeals, human staffing, and final 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 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

    It provides a structured risk assessment for agentic actions, helping you determine if a task—like suspending a user or issuing a rejection—should be handled by an AI or requires human intervention based on ethics and impact.

    This skill is a decision-support module designed to be integrated into any LLM-powered agent workflow via standard API or function calls before the final action phase.

    No, the skill operates as a closed-loop evaluation tool; it analyzes the proposed action against a rubric and returns a classification without performing any external API calls or database changes.

    The skill evaluates actions against seven specific risk dimensions, including irreversibility, power imbalance, and recipient vulnerability, to ensure a stable and defensible verdict.

    You receive the complete logic package for the 'Should This Be Automated?' skill, including the specialized classification rubric and documentation for integrating it into your agent's decision-making flow.

    If the skill detects high-stakes factors like high irreversibility or a lack of context, it will flag the action for 'Human Review' or 'Human Delivery' rather than approving automated execution.