More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    🤨 Raised Eyebrow

    1

    Return the single best-supported detail that deserves one more question, with benign and concerning explanations.

    Free

    3 usesSecurity scanned
    🤨 Raised Eyebrow

    🤨 Raised Eyebrow

    Example session with this skill installed

    A vendor promises a guaranteed outcome but will not name the data source behind its benchmark.

    • Read your context and instructions
    • Compiled the raised eyebrow

    verdict: ask_one_question
    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

    Find the one detail that deserves another question before you proceed. Raised Eyebrow gives anyone screening a message, offer, plan, profile, proposal, or claim before committing more time or money. a bounded, structured review built around observable evidence, calibrated inference, alternative explanations, missing context, and stable verdicts. Its specific rubric covers internal inconsistency, unsupported specificity, missing evidence, asymmetric risk, pressure, unusual omission, claim-to-proof gap. 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.

    • It selects one detail and may omit other risks.
    • An eyebrow-raising detail is not proof of deception or wrongdoing.
    • Compact output is unsuitable for legal, safety, financial, or due-diligence decisions without human review.

    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

    3 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    • Free with an Agensi account

    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

    The skill acts as a critical thinking filter that identifies the single most significant inconsistency or gap in a document, helping you avoid "too good to be true" scenarios or hidden risks before you commit resources.

    You can use Raised Eyebrow on any text-based input, including business proposals, job applications, sales pitches, legal claims, or project plans that require a second look.

    No, this skill is designed for privacy and safety; it never makes external network requests, performs purchases, or delivers messages to third parties.

    The skill adheres to a strict "no diagnosis" policy, meaning it focuses solely on observable evidence and logic gaps rather than attempting to guess a person's inner state or character.

    You receive the core logic package and the structured rubric, which is compatible with any AI agent capable of processing complex analytical instructions.