Empat.ia: User Discovery Guide

    1

    A guided Design Thinking method that turns your user interviews into design principles backed by evidence.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Empat.ia: User Discovery Guide

    Example session with this skill installed

    I want to start a new user discovery for a project called "DevFlow", a tool to automate PR reviews. Help me get the workspace ready.

    • Read your context and instructions
    • Compiled the empat ia

    I will initialize the Empat.ia discovery framework for

    DevFlow. This will create the discovery/ directory and set up your initial research state.

    Initialization Result

    ActionPathStatus
    Workspace Createddiscovery/Success
    State Initializeddiscovery/_engine/state.yamlPhase 1: Capturing
    Brief Generateddiscovery/1-desk-research/brief.mdDrafted
    Assumptions Logdiscovery/_engine/assumptions.mdInitialized
    Scripts Readyscripts/init_project.pyVerified

    Project Summary

    • Project Name: DevFlow
    • Current Phase: 1 (Desk Research)
    • Goal: Automate PR reviews

    Recommended Action: Complete the brief.md to define the target user and the specific hypothesis you need to validate.

    Next steps

    1. Open discovery/1-desk-research/brief.md and fill in the "Decision to unblock" section.
    2. Run python3 scripts/init_project.py --add market-research when you are ready to analyze competitors.
    3. Review discovery/_engine/assumptions.md to see the initial risks I've flagged regarding your user profile.

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

    About this skill

    Empat.ia walks you through a user discovery project step by step, from framing the challenge and desk research to interview guides, recruiting, fieldwork capture, synthesis and a final report. It creates a discovery/ folder in your project with living documents, visible state and gates that close with a clear recommendation: advance, deepen, question or call the council. Facts, assumptions and the assistant's own readings are kept separate, and every principle traces back to verbatim quotes and atomic evidence. A council of specialist agents can pressure-test decisions. It does not interview for you: you need 10 to 12 real conversations and about a week of work.

    Requires Python 3 standard library. The assistant must have filesystem and command execution permissions to run the init and migration scripts. Web research requires an active search tool.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The skill automates the creation of a structured `discovery/` directory in your repo, using Python and YAML to track research state, validate evidence, and ensure design principles are never based on guesses.

    You receive the complete Python-based discovery framework, directory templates, state-tracking schemas, and the specialized agent logic required to manage gated research transitions.

    This skill is designed for agents with local file system access and a Python 3 environment, making it ideal for use within IDE-based assistants or local developer environments.

    Unlike a single prompt, this skill maintains a persistent 'source of truth' in your repository, preventing the AI from losing context over long research cycles and enforcing rigid evidence-linking.

    Simply point the skill to your project's root directory; it will automatically scaffold the necessary folders and initialize a `state.yaml` file to begin your guided discovery process.

    The Expert Council is a simulated panel of diverse personas (like sociologists and technologists) that audit your findings to identify biases and stress-test your design principles before you finalize them.

    New in Business & Operations