Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Feature Prioritizer (RICE)

    1

    It also generates the questions to ask in the prioritization meeting — the ones that make advocacy visible before it's baked into the roadmap.

    $8.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Feature Prioritizer (RICE)

    Feature Prioritizer (RICE)

    Example session with this skill installed

    Apply RICE to our new product features: In-app chat (500 users, high impact, 2 weeks) and Dark Mode (all users, low impact, 2 days). Identify the weakest assumptions.

    • Read your context and instructions
    • Compiled the feature prioritizer rice
    • In-app Chat: Score 45. Critical assumption: 50% increase in retention (Confidence ceiling 50% - anecdote only).
    • Dark Mode: Score 120. Data-backed Reach (100% of users) provides higher confidence (90%).
      Recommendation: Verify retention impact for Chat before committing.

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

    About this skill

    RICE fails in practice for one reason: the numbers are advocacy. Reach is inflated because the team is excited, effort is underestimated because no one wants to kill their feature, and confidence is whatever makes the score win. This skill applies RICE in a way that surfaces the biases: it asks for the reasoning behind each estimate rather than just the number, flags when estimates are inconsistent with historical data, separates the team's confidence from the model's implied confidence, and produces a prioritized stack with the key assumptions that would flip each ranking. It also generates the questions to ask in the prioritization meeting — the ones that make advocacy visible before it's baked into the roadmap. Bring your feature list and context; get back a scored stack you can defend and the list of assumptions worth stress-testing.

    • Requires external user data for Reach accuracy.
    • Cannot automate engineering effort estimates.
    • Best for strategic planning, not real-time task sorting.

    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 4 months ago

    Permissions

    No special permissions declared or detected

    Listed4 months ago
    Updated4 months ago

    What's inside

    Frequently Asked Questions

    Unlike standard templates, this skill identifies 'advocacy' by requiring reasoning for every metric, flagging inconsistencies with historical data, and highlighting the specific assumptions that, if changed, would flip your rankings.

    You get the core Feature Prioritizer agent skill, a guide on preparing your feature backlog for analysis, and a structured output template that includes both the RICE stack and the 'stress-test' questions for your next meeting.

    The skill is designed to work with any large language model (LLM) that supports reasoning and data processing; simply import the skill into your preferred AI agent environment and provide your feature list via text or document upload.

    No complex coding is required; once added to your workspace, you simply provide your feature descriptions and any historical project data you have, and the agent will guide you through the calibration process.

    The skill separates your team's subjective confidence from the model's objective analysis, providing a secondary 'implied confidence' score based on the evidence provided for Reach, Impact, and Effort.