Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+20 more

    senior product spec engine

    2

    Turns vague ideas into shippable, metric-driven PRDs and experiment designs with a Principal PM's rigor.

    $17.99

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    0 installsSecurity scanned
    senior product spec engine

    senior product spec engine

    Example session with this skill installed

    Turn this idea into a PRD: We need a "Save for Later" button on the product page to reduce cart abandonment. Target users are logged-in shoppers. Scope for mobile and desktop.

    • Read your context and instructions
    • Compiled the senior product spec

    I have drafted the product specification for the "Save for Later" feature. It focuses on reducing abandonment by capturing intent earlier in the funnel.

    Product Requirement Document: Save for Later

    1. One-Sentence Outcome

    Increase the cart conversion rate by allowing high-intent users to persist items across sessions without cluttering the active checkout flow.

    2. Problem Statement

    Problem: Users are using the cart as a "wishlist," adding items they aren't ready to buy yet, which skews conversion data and leads to forgotten items when they expire from the session.

    • Evidence: [NEEDS DATA: % of carts abandoned with 3+ items] and user feedback regarding lost items.
    • Cost of Inaction: Continued loss of high-intent shoppers who do not return once their session cookie expires.

    3. Success Metrics

    • Primary Metric: % increase in successful checkouts from "Saved" items within 30 days.
    • Guardrail: No decrease in immediate "Add to Cart" clicks.
    • Baseline: [NEEDS DATA: current checkout conversion rate]

    4. User Stories & Acceptance Criteria

    User Story 1: As a logged-in shopper, I want to move an item from my cart to a "Saved" list so I can clean up my current checkout view without losing the item.

    • AC: Button must be visible in the cart under each line item.
    • AC: Moving to saved must immediately remove the item from the subtotal.
    • Priority: P0
    • User Story 2: As a shopper, I want to see my saved items on the product page so I can quickly add them back.
      • AC: Display a "Saved Items" counter in the header.
      • Priority: P1

    5. Experiment Design

    Hypothesis: If we add a "Save for Later" option, then cart abandonment will decrease by [NEEDS DATA: Target %] because users will distinguish between "buying now" and "considering."

    • Decision Rule: Ship if the checkout conversion rate sees a statistically significant lift without hurting AOV.

    6. Risks & Open Questions

    1. Risk: Users might use this to defer purchases indefinitely (High severity, Medium likelihood).
    2. Question: Should we trigger an automated email when a "Saved" item goes on sale?
    3. Question: What is the current technical limit for persisted items in the database?

    Next steps

    1. Provide the current baseline cart abandonment rate to replace placeholders.
    2. Review the P0 user stories with the engineering lead for a T-shirt estimate.
    3. Confirm if the "Saved" list should persist across different devices.

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

    What you get

    Draft production-ready PRDs from rough feature ideas.Define testable acceptance criteria for engineering handoff.Design A/B test frameworks with clear success/fail decision rules.Structure phased rollout plans and instrumentation checklists.

    About this skill

    The problem

    Vague feature requests and hand-wavy business goals lead to endless clarification meetings, scope creep, and engineering frustration. Most AI-generated PRDs rely on fluff and fabricated metrics that no experienced team can actually ship.

    What it does

    • Transforms raw ideas into structured PRDs with measurable outcomes and rigorous risk analysis.
    • Generates testable user stories with binary pass/fail acceptance criteria for QA.
    • Designs falsifiable A/B experiments including hypothesis, sample size considerations, and kill criteria.
    • Identifies P0/P1/P2 priorities to define a strict MVP scope and phased rollout plan.
    • Enforces an Anti-Fabrication Rule that flags missing data instead of inventing fake metrics.

    Why this beats prompting it yourself

    General-purpose LLMs tend to use "motivational" corporate speak and invent plausible-sounding but fake data points. This skill operates like a Principal PM, ruthlessly cutting scope and forcing you to confront missing baselines and real risks before a single line of code is written.

    Use cases

    • Converting a messy Slack thread or customer complaint into a shippable feature spec.
    • Defining the instrumentation and success metrics for a new growth experiment.
    • Breaking down a high-level roadmap item into actionable developer tickets.
    • Drafting a phased rollout strategy for a high-risk infrastructure change.

    Known limitations

    Does not generate UI/UX mockups, technical architecture diagrams, or production code. Requires user-provided baseline data to avoid placeholders.

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 1 day ago

    • Passed all security checks, Safe to install

    Listed1 day ago

    Frequently Asked Questions