Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    StreamTeem Product Manager Expert

    1

    Product Manager Expert makes your agent frame product work the way a product manager does: a user problem, an outcome, and a now-versus-later cut, with the decisions written down.

    $4.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    StreamTeem Product Manager Expert

    StreamTeem Product Manager Expert

    Example session with this skill installed

    Start a Product Initiative for checkout friction on mobile. Use work item PM-214. No outside references yet.

    • Read your context and instructions
    • Compiled the streamteem product manager

    Work item PM-214 is set up on the

    Product Initiative workflow. Your role was already defined, so I went straight to the work item and its first phase, intake.

    Where things stand

    ItemValue
    Work itemPM-214, checkout friction on mobile
    WorkflowProduct Initiative
    PhaseIntake
    Journalproduct-manager/journals/work-items/PM-214/progress.md
    Brief (not written yet)product-manager/work-items/PM-214/docs/charter/brief.md

    Four questions before I write the brief

    These are blocking, and "continue" does not count as an answer.

    1. Problem: What problem is this, and for whom?
    2. Outcome: What outcome would show it is solved?
    3. Out of scope: What is explicitly out of scope?
    4. Agreement: Who must agree before this plan is current?

    Next steps

    1. Answer the four questions. I record each answer in the journal in the same turn, then write the brief with the answers, the unknowns, and the risks.
    2. After the brief comes the Opportunity Brief and its diagrams: journey, prioritization, stakeholder map, and decision flow.
    3. I then stop until you say "I approve the charter" or "Skip charter approval". Only after that do I write the Product Plan.

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

    About this skill

    Product Manager Expert makes your agent frame product work the way a product manager does: a user problem, an outcome, and a now-versus-later cut, with the decisions written down.

    Say "start". The pack asks what the problem is and for whom, what outcome would show it is solved, what is explicitly out of scope, and who must agree. It writes a brief, then an Opportunity Brief (problem, users, outcome, non-goals, assumptions) with its diagrams, and stops for your approval. The Product Plan follows (scope now, scope later, success metrics, risks, rollout narrative, open decisions) with a second approval gate. Only then does it write the action list, create the discovery log, the decision log, the roadmap slice, and the stakeholder list, and work through the actions one at a time: discovery notes, prioritization decisions, roadmap updates, stakeholder readouts, metric checks. Verification and a close-out finish the work item.

    A second workflow handles escalations: a launch problem, a priority conflict, a user issue that changes the outcome. It assesses, lays out the options and who decides, waits for your approval of a response, then records what was communicated and what is being watched.

    Everything the pack knows lives in a product-manager/ folder in your project: a journal with the next step, the documents, and a memory of facts and rules about your role. Close the session, switch agents, come back next week, and "continue" picks up at the exact step where the work stopped.

    What makes it different:

    • "Continue" is never taken as approval. A gate clears only when you say "I approve the charter" (or the plan, the change, the response).
    • Actions are discovery notes, priority decisions, roadmap updates, and readouts. They are never build tasks.
    • A change to priority, to what is in scope now, or to the success metric goes through a change request, not a quiet edit of the plan.
    • It remembers. The pack starts with ten facts and ten rules for the role and adds your own.
    • Skill names are prefixed pm-, so the pack installs beside the other StreamTeem packs.

    Works on local Markdown files only; it does not connect to Jira, Linear, Productboard, or other product tools. Actions are discovery notes, priority decisions, roadmap updates, and readouts, not build tasks. Viewing the diagram page needs internet access, because the page loads Mermaid from a CDN. Python 3 is needed only to run the optional memory analysis script; without it the agent does the same counts by reading the files.

    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 days ago

    Requires

    Writable project folder
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Read/Write create the journal, charters, plans, diagrams, trackers, and notes under one folder in the project. Shell runs only the bundled read-only memory analysis script, and only when you ask for a memory check.

    Listed4 days ago

    What's inside

    Frequently Asked Questions

    The pack keeps a journal in a product-manager/ folder in your project that records the current phase, the decisions, and the single next step. Each "continue" performs that one step and stops, and the Opportunity Brief, the Product Plan, changes, and escalation responses each wait for your explicit approval. Because the state is in files, a new session or a different agent resumes where the last one stopped.

    Twenty-six skills (all prefixed pm-), two workflows (Product Initiative and Product Escalation), templates for the journal, the work item status and action list, and the memory files, a starter memory of ten facts and ten rules for the role, and one read-only Python script that reports on the size and health of the memory files. The skills write the Opportunity Brief, the Product Plan, discovery and decision logs, and diagrams (journey, prioritization, stakeholder map, decision flow, in Mermaid) as the work proceeds.

    Yes. The diagram generator writes Mermaid files for the journey, prioritization, stakeholder map, and decision flow, plus a local HTML page that shows them. Viewing that page needs internet access to load Mermaid from a CDN.

    A project folder the agent can write to. Nothing else has to be installed. Python 3 is optional: it runs the memory analysis script, and without it the agent does the same counts by reading the files. To view the diagram page, your browser needs internet access to load Mermaid.

    Each initiative is a work item under product-manager/work-items/, with its own journal. Switch between them by asking to switch context to another work item id; "continue" then resumes that item at its next step.

    New in Business & Operations