Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Skill Pack Manager

    1

    Guidance and verification for the JetFerrari Agent Engineering stack: finds which skills your agent exposes, picks the smallest profile, and checks setup, marking discovery CONFIRMED or UNVERIFIED. Installs nothing.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Skill Pack Manager

    Skill Pack Manager

    Example session with this skill installed

    I connected this pack to my agent. Which skill do I use to review a risky PR, and is it loaded?

    • Read your context and instructions
    • Compiled the manager

    Illustrative example, synthetic data. File names, findings and outputs below are made up to show the shape of a real run. In actual use the skill reports only evidence supplied or verified in your environment and marks anything unavailable as UNVERIFIED.

    RUNTIME: agent-hosted (MCP connection).
    SKILLS AVAILABLE / EXPECTED: change-assurance-review expected for diff review; ship-gate for final readiness.
    PROFILE IN USE: core (covers implementation/debug/review/continuity).
    MISSING / UNAVAILABLE: none detected; if change-assurance-review does not activate on a review prompt, acquire/enable it via the marketplace.
    DISCOVERY: CONFIRMED (agent listed change-assurance-review).
    NEXT ACTION: invoke change-assurance-review on the PR; if it is complete and you want a go/no-go, follow with ship-gate.
    

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

    About this skill

    Skill Pack Manager is a guidance and verification skill for the JetFerrari Agent Engineering stack. It helps you find out which skills your agent can load, choose the smallest profile that covers your recurring work, and confirm that the skill you intended actually activates. It reports discovery as CONFIRMED or UNVERIFIED instead of assuming a skill is loaded.

    The problem it addresses

    A set of engineering skills only helps if you know which one to reach for and whether your agent really has it. This skill answers questions such as "which skill should I reach for", "is this skill loaded" and "what profile fits my work", and keeps each answer tied to what the runtime actually exposes.

    How it works

    It runs three phases in order.

    1. Discover what the runtime exposes: ask the active agent to list or search its available skills and check whether the JetFerrari skill you intend to use is present. If the runtime offers no way to enumerate skills, discovery is marked UNVERIFIED and you invoke the skill directly to observe whether it activates.
    2. Select the smallest profile: choose the smallest set of skills that covers the recurring work. The package describes four profiles: core, architecture, ui and full. When the right workflow is unclear, start with master-orchestrator, which routes to the smallest sufficient next phase.
    3. Verify: confirm that the intended skill activates on a representative prompt and produces its documented output contract. If an expected skill is not available through your agent, name it by its canonical name and acquire or enable it through your marketplace instead of assuming it exists.

    What you get back

    A fixed six-field report: RUNTIME, SKILLS AVAILABLE / EXPECTED, PROFILE IN USE, MISSING / UNAVAILABLE, DISCOVERY (CONFIRMED or UNVERIFIED) and NEXT ACTION. The package includes a filled-in worked example in which a user asks which skill reviews a risky PR and whether it is loaded.

    Boundaries

    It is guidance and verification only. It does not install software or modify system configuration, and it is not for installing application dependencies such as npm, pip or cargo packages. The package states that skills reach your agent through the marketplace or agent connection, for example Agensi over MCP, so there is no local installer to run. Project governance documents, ADRs and approved specs outrank this skill, and it stops at its own boundary and names the next phase instead of certifying downstream work.

    How it differs from nearby work

    It is not one of the workflow skills it points to. In the worked example, change-assurance-review is named for diff review and ship-gate for a final go/no-go, and this skill only tells you which one to invoke and whether it is available. It is also not an installer, and it is not used in place of simply invoking the skill you need.

    Evidence discipline

    Facts, inferences and unknowns are kept separate. The skill never assumes a shell, Git, browser, network or MCP tool exists, verifies capability first, and never claims a tool ran when it did not.

    Validation scope

    The package is five text files: the process, a README, a worked example and two reference documents. It ships no executable scripts, test suite or benchmark results, and this listing makes no claim about measured outcomes or host-specific testing. Discovery is only as reliable as the skill listing or search capability your agent exposes.

    Skill Pack Manager gives guidance and verification only; it does not install, update or configure anything and does not replace invoking the skill you need. Discovery is only as reliable as the skill listing or search capability your agent exposes: when a host cannot enumerate skills, discovery is marked UNVERIFIED. It is written around the JetFerrari Agent Engineering stack and its four profiles and does not describe other skill collections. The package ships no executable checks, benchmarks or host-specific test results, and a successful activation on one prompt proves only that prompt.

    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 17 days ago

    Permissions

    No special permissions declared or detected

    Listed17 days ago

    What's inside

    Frequently Asked Questions

    It helps you work out which JetFerrari Agent Engineering skills your agent can load, which profile fits your work, and whether the skill you expect is really available. It returns a six-field report with discovery marked CONFIRMED or UNVERIFIED.

    No. It is guidance and verification only and does not install software or modify system configuration. The package describes skills as delivered through the marketplace or agent connection, so there is no local installer to run.

    Pick the smallest profile that covers your recurring work: core for implementation, debugging, review, continuity and orchestration, architecture for architecture, domain language and decision work, ui for frontend implementation and component selection, or full for every skill. If the right workflow is unclear, start with master-orchestrator.

    Discovery is then marked UNVERIFIED instead of guessed. You invoke the skill you need directly and observe whether it activates. If an expected skill is missing, name it by its canonical name and acquire or enable it through your marketplace.

    A SKILL.md-capable agent host that can list or search its available skills. The package contains five text files and declares no scripts, accounts or API keys.

    New in Prompt & Skill Engineering