More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Marketplace Listing Pipeline

    1

    Turn finished skills into complete marketplace listings: fields from source, real demos, media in one system, two-step API submit with race-guards, verified by fresh read.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Marketplace Listing Pipeline

    Marketplace Listing Pipeline

    Example session with this skill installed

    I have two finished skills to sell, an email subject line tester and a changelog writer. Neither is listed anywhere yet. I want both posted as paid listings with correct tags and media, and afterwards I want proof of what actually got submitted, not just "done."

    • Read your context and instructions
    • Compiled the marketplace listing pipeline

    Preflight: creator mode on, payouts connected, unfiltered listings read shows 0 live, so neither name collides. Category list fetched this session; tags copied from it, nothing from memory.

    Fields assembled per skill from its source file. Demo results produced by running each skill, not written from its description: the subject line tester scored 5 real subject lines for a product launch email and returned them ranked with reasons; the changelog writer turned 14 raw commit messages into a grouped, user-facing changelog. Both outputs pasted into the listings as the demos.

    Media: one logo per skill (same panel system, different monogram and accent), three screenshot cards each (demo, use cases, what's inside with real section headings and word counts). Contact sheet review caught the changelog listing's title clipping on card 1; shortened before submit.

    Submit, one at a time, two steps each. Skill 1: preview read field by field against the listing file, price and tags match, 3 screenshots attached; race-guard re-read shows no duplicate; confirmed. Skill 2: same loop; the preview shows the FAQ field empty, so the FAQs are sent alongside the draft ID on the confirm call instead of re-uploading the package.

    Final verification from a fresh listings read: 2 listings present, both status in review, security scan passed on both, zero warnings recorded in the state file. Reported as in review, not live, because that is what the marketplace says. State file holds both draft IDs, listing URLs, and confirm results for audit.

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

    About this skill

    This skill publishes agent skills to an MCP- or API-driven marketplace as complete, review-ready listings. It starts with preflight reads (creator status, payouts, an unfiltered read of your existing listings so nothing gets duplicated), then assembles every listing field from the source material: name, summary, description, a real demo, compatibility, price, tags copied from the marketplace's live category list, keywords, use cases, permissions, limitations, and FAQs.

    It generates the logo and screenshot cards in one consistent visual system and checks them on a contact sheet before anything is submitted. Submissions run in two steps, preview draft first, then confirm, with a race-guard re-read of your live listings immediately before every confirm, because a timed-out submit can still have landed. A state file records draft IDs, URLs, and warnings for the whole batch.

    It finishes by verifying the end state from a fresh listings read, not from submit receipts, and reports each item's real status, in review versus live, plainly.

    This skill publishes listings; it does not write or improve the skills themselves. It cannot finish drafts that exist only in a marketplace's web dashboard, and it cannot control review outcomes or timelines: a submitted listing is in review until the marketplace approves it. Marketplace field names and tag lists change, so the pipeline re-fetches them each run rather than guaranteeing a specific platform's current shape.

    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 24 days ago

    Permissions

    No special permissions declared or detected

    Listed24 days ago
    Updated21 days ago

    What's inside

    Frequently Asked Questions

    Yes. The pipeline assembles listing fields from your source files and produces the demo by running the skill. A half-written skill produces a half-filled listing, and the readiness rubric will block it.

    Names are unique platform-wide. The preview fails with a duplicate-name error and creates nothing. The fix is a new listing name; your skill content does not change.

    No. It is built for MCP- or API-driven submission. Dashboard-only flows need manual submission, though the listing field template and readiness rubric still apply to what you type in.

    New in Workflow Automation