Agensi Skill Packaging & Marketplace Listing

    1

    Get a finished Agent Skill through Agensi's security scan and listed cleanly — without leaking your method.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Agensi Skill Packaging & Marketplace Listing

    Example session with this skill installed

    I have a Python-based research skill in folder ./skills/deep-research. I need to package it for Agensi, set a $25 price, and ensure I don't leak the router logic in the listing.

    • Read your context and instructions
    • Compiled the agensi packaging
    • Generated the document

    The packaging process for deep-research is complete. I have staged the metadata, generated the sanitized listing, and verified the folder structure against the 8-point security scan.

    Agensi Submission Package: deep-research

    TaskStatusResult
    Metadata StagingSuccessHomepage set to neutral repo; Price staged at 25
    Security AuditPassedNo `curl
    Listing GenerationCompleteCreated agensi-listing.md (Sanitized)
    Archive BuildSuccessdist/deep-research.zip generated via manifest

    Staged Listing Preview (Summary)

    Name: Deep Research Pro
    Summary: Automated multi-source market analysis and competitor intelligence.
    Permissions: internet-access, filesystem-read
    Security Note: All shell interactions are advisory; no destructive commands included.

    Package Manifest

    deep-research.zip
    ├── SKILL.md
    ├── LICENSE.txt
    ├── references/
    │   └── data-sources.md
    └── scripts/
        └── parse_results.py
    

    Next steps

    1. Run unzip -l dist/deep-research.zip to perform a final manual manifest check.
    2. Copy the content from agensi-listing.md into the Agensi Creator Dashboard "List a Skill" form.
    3. Upload the ZIP file and submit for manual review.

    deep-research.zip

    PDF · document

    Generated

    Example file from a real run - the skill writes it into your workspace.

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

    About this skill

    You've finished an Agent Skill and want it on the Agensi marketplace — passing the automated security scan on the first try and listed in a way that sells without handing competitors your method. This skill is the packaging and listing advisor for exactly that. You bring a finished skill folder; it gets the folder upload-ready and tells you what to fix before you submit.

    It neutralizes marketplace-specific metadata so a rival storefront's fingerprints don't ship inside the buyer's download, resolves the license so it travels with the archive, and screens the skill body against the platform's automated checks so you learn about a flag before the reviewer does. It also shapes the listing copy — name, summary, description, tags, pricing, permissions, FAQ — to say what the skill does and when to use it, never how it works internally.

    It ships a deterministic packager that builds the zip from an explicit file list and prints the manifest plus a local pre-flight report, so no .git, .env, or stray files sneak in. Honest limits: it does not author the skill's substance — bring a finished skill. The local pre-flight mirrors the platform's published criteria but does not replace the real automated scan and manual review on upload. Marketplace forms change, so it flags which fields must be confirmed against the live submission form rather than assumed.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.

    Does not author skill substance. Requires the skill logic to be pre-written. Focuses on Agensi-specific packaging and compliance rather than general development.

    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 buying a skill.

    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 1 month ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    Advisory guidance plus one local packaging script (bash + zip). It reads the skill folder you point it at and writes an upload-ready .zip archive plus a local pre-flight scan report to an output directory you choose; it works from a staging copy and does not mutate your source folder. No network requests, no secrets, no destructive commands.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    No, bring a finished skill folder. This gets it packaged, screened, and listed; it does not author the skill's substance. Author the skill first, then use this to ship it.

    No. It runs a local pre-flight that mirrors the platform's published criteria and fixes the usual triggers, but the real automated scan and manual review happen on upload.

    A shell with bash and zip. The packaging script reads your skill folder and writes an upload-ready archive plus a local report; it makes no network calls and doesn't touch your source folder.

    It shapes the public listing copy to say what your skill does and when to use it, never how it works internally, so the description doesn't hand competitors your approach.

    Yes. Neutralizing another storefront's metadata and license references so they don't ship inside the buyer's download is a core step.

    No, you set the real price on the submission form. It advises on a price band and makes sure a placeholder price inside the zip doesn't misrepresent a paid listing.

    New in LLM Ops