Marketplace skill packager

    1

    Standardizes, scrubs, and packages AI skills into production-ready zips for marketplaces and GitHub directories.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Marketplace skill packager

    Example session with this skill installed

    I have a skill that generates Kubernetes manifests. The files are SKILL.md and a python helper called k8s_gen.py. Package this for Agensi and draft the listing copy.

    • Read your context and instructions
    • Compiled the marketplace packager

    I have audited your files, scrubbed potential secrets, and prepared the packaging structure. The SKILL.md frontmatter is valid, and the helper script uses relative paths.

    Marketplace Listing Draft

    FieldValue
    TitleK8s Manifest Architect
    Value PropAutomate the creation of production-ready Kubernetes manifests with built-in best practices for security and resource limits.
    Categorydevops-cloud
    Tagsdevops, kubernetes, k8s, yaml, infrastructure-as-code
    Price Band$20–50 (Deep Expertise)

    Package Structure

    k8s-manifest-architect/
    ├── SKILL.md (Validated frontmatter + body)
    └── k8s_gen.py (Relative path verified)
    

    Next steps

    1. Review the generated listing copy for tone alignment.
    2. Run the final zip -r k8s-manifest-architect.zip k8s-manifest-architect/ command.
    3. Upload the zip to the Agensi Creator Dashboard.
    secrets, and prepared the packaging structure. The SKILL.md

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

    About this skill

    Packaging an AI skill for distribution often fails due to improper formatting, leaked secrets, or messy file structures. This skill enforces the exact standards required by Agensi, SkillHQ, and GitHub skill directories to ensure your product passes review.

    What it does

    • Frontmatter validation ensures the SKILL.md contains the mandatory YAML name and one-line description.
    • Safety scanning greps for API keys, private keys, emails, and internal hostnames to prevent accidental data leaks.
    • Dependency auditing verifies helper scripts use relative paths and excludes sensitive files like .env or local keys.
    • Package optimization structures the folder and zip file correctly to avoid nested directory errors during installation.
    • Listing generation produces a title, value proposition, and recommended price band for the marketplace dashboard.

    How it works

    1. Audit phase where the agent inspects the SKILL.md body for imperative steps and strips forbidden patterns like prompt injection or destructive commands.
    2. Helper verification to ensure all referenced scripts are present and correctly linked via relative paths.
    3. Secret scrub to identify and remove any hardcoded credentials or internal infrastructure references.
    4. Packaging to build the final zip folder using the skill slug naming convention.

    Frameworks & tools

    Works with any text-based AI skill files, specifically targeting Agensi Creator Dashboard, SkillHQ publish workflows, and skills.sh GitHub repositories.

    Why this beats prompting it yourself

    Manual packaging often leads to rejection because of hidden Mac OS metadata files, missing frontmatter, or absolute file paths that break on the buyer's machine. This skill automates the compliance check against marketplace-specific rules so you can ship without back-and-forth edits.

    Use cases

    • Preparing a prompt-based skill for sale on the Agensi marketplace.
    • Auditing a repository for secrets before pushing to a public GitHub skill directory.
    • Generating the marketing copy and pricing strategy for a new developer tool.

    Known limitations

    Does not perform functional testing of the prompt logic itself, only structural and safety compliance for packaging.

    Source: https://github.com/fei36bot/agent-skills-pack

    Focuses on structural packaging and safety; does not validate the functional performance or accuracy of the skill's logic.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 14 days ago

    • Free with an Agensi account

    Permissions

    Read Files
    Listed14 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the compliance process by validating frontmatter, scrubbing sensitive data like API keys, and structuring folders to meet the strict technical standards of platforms like Agensi and SkillHQ.

    The packager is compatible with any text-based AI skill files and is optimized for the Agensi Creator Dashboard, SkillHQ workflows, and skills.sh GitHub repositories.

    No, the packager focuses on structural integrity, security, and marketplace compliance; it does not test the effectiveness or logic of the actual prompt instructions.

    You will receive the standard packaging agent, along with a listing generation tool that suggests optimized titles, value propositions, and price bands for your marketplace submission.

    The skill scans for common sensitive patterns including API keys, private keys, personal emails, and internal hostnames, prompting you to remove them before packaging.

    The tool automatically identifies and flags absolute file paths, ensuring all helper scripts use relative paths so they function correctly on a buyer's local machine.

    New in Prompt & Skill Engineering