More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    agensi preflight

    1

    Audit and package your AI agent skills against Agensi security and listing requirements before submission.

    $12

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    agensi preflight

    agensi preflight

    Example session with this skill installed

    I'm ready to submit my new git-automation skill. Can you check the folder at ./my-skill and make sure it's safe to upload?

    • Read your context and instructions
    • Compiled the agensi preflight

    Pre-flight result: NEEDS WORK

    Blockers: 2 Warnings: 1 Notes: 1

    [BLOCKER] 4. Secrets scripts/push.sh:2
    Possible live GitHub token
    [BLOCKER] 3. Dangerous scripts/push.sh:9
    Recursive delete of a root, home, or wildcard path
    [WARNING] 2. File types .DS_Store
    Junk or build artifact should be removed
    [NOTE ] Listing -
    Description does not say when the skill should trigger

    Fixed: removed .DS_Store. Rotate that GitHub
    token — deleting it from the file isn't enough.

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

    About this skill

    The problem

    Submitting a skill to the Agensi marketplace often results in a 24 to 48 hour wait only to face rejection due to minor security flags or formatting errors. Catching leaked secrets, dangerous commands, or malformed metadata manually is error-prone and slows down your distribution cycle.

    What it does

    • Performs an 8-point security audit covering secrets, dangerous commands, and network access.
    • Automatically strips junk files like .DS_Store, node_modules, and git history from the package.
    • Validates SKILL.md frontmatter and normalizes folder structures for marketplace compatibility.
    • Identifies potential prompt injection risks that could override host agent instructions.
    • Generates a marketplace-ready .zip file with the correct internal hierarchy.

    Frameworks & tools

    Python 3, YAML frontmatter, shell scripts, and standard Agensi skill packaging formats.

    Why this beats prompting it yourself

    Standard LLM prompts often miss obscured security risks or subtle packaging requirements. This skill uses a dedicated scanner to find exact strings and patterns that trigger marketplace rejection, providing a definitive pre-submission verdict rather than a guess.

    Use cases

    • Auditing a newly developed skill for hardcoded API keys before public release.
    • Cleaning up local development artifacts and junk files before zipping a package.
    • Fixing "No SKILL.md at root" errors that cause automated ingestion failures.
    • Optimizing marketplace listing descriptions and tags for better discoverability.

    Known limitations

    The scanner uses heuristics. Passing locally is a strong indicator of success but does not guarantee manual approval by Agensi reviewers.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skill Creator Skills.

    Scanner is heuristic. Prompt-injection detection is subjective and needs manual judgment. Does not guarantee marketplace approval — it’s an independent check covering the same eight areas, not the official scanner. Requires Python 3.8+.
    Documentation examples inside code fences are downgraded rather than blocked, with a # preflight: allow escape hatch. This means it won’t false-block a skill that legitimately documents dangerous patterns.

    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 3 months ago

    Permissions

    Terminal / Shell
    Write Files
    Read Files

    File Scopes

    **/*
    —

    Shell: the skill runs as a Python CLI. Read: scans the skill package the user specifies. Write: only creates the output zip when --package is passed. No network or environment access — the tool runs entirely offline, which matters since users are handing it unreleased work.

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill automates the pre-submission audit, scanning your project for hardcoded secrets, dangerous commands, and metadata errors that typically lead to marketplace rejection. It saves you the 24-48 hour wait time associated with failed manual reviews.

    It is designed specifically for the Agensi ecosystem and works with any skill regardless of the underlying LLM, provided it follows standard Agensi packaging structures. It validates Python-based scripts, YAML frontmatter, and standard shell command configurations.

    You receive the full preflight scanning utility, the automated packaging engine, and a set of templates to ensure your SKILL.md and folder hierarchy meet the marketplace's exact specifications.

    No, the skill performs its audit locally on your environment. It identifies risks like API key leaks and prompt injection vulnerabilities within your files before you ever upload them to the marketplace.

    While this skill checks against all publicly documented Agensi security flags and formatting rules, it cannot account for subjective manual reviews. It serves as a definitive technical validator, but human moderators still have the final say on content quality.

    Yes, the package includes the core auditing logic and the zipping utility. Once installed in your Agensi workspace, you can trigger it via simple commands to process your development directories.

    New in Agents & Orchestration