Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    AI Skill Quality Gate

    2

    Run a buyer-readiness check before you publish an AI agent skill. PASS/WARN/FAIL on structure, claims, secrets, and listing clarity.

    Free

    3 usesSecurity scanned
    AI Skill Quality Gate

    AI Skill Quality Gate

    Example session with this skill installed

    Run a quality gate audit on my 'jira-automation-pro' skill package before I upload it to the marketplace.

    • Read your context and instructions
    • Compiled the ai quality gate

    Skill Quality Gate

    Status: WARN

    Painpoint: Manual Jira ticket updates
    Buyer: Project Managers
    Primary output: Automated ticket transitions

    Findings

    • [CRITICAL] Hardcoded API token found in config.json
    • [WARN] Missing demo fixture data

    Must fix

    • Remove secrets! Use ENV vars.
    Hardcoded API token found in config.json

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

    About this skill

    Static pre-publish review for SKILL.md packages. Flags unclear triggers, missing examples, local-only paths, secrets, and overclaimed security/compliance wording. Outputs a PASS/WARN/FAIL report with must-fix items.

    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.

    This is a static review aid, not a certification tool. It does not guarantee marketplace approval, buyer adoption, security, compliance, production readiness, or implementation correctness.

    Results depend on the files and context provided to the reviewing model. It may miss issues that are hidden outside the inspected package, depend on private runtime behavior, or require executing the skill in a specific environment.

    The package is designed to surface likely readiness issues, unclear claims, missing documentation, and buyer-facing gaps before publication. Final review and publishing decisions remain with the operator.

    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

    3 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 15 days ago

    • Free with an Agensi account

    Permissions

    File Scopes

    **/SKILL.md
    **/*.md
    **/*.json
    **/examples/**
    **/docs/**
    **/tests/**
    **/package.json
    **/pyproject.toml
    **/README*

    None. This skill does not require external network access or connect to external hosts.

    Listed5 months ago
    Updated15 days ago

    What's inside

    Frequently Asked Questions

    This skill acts as a pre-submission audit, identifying common pitfalls like unclear triggers, risky file references, and overpromised claims that often lead to marketplace rejection or poor user experiences. It saves you time by providing a structured report of must-fix items before you hit upload.

    The workflow is designed to be platform-agnostic, meaning it can review skill documentation and instruction files intended for any major AI agent framework or marketplace ecosystem. It focuses on the linguistic, structural, and logical readiness of your package.

    You will receive a complete review workflow package, including the core quality-gate instructions, structured report templates for PASS/WARN/FAIL assessments, and a guide for generating claim-safe listing descriptions.

    No, this is a static review tool. While it scans for risks like local file paths and sensitive strings in your documentation, it is not a sandbox execution environment and does not perform active security or compliance certification.

    Simply import the workflow into your preferred LLM environment and provide it with your skill's instruction files, documentation, and draft listing text. The agent will then process the materials against its proprietary review criteria.

    Minor updates and refinements to the review criteria are included with your purchase. For major version releases that align with new industry standards or marketplace policy changes, check the 'Updates' section of the listing for eligibility.

    New in Agents & Orchestration

    Free