Skill Inspector & Certifier

    1

    Before zipping and submitting to any marketplace — run this inspector.

    $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 CLIMuseMuseDotsDots+21 more

    Skill Inspector & Certifier

    Example session with this skill installed

    Run the inspector on my directory ./weather-agent and check for Agensi marketplace compliance. Show me the certificate score.

    • Read your context and instructions
    • Compiled the inspector & certifier
    • Generated the document

    The inspector has completed the scan of the weather-agent directory. Below is the detailed validation report and compliance score.

    Skill Inspection Report

    [SKILL INSPECTOR] weather-agent/
    ═══════════════════════════════════════════════
    SKILL.md ............ FOUND ✓
    Frontmatter ......... VALID ✓
    Required fields ..... ALL PRESENT ✓
    Body length ......... 845 chars (min 200) ✓
    File references ..... 2/2 RESOLVED ✓
    Package size ........ 45 KB (limit 3 MB) ✓
    Directory depth ..... 1 level ✓
    Junk files .......... NONE ✓
    Sensitive wording ... CLEAN ✓
    ═══════════════════════════════════════════════
    CERTIFICATE SCORE: 100/100 ✓
    STATUS: READY TO PUBLISH
    ═══════════════════════════════════════════════

    The package meets all 14 validation rules. No dangling references or hardcoded credentials were detected. The metadata includes all required fields for the Agensi marketplace, including localized descriptions and correct category mapping.

    Next steps

    • Zip the directory using zip -r weather-agent.zip ./weather-agent.
    • Upload the generated zip file to the Agensi developer portal.
    • Keep the inspection log for your records in case of manual review queries.

    weather-agent.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

    What it does

    You just wrote a SKILL.md. Before zipping and submitting to any marketplace — run this inspector. 14 validation rules output a certificate score with itemized fixes.

    14 Rules Checked

    • SKILL.md exists at package root
    • Frontmatter valid YAML
    • All required fields present (name, version, display_name, description, author, category)
    • Body length minimum (200 chars)
    • Zero dangling file references (scripts/, references/, assets/)
    • No hardcoded credentials (Stripe keys, AWS keys, passwords, API secrets)
    • Package size within limits (3 MB)
    • Directory depth within limits (max 2 levels)
    • No junk files (.git, node_modules, pycache)
    • No sensitive / red-line wording
    • Version follows semver (X.Y.Z)
    • name field is kebab-case
    • No external URLs in code blocks
    • Values with special characters properly quoted

    Usage

    python skill_inspect.py ./my-skill-folder
    python skill_inspect.py ./my-skill.zip --format json
    python skill_inspect.py ./skill --market agensi
    

    Zero Dependencies

    Pure Python stdlib. No pip install needed. Works on Windows, macOS, Linux.

    Requires a local Python environment. Auto-fix creates a new copy rather than modifying the original. Package size limit is fixed at 3MB.

    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 14 days ago

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed14 days ago

    What's inside

    Frequently Asked Questions

    This tool eliminates 'parse failed' rejections by scanning for YAML syntax errors, missing file references, and security risks before you submit. It ensures your SKILL.md package meets all standardized marketplace requirements in seconds rather than waiting days for manual review.

    It is fully compatible with the SKILL.md and Anthropic Skill standards, featuring specific validation profiles for major platforms like Agensi, Coze, WorkBuddy, and SquidBay. You can toggle between these standards using the --market flag to ensure compliance with your specific target platform.

    Unlike a text-based LLM prompt, this tool performs programmatic file-system checks to identify hidden directory depth and dangling pointers. It provides 100% accuracy on package size and path resolution that a chat interface simply cannot verify visually.

    Yes, the inspector can export results in JSON format, allowing you to integrate it directly into your GitHub Actions or Jenkins workflows. This enables your team to automatically enforce packaging standards and security audits on every commit.

    The 'auto-fix' feature automatically corrects common structural issues like unquoted YAML values and removes junk files like node_modules or .DS_Store. For safety, it creates a cleaned copy of your package rather than modifying your original source files.

    You will receive the full Python-based inspector tool, documentation for all 14 standardized validation rules, and specialized configuration profiles for the leading agent marketplaces. All updates to the SKILL.md standard are included to ensure your validator remains current.

    New in Prompt & Skill Engineering