Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    SKILL.md Validator / Linter

    1

    Free, instruction-only SKILL.md validator/linter. Checks frontmatter, required sections, and common pitfalls. Returns PASS/REVISE/FAIL with fixes.

    Free

    5 uses5.0 (1 review)
    SKILL.md Validator / Linter

    SKILL.md Validator / Linter

    Example session with this skill installed

    validate skill at ./my-new-skill/SKILL.md

    • Read your context and instructions
    • Compiled the md validator linter

    I have completed the validation of the SKILL.md file located at ./my-new-skill/SKILL.md. The linter identified three issues that need to be addressed before the skill is considered compliant.

    SKILL.md Validation Report

    Verdict: REVISE

    IDSeverityFile:LineIssueFix
    FM01FAIL0:3Missing license key in frontmatterAdd license: MIT or preferred license.
    ST04WARN12:0Missing ## Examples sectionAdd a section with 2-3 usage examples.
    NM02FAIL0:2Name is not kebab-caseRename My New Skill to my-new-skill.
    SC01PASS-No secrets detectedNo action required.

    Checklist:

    • Frontmatter Parsed
    • Required Sections Present
    • Security Scan Completed
    • Naming Convention Met

    Next steps

    1. Update the frontmatter to include the missing license key and fix the skill name casing.
    2. Add a ## Examples section to provide clear usage context for developers.
    3. Re-run the validate skill command to confirm all checks pass.
    I have completed the validation of the SKILL.md

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

    About this skill

    Free, instruction-only SKILL.md validator/linter for agent skills. Checks frontmatter, required sections, consistency, and common pitfalls. Outputs a clear PASS/REVISE/FAIL verdict with concrete fixes.

    Heuristic linter only. Does not execute code or verify external URL availability. Treatment as a review aid, not a functional test.

    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

    5.0
    1 review
    5
    1
    4
    0
    3
    0
    2
    0
    1
    0

    This skill has been used 5 times.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Read Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The skl validator prevents deployment failures by ensuring your SKILL.md files strictly follow Agensi and OpenClaw standards, catching structural errors and security risks before you submit them to a marketplace.

    It is designed for seamless use within agentic IDEs like Claude Code, Cursor, and Windsurf, making it compatible with any workflow that supports Markdown-based skill definitions.

    No complex installation is required; simply point the validator to your SKILL.md file or directory within your preferred agentic environment to start the automated parsing process.

    Yes, the validator performs a security scan to identify hardcoded secrets, sensitive credentials, or suspicious commands that could lead to data exfiltration or unauthorized access.

    You will receive the instruction-based validator optimized for Agensi and OpenClaw specifications, along with documentation on how to interpret the PASS, WARN, and FAIL reports.

    The validator uses a deterministic heuristic approach to check structure and consistency, but it does not execute code or verify if external URLs are live.

    New in Prompt & Skill Engineering