Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    YAML Frontmatter Fixer

    1

    Fix broken SKILL.md frontmatter — colons, quotes, trailing commas, list syntax — and show a before/after for each fix.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    YAML Frontmatter Fixer

    YAML Frontmatter Fixer

    Example session with this skill installed

    Fix frontmatter in ./my-skill/SKILL.md

    • Read your context and instructions
    • Compiled the yaml frontmatter fixer
    Summary: 3 issues found, 3 fixed
    
    1. Unquoted value containing a colon (description)
       before: description: A validator: checks SKILL.md
       after:  description: "A validator: checks SKILL.md"
    
    2. Trailing comma in inline list (tags)
       before: tags: [linter, validator,]
       after:  tags: [linter, validator]
    
    3. Value parsed as a number (name)
       before: name: 1.2-thing
       after:  name: "1.2-thing"
    
    Corrected frontmatter:
    ---
    name: "1.2-thing"
    description: "A validator: checks SKILL.md"
    tags: [linter, validator]
    ---
    
    Run skl-validator to verify
    

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

    About this skill

    Why does your SKILL.md keep failing to load?

    Nine times out of ten it's the frontmatter. An unquoted colon, a trailing comma, a version that looks like a number — YAML is picky, and the error message rarely points at the culprit.

    json-frontmatter-fixer reads your frontmatter, finds the common breakages, and repairs them without changing meaning — then shows every fix as a before/after so you can trust it.

    What it fixes

    • Unquoted strings containing a colon (description: A validator: checks...)
    • Trailing commas in inline lists ([a, b,])
    • Values that parse as the wrong type (name: 1.2-thing)
    • Inconsistent list style and stray tabs

    What it returns

    • N issues found, N fixed
    • A before -> after snippet per fix
    • The corrected full SKILL.md
    • A reminder to run skl-validator to confirm

    A fast pass over common frontmatter errors. Instruction-only; nothing leaves your machine.

    Works with Claude Code, Cursor, Codex CLI, OpenCode, Gemini CLI, WindSurf.

    Heuristic-based. May not fix deeply nested invalid YAML or resolve ambiguous semantics. Requires triple-dash markers to isolate the frontmatter block.

    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 1 month ago

    Permissions

    Read Files
    Write Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill specifically targets and repairs syntax errors in SKILL.md YAML headers—such as unquoted colons or improper indentation—that often cause automated validation tools to fail during development.

    Yes, it is designed for seamless use within developer environments like CLAUDE_CODE, Cursor, and Windsurf, ensuring your skill files pass validator checks without manual editing.

    No, the skill uses strict extraction logic to isolate the YAML block, ensuring that your skill descriptions, instructions, and rules remain completely untouched during the repair process.

    The fixer uses heuristic-based logic to address common syntax violations; however, it cannot resolve semantic errors or extremely complex, deeply nested YAML structures where user intent is ambiguous.

    You will receive the full skill logic ready for integration into your AI environment, along with documentation on how to trigger the fix and interpret the change tracking reports.

    New in Prompt & Skill Engineering