DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to lint a SKILL.md file before you share it with Skillmd

Run the same checks the registry uses and fix format problems before a skill goes public.

Who it is forA skill author who has written a new SKILL.md and wants to confirm it follows the format before sharing it with teammates or the registry.

The problemFormat mistakes in frontmatter or instructions can make a skill fail to load or fail publish checks, and the author has no quick way to see them.

The outcomeA list of diagnostics, a 0 to 100 quality score, and optional automatic fixes for mechanical issues.

What you need first

  • Node.js with npm, since the README uses npm and npx commands
  • A terminal on your machine or in CI
  • A skill folder containing a SKILL.md file (for lint and publish use cases)
  • A skillmd.com account and token (only for publishing)

Steps

  1. Install the tools with npm i -g skillmds, or skip the install and use the npx form below.
  2. Run npx skillmds lint ./my-skill on the folder that contains your SKILL.md.
  3. Read the diagnostics and quality score, then run skillmd lint . --fix to apply the mechanical fixes. (inferred, check the README)
  4. Run skillmd lint . --strict so warnings also fail the check before you share the skill.

Prompt for your agent

Use the skillmds repo to lint the skill at <path-to-skill-folder> by running `skillmd lint <path-to-skill-folder>`. Return the diagnostics and the 0 to 100 quality score. Verify that the command exits without errors before reporting the result.

Caveat. The lint engine checks the SKILL.md format and rules only; the README does not say it judges whether the skill's instructions are good or correct.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page