DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to write and share a new agent skill with Skills

Generate a skill template and edit its SKILL.md with instructions for your agent.

Authorization notice. Skills is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forA developer or team lead who has a repeated task, such as a review checklist, and wants a coding agent to follow the same steps each time.

The problemTeaching a coding agent a repeatable workflow in each chat session wastes time and produces inconsistent results.

The outcomeYou have a generated skill folder with a SKILL.md file that holds your instructions, ready to edit and share.

What you need first

  • Node.js 22.20 or later
  • A terminal opened in your project folder
  • A supported coding agent installed on your machine, such as Claude Code, Codex, or Cursor

Steps

  1. Run npx skills init my-skill in the folder where you want the new skill.
  2. Open the generated SKILL.md and write the instructions your agent should follow.
  3. Read docs/creating-skills.md in the repository for the frontmatter format and discovery rules.
  4. Install the skill locally with npx skills add to test it before sharing.

Prompt for your agent

Run npx skills init <skill name> from the vercel-labs/skills CLI, then fill in the generated SKILL.md with instructions for <task>. Report the path of the SKILL.md file and confirm the frontmatter follows the format in docs/creating-skills.md.

Caveat. The README points to docs/creating-skills.md for the format and discovery rules, so check those details there before publishing a skill.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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