Skip to content

Agent Skill

writing-guidelines

Published by Vercel Labs · MIT (stated in the repository README)

Reviews documentation and prose against the Vercel writing handbook's structure, voice and code-sample rules.

Verified
Claude Code
Cursor
Open source
View official sourceLast verified Nov 15, 2026

How it works

The writing-guidelines skill audits documentation against Vercel's writing handbook: content type and structure, voice and tone, headings, lists, code samples, placeholders, units, typography and pricing pages. It is a style reviewer rather than a copywriter, so it points out where a page breaks conventions instead of quietly rewriting it. That is useful for documentation teams that want consistency across many contributors. The handbook reflects one company's preferences, so adopt the rules deliberately rather than treating every suggestion as a universal standard.

Features and capabilities

  • Check structure and voice
  • Review code samples and formatting
  • Flag typography issues
  • Apply content-type conventions

Primary use cases

  • Documentation style review
  • Docs contribution checks
  • Consistency across pages
  • Pre-publication proofread

Installation and setup

npx skills add vercel-labs/agent-skills

Other agents (open Agent Skills standard): the same folder loads by copying it into the host's skills directory — Codex reads .agents/skills in a repository or ~/.agents/skills; Cursor reads .agents/skills or .cursor/skills and also reads .claude/skills; the ChatGPT desktop app installs skills through its Skills panel, while ChatGPT on the web and mobile only loads skills packaged in a plugin. The installer above is what Vercel documents; setup and requirements differ per host.

Setup instructions are reproduced from the publisher. Explore4.ai never installs or executes a third-party skill on your behalf.

Requirements

An AI coding agent that supports the Agent Skills format, such as Claude Code or Cursor. The repository documents support for AI coding agents including Claude Code, Cursor and Copilot.

Licence, pricing and security

License
MIT (stated in the repository README)
Pricing
Free — Free to use. Running it needs an AI coding agent that supports the Agent Skills format.
Security review
Not reviewedSource verification is recorded separately from any security assessment.
Security notes
No independent security review is published for this skill. Its instructions and scripts are public in Vercel Labs' repository; read them before use and grant only the access the task needs.

Compatible AI Agents

Only the agents and platforms the publisher documents as supported are listed here.

Related AI tools

Tools that commonly host or pair with this kind of capability.