writing-guidelines (Vercel): a Claude skill that reviews docs against a writing handbook

Vercel's writing-guidelines skill has Claude review your docs and prose against Vercel's Writing Guidelines and list findings as file:line.

Installs: 114.3K; on skills.sh
Stars: 33.4K; on GitHub
Updated: Oct 2026; last repo commit

writing-guidelines is a small review skill from Vercel. You give Claude a file or pattern, Claude fetches the latest Writing Guidelines, reads your files, checks them against every rule and prints findings in a terse file:line format.

It loads when you ask to review docs, check writing style, audit prose or check a page against the writing handbook. The rules are not stored in the skill. Claude fetches them from a GitHub URL on every review, so it needs web access.

Good for

Docs writers who want a style check before publishing
Teams reviewing README and handbook changes in pull requests
Anyone auditing prose voice and tone across a folder of files

Install writing-guidelines

Claude Code

Copy this prompt.

Install the writing-guidelines skill in Claude Code. Run this command:

npx skills add https://github.com/vercel-labs/agent-skills --skill writing-guidelines

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

From its listing on skills.sh. Source.

What's in the skill

When it loads

Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".

Sections in SKILL.md

How It Works
Guidelines Source
Usage

Key facts

Author: Vercel
Repo: vercel-labs/agent-skills
Skill folder: skills/writing-guidelines
skills.sh installs: 114,325
Repo stars: 33,354
License: Not recorded
Last repo commit: 2026-10-28
Bundled files: SKILL.md only
skills.sh audits: Gen Agent Trust Hub: pass; Socket: pass; Snyk: warn

What it includes

Download command.md from vercel-labs/writing-guidelines on GitHub each review
Uses WebFetch to get the latest rules and the output format.
Network · Fetch the guidelines
Read the file or pattern you gave; ask you if none was given
Files · Read the files
Apply every fetched rule and print findings as file:line
Read · Check and report

From the official docs

Permissions

Low risk

The skill reads your files and pulls its review rules from a remote URL each time, so the rules can change without you updating the skill.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

The rules come from a URL, not the skill
Claude follows whatever the fetched file says. If you need stable results, pin a copy of the guidelines in your repo and review against that.

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	No read-only switch. SKILL.md only tells Claude to read files and report findings.
Talks to	raw.githubusercontent.com/vercel-labs/writing-guidelines (rules fetched each review)
Sign-in and keys	No account or key is named in SKILL.md.
Scopes	Reads the files or patterns you name Fetches rules from raw.githubusercontent.com

Questions

What does writing-guidelines do?

It reviews files you name for compliance with Vercel's Writing Guidelines and prints findings in a terse file:line format.

How do I install writing-guidelines in Claude Code, Claude or Codex?

Use the install box at the top of the page and pick Claude Code, Claude or Codex. Claude Code and Codex read skills from a folder on your machine. In the Claude app you upload the skill folder as a zip.

Where do the rules come from?

Claude fetches them from a raw GitHub file in the vercel-labs/writing-guidelines repo before each review, so you always get the current version. The rules are not inside the skill.

Does it need an API key?

No key is named. It needs web access to fetch the guidelines.

Does it rewrite my text?

SKILL.md only says to output findings. It does not tell Claude to edit your files.

Is it safe to use?

It bundles no scripts. It reads the files you name and fetches instructions from a URL. Because those rules can change on the remote side, glance at the findings before you act on them.

Information

updated Nov 2, 2026

Repository: vercel-labs/agent-skills
Folder: skills/writing-guidelines

vercel-labs/agent-skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 2

writing-guidelines SKILL.md · github.com
writing-guidelines on skills.sh · skills.sh