Skills vercel-labs/agent-skills
writing-guidelines
- Use it when
- you want docs or other prose checked against Vercel's writing handbook
- It does
- fetches the latest rules from Vercel's writing-guidelines repo, then reviews the files you name against every one
- You get
- terse findings grouped by file, each at a clickable file:line
- Unlike web-design-guidelines
- which runs the same kind of review on UI code
- Needs
- web access, since the rules are fetched fresh before each review
TLDR
The skill itself is a short wrapper: the rules live in Vercel's separate writing-guidelines repo, and the agent fetches them before every review, so they can change between runs. You name a file or pattern, or it asks which files. In October 2026 the rules covered planning each page and declaring its type (tutorial, how-to, reference and so on), active voice and addressing the reader as "you", banned words such as easy, simple and just, vague claims to replace with figures, and signs of AI-written prose such as recap transitions and choppy fragments. They also covered sentence-case headings, code blocks of at most 25 lines with a language tag, snake_case placeholders, units written as 64 KB, and no em dashes. Many rules are specific to Vercel's docs, such as its metadata fields and components, so it fits docs that follow Vercel's conventions best. It reports each issue and where it is, explaining only when the fix isn't obvious.
Summarizes the skill at 063bee9.
npx skills add https://github.com/vercel-labs/agent-skills --skill writing-guidelinesskills.sh page · Source on GitHub · All skills from vercel-labs/agent-skills
- Installs
- 71,904 on skills.sh, Sep 21, 2026
- Repo stars
- 31,405 vercel-labs/agent-skills
- First seen
- Jun 1, 2026 on skills.sh
Weekly values
| Week to | Installs |
|---|---|
| Aug 3 | 3,454 |
| Aug 10 | 3,560 |
| Aug 17 | 3,724 |
| Aug 24 | 4,573 |
| Aug 31 | 5,872 |
| Sep 7 | 4,637 |
| Sep 14 | 4,404 |
| Sep 21 | 6,285 |
| Category |
Articles, docs, internal comms, research write-ups and prose that doesn't read as generated. |
|---|---|
| Type |
A multi-step process the agent follows: interview, debug, run a TDD loop, review. |
| Effect |
Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code. |
| Needs |
Instructions only. Works in any agent that supports skills. |
| Publisher |
A verified publisher on its registry (skills.sh, ClawHub or Tencent SkillHub), or the company or maintainer behind the product the skill operates. |
| Topics |
SKILL.md
From vercel-labs/agent-skills at 063bee9. Checked daily, last changed Oct 20, 2026.
Frontmatter
name: writing-guidelines
description: 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".
metadata:
author: vercel
version: "1.0.0"
argument-hint: <file-or-pattern>Writing Guidelines
Review files for compliance with Writing Guidelines.
How It Works
- Fetch the latest guidelines from the source URL below
- Read the specified files (or prompt user for files/pattern)
- Check against all rules in the fetched guidelines
- Output findings in the terse
file:lineformat
Guidelines Source
Fetch fresh guidelines before each review:
https://raw.githubusercontent.com/vercel-labs/writing-guidelines/main/command.md
Use WebFetch to retrieve the latest rules. The fetched content contains all the rules and output format instructions.
Usage
When a user provides a file or pattern argument:
- Fetch guidelines from the source URL above
- Read the specified files
- Apply all rules from the fetched guidelines
- Output findings using the format specified in the guidelines
If no files specified, ask the user which files to review.