Vercel Labs Agent Skills — Skill-Authoring Template
One of the most-copied skill-authoring references: a full SKILL.md skeleton (How It Works / Usage / Output / Present Results /…
- Type
- CLAUDE.md Example
- Repository
- vercel-labs/agent-skills
- GitHub stars
- 31.6k
- License
- Not declared
- Repo last updated
- Aug 28, 2026
- Source file
- AGENTS.md
What Vercel Labs Agent Skills — Skill-Authoring Template is
Vercel Labs Agent Skills — Skill-Authoring Template is a claude.md example published in the vercel-labs/agent-skills repository on GitHub, which has about 31.6k stars. The repository describes itself as: “Vercel's official collection of agent skills”
A CLAUDE.md file holds standing instructions that Claude Code reads at the start of every session in a project, such as conventions, commands, and rules. Examples like Vercel Labs Agent Skills — Skill-Authoring Template show how other teams structure theirs.
In Claude Cowork, the equivalent places for this kind of guidance are your global instructions, project instructions, and folder instructions.
How to install Vercel Labs Agent Skills — Skill-Authoring Template
Claude Code
- Copy the parts that fit your project into CLAUDE.md at the project root, or into ~/.claude/CLAUDE.md for rules that apply everywhere.
- Keep it short and specific; remove anything that doesn't match how your team works.
Claude Cowork
- Put personal rules in Settings → Instructions for Claude (global instructions).
- Put project or folder rules in the project's instructions or the folder instructions for that directory.
New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.
Inside the source file
The repository does not declare an open-source license, so we list only the outline of the file here. Read the full text on GitHub.
- Repository Overview
- Creating a New Skill
- Directory Structure
- Naming Conventions
- SKILL.md Format
- Best Practices for Context Efficiency
- Script Requirements
- End-User Installation
Before you install
- Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
- Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
- Try it in a test project or a copy of your files before pointing it at real work.
- Pin the version you tested, and review changes before updating.
- Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.
FAQ
What is Vercel Labs Agent Skills — Skill-Authoring Template?
Vercel Labs Agent Skills — Skill-Authoring Template is a claude.md example for Claude Code and Claude Cowork from the vercel-labs/agent-skills repository on GitHub. One of the most-copied skill-authoring references: a full SKILL.md skeleton (How It Works / Usage / Output / Present Results /…
How do I install Vercel Labs Agent Skills — Skill-Authoring Template in Claude Code?
Copy the parts that fit your project into CLAUDE.md at the project root, or into ~/.claude/CLAUDE.md for rules that apply everywhere. Keep it short and specific; remove anything that doesn't match how your team works.
Can I use Vercel Labs Agent Skills — Skill-Authoring Template in Claude Cowork?
Put personal rules in Settings → Instructions for Claude (global instructions). Put project or folder rules in the project's instructions or the folder instructions for that directory.
Is Vercel Labs Agent Skills — Skill-Authoring Template safe to install?
It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.
Similar resources
- Vercel React Best Practices React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or… Skill · vercel-labs/agent-skills
- Beads — Deliberately Short Entry Point A model of restraint: the file opens by stating it is intentionally short, links the canonical AGENTS.md / instructions / architecture… CLAUDE.md Example · gastownhall/beads
- Ponytail — Lazy Senior Dev Persona A persona file that is actually a decision procedure: the 'lazy senior dev' framing resolves into a concrete 7-rung ladder (YAGNI → reuse… CLAUDE.md Example · DietrichGebert/ponytail
- SwiftUI Agent Skill — Scoping What NOT to Include A rare example that spends most of its length defining boundaries: what the skill must exclude (architecture opinions, formatting, tool… CLAUDE.md Example · AvdLee/SwiftUI-Agent-Skill
- Supabase Agent Skills — Symlinked Config + Task Runner Shows the pragmatic way to serve multiple agents from one file — CLAUDE.md is a symlink to AGENTS.md, noted up front — and routes all… CLAUDE.md Example · supabase/agent-skills
- Tiger pg-aiguide — MCP Server Code Style Guide A tight, transferable style guide for a TypeScript MCP server: ESM with .js import extensions, zod for tool-input validation, and the… CLAUDE.md Example · timescale/pg-aiguide
- Callstack Agent Skills — Quick Checklist & 'Good Skill' Rubric Distills skill authoring to a numbered quick checklist plus a 'What Makes a Good Skill' rubric (concise, third-person description… CLAUDE.md Example · callstackincubator/agent-skills
- cc-safety-net — TypeScript Style Guide with Good/Bad Pairs The clearest way to express code conventions to an agent: every rule (inline single-use vars, no unnecessary destructuring, early returns… CLAUDE.md Example · kenryu42/cc-safety-net