LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
SkillRisingofficial publisher

React best practices (Vercel)

Skill : A reusable method: instructions, procedures, sometimes scripts or templates · requires claude-code

React and Next.js rules maintained by Vercel, read by the agent before coding.

The reference skill for clean React, maintained by the makers of Next.js.

Official site GitHub · 36,423 ★
Overall score
9.2 /10
Security: nothing to flag
Utility
8.0
Reliability
10.0
Security
No caveat on record
Ease
1 click · Beginner

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

When a coding agent generates React or Next.js code without precise instructions, it can produce poorly structured components, ignore Vercel conventions, or mix incompatible patterns. This skill provides a set of rules the agent reads before starting to code, reducing the need for manual corrections after generation.

In practice, the skill is installed via the npx skills add command and places a SKILL.md file in the target agent's directory. At each session, the agent consults this file to apply React and Next.js best practices maintained by Vercel. The content is purely textual, with no external code execution.

This skill is aimed at developers who use Claude Code, Cursor, or Codex to generate or refactor React and Next.js code, and who want the agent to follow Vercel conventions from the start without having to restate them in every prompt.

It is not suited to projects that do not use React or Next.js, nor to teams that already have their own style rules codified in another agent configuration system.

What it offers

  • ·Automatic injection of Vercel-maintained React and Next.js rules into the agent's context before each coding session.
  • ·One-command installation via npx skills add, with no additional dependencies to install.
  • ·Compatible with Claude Code, Cursor, and Codex, as well as more than 75 other agents supported by the skills ecosystem.
  • ·Installation available at project level (shared with the team via the repository) or at global level (available across all projects on the machine).
  • ·Skill updates in one command (npx skills update) to keep up with evolving Vercel recommendations.
  • ·Purely textual content: no external code is executed when the agent reads the skill.
  • ·Option to use the skill on a one-off basis without permanent installation using the npx skills use command.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
claude-code, cursor, codex
Host
claude-code
Licence
MIT
FR interface
No

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Maintenance
Active
Last release
19 October 2026

Links and repository checked on 25 October 2026 · added on 1 March 2026

How to install React best practices (Vercel)

1. Make sure Node.js is installed on your machine (npx is included with npm). 2. Open a terminal at the root of your project. 3. Run the command: npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices 4. Select the target agent (claude-code, cursor, or codex) when prompted, or specify it with -a claude-code. 5. Choose the symlink method (recommended) to make future updates easier. 6. The skill is active from the next session of your agent: no additional restart is required.
npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices

In the same category

Whole category Frame (methods, guardrails) →