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|
Skillofficial publisher

Awesome CursorRules

Skill : A reusable method: instructions, procedures, sometimes scripts or templates · requires cursor

Community library of rule files by framework and language to guide Cursor.

The best free starting point: plain text files, worth reading before you adopt them.

Overall score
8.8 /10
Security: nothing to flag
Utility
8.0
Reliability
9.0
Security
No caveat on record
Ease
5 min · 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 using Cursor for coding, the editor has no knowledge of your project's specific conventions: chosen framework, naming style, preferred libraries, or security constraints. Without explicit instructions, it generates generic code that often requires repeated corrections.

Awesome CursorRules is a community repository that collects rule files in Markdown format (.mdc), organized by framework and language. These files are placed in the .cursor/rules/ folder of your project and tell Cursor how to behave: which architecture to follow, which libraries to prefer, which mistakes to avoid. Cursor reads these text files at each code generation.

This tool is aimed at developers who use Cursor daily and want the editor's suggestions to match their project's standards from the start, whether working alone or in a team. Rules shared in .cursor/rules/ allow all contributors to a project to benefit from the same instructions.

However, if you do not use Cursor as your code editor, this library will be of no use to you. It does not work with other editors or AI assistants.

What it offers

  • ·Library of .mdc files covering major frontend frameworks: Next.js, React, Vue 3, Svelte, SvelteKit, Solid.js, Angular, Astro, Qwik.
  • ·Rules for backend and full-stack environments, including Cloudflare Workers, Supabase, Vercel, and other common setups.
  • ·Dedicated files for mobile development, games, and graphics tools.
  • ·Specialized rules by language (TypeScript, Python, etc.) and domain (security, testing, documentation, database, API).
  • ·.mdc format based on Markdown, readable and editable without any special tool, compatible with Cursor's .cursor/rules/ folder.
  • ·Rules shareable among team members via the project's code repository, to align AI assistance on the same standards.
  • ·CC0 license: files are in the public domain, with no usage or attribution restrictions.
  • ·Advanced thematic rules, such as preventing Supabase authentication errors or handling TanStack Query v5 patterns.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
cursor
Host
cursor
Licence
CC0-1.0
FR interface
No

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 June 2024

How to install Awesome CursorRules

1. Go to the GitHub repository github.com/PatrickJS/awesome-cursorrules. 2. Browse the categories (Frontend, Backend, Language-Specific, Security, etc.) and identify the .mdc files suited to your project. 3. Read the content of the chosen file to verify it matches your configuration before using it. 4. Create the .cursor/rules/ folder at the root of your project if it does not already exist. 5. Copy the selected .mdc files into that folder. Cursor will read them automatically in your next interactions. 6. These files contain only Markdown text: no code is executed on your machine.
Copier le fichier choisi dans .cursor/rules/

In the same category

Whole category Frame (methods, guardrails) →