Reading
Explore how ColmoCode unifies the development experience across Antigravity, Claude Code, Cursor, and Codex CLI through 110+ UI/UX skills, 10 super workflows, and custom agent rules
Section 01
ColmoCode (original title: colmocode) is an open-source project by nberezniker, released on GitHub on 2026-06-06 (link: https://github.com/nberezniker/colmocode). It solves the experience fragmentation of AI programming tools (Antigravity, Claude Code, Cursor, Codex CLI) by unifying them via 110+ UI/UX skills, 10 super workflows, and custom agent rules, enabling "learn once, apply anywhere" for developers.
Section 02
With the proliferation of AI programming assistants (Claude Code, Cursor, Codex CLI, Antigravity), developers face experience fragmentation when switching tools. ColmoCode's core idea is to abstract best practices into reusable skills and rules, allowing developers to get consistent high-quality AI assistance across supported platforms without worrying about underlying tool specifics.
Section 03
ColmoCode has a library of over 110 structured UI/UX and product design skills, including Taste Skill (aesthetic cultivation), Refactoring UI, Hooked UX (user retention), Design Sprint, Interface Design, etc. These skills are optimized for AI agents—when a task like "optimize this login page" is given, relevant skills (e.g., Interface Design + Conversion Booster) are auto-loaded to generate professional solutions.
Section 04
ColmoCode provides 10 pre-defined "super workflows" (Superpowers) in the workflows/ directory, such as /forge (fast MVP prototyping), /architect (system architecture design), /conversion-booster (user conversion optimization), /debug-machine (systematic debugging). Each workflow has clear stages, checkpoints, and delivery standards, and requests human confirmation at key nodes for collaboration.
Section 05
The rules/ directory contains hierarchical, composable agent rules: base rules (core identity/boundaries like "you are a professional full-stack assistant"), domain rules (tech stack-specific like React/Vue/Node.js), and project rules (team coding standards/architecture conventions). Developers can inherit generic rules and extend them for specific projects.
Section 06
ColmoCode supports four mainstream AI programming tools: Antigravity, Claude Code, Cursor, Codex CLI. It uses platform-specific adaptation layers—e.g., leveraging Cursor's inline editing for code changes, Claude Code's long context for complex dependency analysis. The agents/ directory has platform configs, and commands/ defines supported command sets.
Section 07
ColmoCode uniquely combines test-driven development (TDD) and high-end visual aesthetics. TDD is embedded in workflows (writing tests before code, maintaining coverage during refactoring), while UI/UX skills ensure generated interfaces are both functional and visually appealing. This is ideal for building user-facing apps.
Section 08
ColmoCode offers an install.sh script for one-click deployment. Documentation includes a README (quick start) and directory-specific details. The project encourages community contributions (new skills/rules) and uses GitHub Issues for feedback, aiming to adapt to the evolving AI tool landscape.
Keep going with more reads from the same topic.
Nornir MCP Server is an enterprise-level server based on the Model Context Protocol (MCP). It seamlessly integrates large language models (such as Claude) with the Nornir network automation framework, supporting natural language orchestration for multi-vendor network devices (Cisco, Arista, Juniper, etc.), and providing production-grade features like a dual-engine architecture (NAPALM + Netmiko), intelligent filtering, and a secure sandbox.
Bibliothèque Française LLM is a structured indexing and annotation project for French public domain literature designed specifically for large language models (LLMs). It integrates multiple authoritative sources such as DraCor, Common Corpus, and Wikisource, providing metadata indexing categorized by genre, author, and era, as well as in-depth annotations for dramatic texts (including characters, lines, stage directions, etc.). Its aim is to enable LLMs to efficiently read and understand classic French literary works.
Splinter is a minimalist, high-performance key-value (KV) and vector storage system enabling zero-latency inter-process communication via shared memory and atomic operations. With only 766 lines of core code, it supports millions of operations per second and 768-dimensional vector storage, offering a new architectural approach for local LLM inference and data-intensive applications.
A complete cloud-native AI application development guide for beginners, building a simple generative AI chatbot using Amazon EC2, Apache, Python CGI, and Amazon Bedrock, covering architecture design, IAM permission configuration, security best practices, and cost optimization suggestions.