Reading
Explore the saitarrun/sdlc-ai-workflow project, a plugin designed for Claude Code that automates the complete software development lifecycle from requirement planning to operation and maintenance monitoring through 26 professional AI agents, 43 knowledge skills, and 14 commands.
Section 01
Explore the saitarrun/sdlc-ai-workflow project, a plugin designed for Claude Code that automates the complete software development lifecycle from requirement planning to operation and maintenance monitoring through 26 professional AI agents, 43 knowledge skills, and 14 commands.
Section 02
Section 03
In modern software development, teams often face a core pain point: context loss, delays, and errors caused by manual handoffs. From product managers to architects, then to engineers, testers, and operations personnel, each role transition can lead to information decay. The SDLC AI Workflow project was created to address this issue—it is a plugin designed specifically for Claude Code that automates the complete Software Development Lifecycle (SDLC) from planning to operations through the collaborative work of 26 professional AI agents. The core philosophy of this project is to encode industry best practices into the behavior of AI agents, allowing the entire development process to run smoothly like an assembly line while maintaining high-quality standards.
Section 04
The project divides software development into six distinct phases, each with dedicated AI agents responsible for it:
Section 05
This is the starting point of the project, determining the direction of all subsequent work. This phase includes four core agents:
These agents automatically load phase-specific skills; for example, requirement analysis skills inject knowledge of the INVEST standard and QUANTS framework to ensure outputs comply with industry norms.
Section 06
After requirements are clarified, the design phase transforms concepts into interactive blueprints:
This phase emphasizes rapid validation of design hypotheses, using disposable prototype code to test key interaction flows and avoid investing too many development resources in the wrong direction.
Section 07
This is the most labor-intensive phase, involving five professional development agents:
Each development agent automatically applies coding standards such as Clean Code, SOLID principles, and DRY (Don't Repeat Yourself) to ensure code quality is guaranteed from the source.
Section 08
The quality assurance phase adopts a multi-layered testing strategy:
The test pyramid principle is automatically applied to ensure a reasonable ratio of unit tests, integration tests, and end-to-end tests, avoiding the accumulation of test debt.
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.
libmlxforge is an embeddable MLX large language model (LLM) inference engine designed specifically for Apple Silicon. It provides a unified C ABI interface, supports calls from Node.js, Swift, and Rust, and features continuous batching, streaming output, JSON-constrained structured output, and embedding vector generation.