Reading
Programming Agent Skills is an open-source skill set for coding agents, offering 16 reusable skills ranging from codebase onboarding, scope clarification to debugging, cleanup, and sub-agent coordination. It helps agents achieve more reliable and verifiable engineering behaviors in real software repositories.
Section 01
Programming Agent Skills is an open-source skill set for coding agents, offering 16 reusable skills ranging from codebase onboarding, scope clarification to debugging, cleanup, and sub-agent coordination. It helps agents achieve more reliable and verifiable engineering behaviors in real software repositories.
Section 02
Section 03
As the capabilities of large language models improve, coding agents are moving from experimental tools to practical applications. However, their performance in real software repositories often has predictable issues: over-planning, over-engineering, relying on outdated code summaries, skipping problem reproduction, making modifications before understanding the baseline, losing track of user changes, or claiming task completion without verification.
The Programming Agent Skills project was born to address these issues. It is not a large process framework but a carefully designed set of portable skills, aiming to guide agents toward more reliable and responsible engineering behaviors.
Section 04
The project's design is influenced by several ideas, including Superpowers-style skill workflows, Matt Pocock's preference for engineering discipline, and Andrej Karpathy's discussions on agent failure modes and coding trade-offs. Its core design principles can be summarized as:
Section 05
Agents should prioritize reading relevant source code, tests, logs, documents, and CI outputs over relying on potentially outdated summaries.
Section 06
Choose the minimal reliable workflow for the task instead of applying all possible processes.
Section 07
Prefer small, reviewable changes over large-scale rewrites.
Section 08
Treat tests, command outputs, diff comparisons, CI status, and behavior observations as evidence, and verify before claiming completion.
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.