Reading
Choral's open-source public agent skill collection, providing repository-based knowledge governance workflows, supporting multiple Agent runtimes and cross-platform compatibility.
Section 01
Choral Skills is an open-source public agent skill collection developed by choral-io. Its core is a repository-based knowledge governance workflow, supporting multiple Agent runtimes (such as Claude Code, Codex) and cross-platform compatibility. Its core concept is "Skills as Code", aiming to build an open agent skill ecosystem where agent capabilities can be version-controlled, shared, and combined.
Section 02
This project aims to solve the problem of agent skills being difficult to reuse and share. Through the form of an independent skill library, skills are not bound to specific products and can be installed into agent runtimes that support local skills.
Section 03
Covers the knowledge lifecycle (from creation to delivery) for different roles:
For delivery teams and individuals:
Section 04
Each skill includes a mandatory SKILL.md file, defining:
agents/openai.yaml is OpenAI/Codex UI metadataSKILL.md + references/ resourcesSection 05
npx skills add <owner>/<repo> (unified experience, automatic dependency handling)skills/<skill-name>/ directory to the runtime's skill directoryclaude plugin marketplace add choral-io/choral-skillscodex plugin marketplace add choral-io/choral-skillsclaude plugin install <plugin-name>@choral-skillscodex plugin add <plugin-name>@choral-skillsReduce size: claude plugin marketplace add choral-io/choral-skills --sparse .claude-plugin plugins/knowledge-workflow
Keep plugins in sync with root directory skills: ./scripts/sync-plugin-skills.sh knowledge-workflow (supports check mode: --check).
Section 06
Treat third-party skill managers and downloaded skills as code: check
SKILL.md, scripts, and bundled resources before installation. Recommendations: review source/author, read function descriptions, check files, install only from trusted sources.
Section 07
Choral Skills not only provides practical skills but also demonstrates best practices for building an agent skill ecosystem: standardized interfaces, cross-platform compatibility, layered architecture, and open installation mechanisms. As AI agents play an increasingly important role in software development, the value of its ecosystem will become more prominent. For developers, this project is an excellent reference case for building their own skill libraries.
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.
Folkering OS is the world's first AI-native bare-metal operating system, entirely written in Rust no_std without relying on Linux, POSIX, or libc. It can generate commands from scratch, compile them into WASM, and run them in 10 seconds, achieving true self-evolution.