Reading
cyber-skills is an open-source skill library and CLI tool that provides structured definitions of skills, roles, and workflows for AI agents (such as Claude Code, Cursor, Codex), helping teams establish consistent AI-assisted development practices.
Section 01
cyber-skills is an open-source skill library and CLI tool that provides structured definitions of skills, roles, and workflows for AI agents (such as Claude Code, Cursor, Codex), helping teams establish consistent AI-assisted development practices.
Section 02
Section 03
cyber-skills is a skill library and CLI tool designed for AI agents, supporting mainstream AI programming assistants like Claude Code, Cursor, Codex. It provides a set of structured skill, role, and workflow definitions to help development teams establish consistent AI-assisted development practices. The core concept of the project is to encode the team's best practices through reusable skill definitions, enabling AI agents to maintain consistent development styles and quality standards across different projects.
Section 04
cyber-skills introduces the concept of skill augmentations, allowing customization of skill behavior through a layered override mechanism:
SKILL.md — Base skill (lowest priority)SKILL.project.md — Project-level override (team-shared, checked into the consuming project)SKILL.local.md — Machine-local override (highest priority, gitignored)Later layers extend and override previous layers. This design allows teams to customize based on project needs while keeping the base skills unchanged.
Section 05
Skills can be placed in different locations based on their usage scope:
| Placement Location | Path | Use Case |
|---|---|---|
| User-level | ~/.agents/skills/<name>/ |
Personal skills across all projects |
| Project Private | .agents/skills/<name>/ |
Contributor tools limited to this repository |
| Project Public | skills/<name>/ |
Released with the package, installed by users via npx skills add |
Section 06
cyber-skills defines three skill modes:
| Mode | Use Case |
|---|---|
| Process | Multi-step workflows where sequence and decision-making matter |
| Tool | Consistent usage around tools, systems, or connectors |
| Standard | Skills that enforce tone, structure, format, or quality standards |
Section 07
The cyber-skills codebase is organized as follows:
skills/ — Public skills released with the package, installed by users via npx skills add cyberuni/cyber-skills.agents/skills/ — Internal repository skills for contributor workflows (changesets, security PRs, repository renaming), all must be marked metadata: internal: truesrc/ — TypeScript source code; domain folders: audit/, awesome/, commit/, governance/, hook/, skill/governances/ — Version-locked agent tool contracts released with the npm package, loaded via cyber-skills governance show <name>docs/adr/ — Architecture Decision Recordsdocs/research/ — Background research linked from ADRs and governances (not loaded via CLI)bin/cyber-skills.mjs — Minimal tracking shim, delegates to dist/cli.mjsdist/cli.mjs — Single bundled CLI (gitignored, built by tsdown)Section 08
The cyber-skills CLI is used to register agent hooks and run scripts without adding it as a devDependency. In other repositories, use fixed npx calls with the exact version from npm view cyber-skills version. In this repository, build first, then use the local bin. The tool is idempotent.
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.