Skills, CLAUDE.md, MCP and agents: how you actually work with Claude inside a company, from someone who uses it every day for consulting.
Claude Code is not an editor with autocomplete: it is a collaborator that reads your repository, follows the rules you write for it and uses the tools you give it. The practical difference comes down to three things. Skills, which are procedures written once and reused forever. The CLAUDE.md file, which is the context the agent reads before doing anything. And MCP, the protocol it uses to talk to your systems instead of to thin air.
These articles are the log of how we actually use it for consulting work, mistakes included. They are not reviews: they are configurations, checks and limits found in the field. They are also the part of the blog that brings the most technical readers, which is why you will not find a sales pitch at the bottom: you will find the code.
13 articles in this topic, updated 05 Aug 2026
Context engineering for one project is a CLAUDE.md. For a whole company it is a different problem: shared context across repositories, selective loadi…
We open-sourced the method we use to map our clients' processes: process-builder is an AI skill that interviews you (who does what, when, with which t…
An MCP server connects Claude and AI agents to your CRM: read the pipeline and update deals in plain language. A hands-on guide with real code, a safe…
Claude Code can speed up software development, but only if it enters a controlled process. Here are the 7 controls I use to turn AI from a shortcut in…
If you are explaining the same things to Claude every time you open a new session, you are wasting time. The solution is called CLAUDE.md, and most pe…
Every time you open a new session with Claude, it starts from zero. It does not know how you work, does not know your project, does not remember anyth…
Claude Code is Anthropic's command-line interface for using Claude directly in the terminal, integrated with your development environment. It is not a…
The structure of a Claude Code project in VSCode determines how well Claude understands your project, how reproducible behaviors are across sessions, …
A Claude Code skill is a file of structured instructions that Claude executes on request, invoked with a command like /skill-name. It allows you to sa…
In October 2024 Anthropic published the Model Context Protocol specifications. Within months, OpenAI, Google, and practically every relevant player in…
You've probably already heard about Claude Code skills. Maybe you've read something about them, maybe you've seen someone using them, but you haven't …
An MCP server for VTENext is middleware that exposes the CRM's APIs as tools usable by Claude and other LLMs compatible with the Model Context Protoco…
When Anthropic introduced skills for Claude Code in October 2025, few understood immediately what was happening. It was not a feature: it was a protoc…
They are procedures written in a markdown file that the agent loads when needed. Instead of explaining how something is done every time, you write it once and call it by name. It is the difference between giving verbal instructions and having a company procedure.
It is the context the agent reads before working on the repository: conventions, commands, things not to do. Without it, the agent guesses, and it guesses wrong exactly where your project has a rule of its own.
It is the standard way an AI agent connects to an external system, your CRM for instance, and works inside it through defined operations. It changes the game because the AI stops suggesting text and starts reading and writing real data.
The two topics closest to this one
Skills, MCP servers and the projects we use every day live in the Open Lab, with the code in plain sight.
Go to the Open LabOpen code, no sign-up