Articles

Original writing on getting more out of AI tools.

Series
39 articles · page 1 of 2

Knowing when to stop

Six hours in, one step left, everything green, and the incident that didn't happen

LLM Mart · Sep 24, 2026 2 views 0 reactions

CLAUDE.md vs. skills: where should Claude Code instructions live?

CLAUDE.md carries persistent project context. Skills load reusable procedures when relevant. Separating stable facts from task-specific workflows keeps both easier to maintain.

LLM Mart · Sep 23, 2026 1 views 0 reactions

Those are the other app's keys

Twenty minutes recovering secrets that never existed, and the one sentence from a human that ended it

LLM Mart · Sep 23, 2026 1 views 0 reactions

How to use remote MCP servers with the OpenAI Responses API

An API request routing a model's tool call through an approval gate to a remote MCP server

LLM Mart · Sep 22, 2026 1 views 0 reactions

The coverage audit before you delete the safety net

31 config keys, two audits, and why the first one was wrong in both directions

LLM Mart · Sep 22, 2026 3 views 0 reactions

How to publish an MCP server to the official MCP Registry

The official MCP Registry stores standardized server metadata rather than package code. Publishers verify a namespace, describe installation or remote access, and submit immutable versions.

LLM Mart · Sep 21, 2026 2 views 0 reactions

Rotating a leaked credential, in the right order

Everyone looks at the Dockerfile. The file that actually leaked the key was the project file.

LLM Mart · Sep 21, 2026 1 views 0 reactions

MCP authentication explained: OAuth, scopes, and safe token handling

Remote MCP authorization uses established OAuth standards, but secure integration still requires issuer validation, least-privilege scopes, protected token handling, and server-side enforcement.

LLM Mart · Sep 20, 2026 4 views 0 reactions

Byte-identical or bust

"Copy it over and switch the reference" is two steps, and the outage lives in the one nobody checks

LLM Mart · Sep 20, 2026 5 views 0 reactions

MCP stdio vs. Streamable HTTP: which transport should you use?

stdio fits local processes and prototypes. Streamable HTTP fits hosted services and shared integrations. The right choice follows where the capability runs and who must reach it.

LLM Mart · Sep 19, 2026 3 views 0 reactions

Never let the AI print a secret

The most important rule wasn't about what I could change. It was about what I was allowed to display.

LLM Mart · Sep 19, 2026 1 views 0 reactions

MCP tools vs. resources vs. prompts: when to use each

Tools perform operations, resources expose readable context, and prompts provide reusable templates. Choosing the correct primitive makes an MCP server easier to understand and govern.

LLM Mart · Sep 18, 2026 5 views 0 reactions

How to test an MCP server with MCP Inspector

Use MCP Inspector to connect to local or remote servers, inspect capabilities, call tools, read resources, test prompts, and diagnose failures before release.

LLM Mart · Sep 17, 2026 4 views 0 reactions

How to build an MCP server in TypeScript: step-by-step

Build an MCP server in TypeScript with focused tools, validated schemas, local and remote transports, Inspector tests, and production security controls.

LLM Mart · Sep 15, 2026 6 views 0 reactions

What is an MCP server? A practical guide

An MCP server exposes tools, resources, or prompts through a standard protocol so an AI application can discover and use external capabilities.

LLM Mart · Sep 11, 2026 12 views 0 reactions

How to vet AI agent skills before installing them

Treat an AI agent skill as both an instruction package and a software dependency: inspect what it says, what it runs, what it can access, and how it updates.

LLM Mart · Sep 10, 2026 31 views 0 reactions

How to add an MCP server to Claude Code safely

Add remote HTTP or local stdio MCP servers to Claude Code, choose the right scope, protect credentials, verify the connection, and test with least privilege.

LLM Mart · Sep 9, 2026 28 views 0 reactions

Claude skills vs. connectors vs. plugins: what is the difference?

Skills teach Claude a repeatable method, connectors provide governed access to apps and live data, and plugins package related capabilities for installation and sharing.

LLM Mart · Sep 8, 2026 60 views 0 reactions

AI agent skills vs. MCP servers: which should you build?

Use an agent skill to package reusable know-how and workflow instructions. Use an MCP server when an agent needs live, governed access to external data or actions.

LLM Mart · Sep 4, 2026 27 views 0 reactions

Claude Code skills vs. slash commands: what changed

Custom commands and skills can both create a slash-invoked workflow in Claude Code. The important choice is how the workflow is discovered, shared, and permissioned.

LLM Mart · Sep 3, 2026 38 views 0 reactions

10 best Claude skills for developers in 2026

A useful Claude skill solves one recurring engineering job, is easy to inspect, and saves more time than it creates in setup and review.

LLM Mart · Sep 2, 2026 38 views 0 reactions

How to install Claude skills in Claude and Claude Code

Claude skills can live in your Claude account, your local Claude Code setup, or a repository. Install them where the sessions that need them can load them.

LLM Mart · Sep 1, 2026 34 views 0 reactions

How to create an AI agent skill: a practical SKILL.md guide

Build a portable AI agent skill from one repeatable job: a precise description, concise instructions, focused resources, and tests that prove it works.

LLM Mart · Aug 31, 2026 24 views 0 reactions

What are AI agent skills? How SKILL.md works

AI agent skills package instructions, scripts, references, and templates into portable folders an agent loads only when the task calls for them.

LLM Mart · Aug 30, 2026 30 views 0 reactions