Claude

I write and review a lot of Agent Skills, and find myself frequently pushing back in reviews, as many authors assume they’re writing “just another markdown prompt” without considering that they’re actually working with one component of an agentic system. The TLDR of my feedback is usually along the lines of: The description’s only job is to tell the agent when the skill should be triggered. Keep the description as terse as possible while still triggering. The SKILL.md should be lean with detail pushed to reference files. Put repeatable work in scripts rather than relying on model inference. Skill Creator Primer I recommend teams use or create their own version of my skill-creator-primer skill. ...

Configuration Agent rules - concise, scoped CLAUDE.md files that shape agent behaviour Sandboxing - constrain file access and network connections Permissions - pre-approve safe operations, hard-block dangerous ones Hooks - run shell commands before/after tool calls as a safety net Extend knowledge and capabilities Skills - dynamic knowledge acquisition with progressive disclosure Language servers - give the agent go-to-definition, find-references, and type checking MCP tools - external tool servers, used sparingly Workflow Plan before acting - read-only exploration and task definition Embrace starting fresh sessions - keep context clean Template out common commands - reusable prompts for common tasks ...

If you’re building MCP servers, you should be adding the ability to disable individual tools.

MCP DevTools - The one tool that replaced the 10-15 odd NodeJS/Python/Rust MCP servers I had running at any given to for agentic coding tools with a single server that provides tools I consider useful for agents when coding. The Problem The MCP ecosystem has grown rapidly, but I found myself managing many separate servers, each often running multiple times for every MCP client I had running, not to mention the ever growing memory and CPU consumption of the many NodeJS or Python processes. ...