Manage Your Agent's Loadout with Dr. Skill

Jul 24, 2026

AI

DEVOPS

CI

AGENTS

SKILLS

CONTEXT

Manage Your Agent's Loadout with Dr. Skill

Keep Your Agent’s Skills and Tools in Check

When I wrote “How to Fix Your Context”, it was really hard to find real-world examples of the Tool Loadout pattern. But as Skills have grown in popularity, our contexts have become cluttered.

Recently, I met a developer who told me how his enterprise agent was loading over 600 skills. All the skills created by colleagues were getting pulled in by default, without alerting the dev, silently degrading the context before a word was typed.

Last week, my Hermes agent kept loading the wrong note-taking skill. SSH’ing into the machine, I discovered Hermes ships with nearly 100 skills. Deleting the stock note-taking skill helped, but didn’t fully solve the issue. And I wasn’t eager to pore over every Hermes skill.

So I built drskill, a tool that evaluates all the skills and MCPs in your global or project environment.

Install drskill with uv tool install drskill or pip install drskill.

Then run drskill scan:

Here, drskill spots an error (my plumb skill is missing a description) and some warnings (a skill I was developing for Overture is installed twice, in two different places). drskill prints the path (and a solution, if relevant) and lets me fix these quickly.

drskill looks for 34 different issue categories, across MCPs and Skills. If you pass in the --deep flag, it will use an LLM (you need to provide your own key) to judge whether two skills are distinct, if their descriptions collide, or whether their scopes overlap.

If I run drskill list, I can see my current loadout. Adding --harness claude-code limits it to just what Claude Code sees:

If I want to know what parts of the loadout I actually use, I can run drskill audit. This scans my traces and finds all the times skills or tools are called and prints a report:

In only a week, drskill has been earning its keep. Beyond debugging Hermes and spotting some local issues, it’s been helpful when building my own skills and testing how they might play nicely in production.

I’ve heard from people using it to:

Learn why an agent reaches for the wrong skill or tool , e.g. two descriptions overlap so a router cannot tell them apart.

Catch config risks before they ship , e.g. a secret in a committed file or an unpinned server package.

Notice when their loadout changes , e.g. a skill that drifted from its lockfile or a server that rewrote a tool description.

Write skill and tool descriptions that don’t clash with other libraries .

See which skills and MCP tools their agents actually use , and read the queries that triggered them.

drskill has some nice convenience functions for using it locally or as part of CI.

Check it out! And let me know how it helps you or could be improved.

Enter your email to receive the occasional update.

BETA: Translations

I'm testing out using LLMs to rewrite articles for different contexts and audiences. The following content has not<br>been exhaustively reviewed and is presented as a proof-of-concept. Reach out if you spot<br>something egregious or want to know more.

-->