With the Pace of Change, You Probably *are* Using Claude Code Wrong

Back to list

They're talking more and more about skills (instead of prompts) and how you shouldn't have overlap in your skills - does that smell like SRP? Single responsibility principle? So, you're the conductor, orchestrating code, but, you still need to know proper coding principles. Hey, just tell CC to call you out. Why not a skill that will run a nightly check on your code-base and report back in the morning. BTW, what if you want to shut your computer down for the night - can yuou 

Here's one enterprising (austinmarchese@smoothmedia.co) guy's useful prompt:

Audit my Claude Skills for:

l. Visibility:

- Skills with high risk side effects (deploy, commit, send messages): add  disable-model-invocation: true so Claude can't auto-fire.

- Skills that are pure background knowledge users would never /run themselves: add user-invocable: false to hide from /menu.

2. Deterministic vs non-deterministic:

- Find any step inside a skill where Al is interpreting something that's actually a fixed, repeatable operation.

- Suggest replacing those steps with a script saved inside the skill folder.

Code = same result every time, no tokencost.

- Keep Al for the steps that need judgment.

3. Composability:

- Flag any skill that duplicates logic another skill already has. Suggest extracting shared logic into a callable script or a smaller composable skill.

Show me the rewrites with a changelog of what changed and why.