[BUG] Claude Code keeps coming back to /skill after compacting memory

Resolved 💬 3 comments Opened Mar 30, 2026 by JochemMichiels Closed Apr 3, 2026

Preflight Checklist

  • [x] I have searched existing issues and this hasn't been reported yet
  • [x] This is a single bug report (please file separate reports for different bugs)
  • [x] I am using the latest version of Claude Code

What's Wrong?

we were deploying a tool to a server, and suddenly after compacting claude started a very old prompt / piece of work. I used the /frontend-design back then, and the first time it did this, it mentioned that it was because that skills was still in its memory.

<img width="833" height="143" alt="Image" src="https://github.com/user-attachments/assets/a0d08dce-7227-4f2d-a2cc-5f574112d485" />

What Should Happen?

Claude should not over emphasize a skill from its memory

Error Messages/Logs

Steps to Reproduce

I used the /frontend-design back then, and the first time it did this, it mentioned that it was because that skills was still in its memory.

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.87

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

_No response_

View original on GitHub ↗

This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗