[BUG] VSCode Slash-command autocomplete doesn't show available skills until after first message
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?
In the _VS Code extension_, the / slash-command picker does not display available skills (e.g., /consolidate-worktrees, /commit, etc.) until after the user has already typed their first message in a conversation.
Actual behavior:
The skill list in the autocomplete dropdown is empty or incomplete before the first message is sent. Skills only appear after the conversation has started and the system context (including the skill list) has been loaded.
VS Code extension
Linux (WSL2)
What Should Happen?
Slash-command autocomplete should show all available skills immediately when typing / in a new conversation, before sending any messages.
Actual behavior:
The skill list in the autocomplete dropdown is empty or incomplete before the first message is sent. Skills only appear after the conversation has started and the system context (including the skill list) has been loaded.
Error Messages/Logs
Steps to Reproduce
- Open new panel in VS Code extension
- type
/ - observe that no slash commands appear at all, nor as you start typing
Expected behavior:
Slash-command autocomplete should show all available skills immediately when typing / in a new conversation, before sending any messages.
Actual behavior:
The skill list in the autocomplete dropdown is empty or incomplete before the first message is sent. Skills only appear after the conversation has started and the system context (including the skill list) has been loaded.
Claude Model
None
Is this a regression?
Yes, this worked in a previous version
Last Working Version
2.1.76
Claude Code Version
2.1.81
Platform
Anthropic API
Operating System
Windows
Terminal/Shell
WSL (Windows Subsystem for Linux)
Additional Information
_No response_
This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗