[BUG] /effort command returns "Unknown skill: effort" despite being documented

### Preflight Checklist

- [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) 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?

The `/effort` command is documented on Claude's official blog and docs but returns "Unknown skill: effort" when used in Claude Code v2.1.12.

Running `/effort` or `/effort high` both fail with the same error message.

The feature is referenced in:
- https://claude.com/blog/claude-model-and-effort-level-in-claude-code
- https://platform.claude.com/docs/en/build-with-claude/effort
- https://code.claude.com/docs/en/model-config

### What Should Happen?

The `/effort` command should either:
1. Open an interactive slider to set thinking effort level (as documented)
2. Accept a level argument like `/effort high` to set effort directly

Or if the feature isn't available yet, it should not be in public documentation.

### Error Messages/Logs

```shell
"Unknown skill: effort"
```

### Steps to Reproduce

1. Install Claude Code via npm: `npm install -g @anthropic-ai/claude-code`
2. Verify version: `claude --version` → 2.1.12
3. Start a session: `claude`
4. Run `/effort`
5. Observe error: "Unknown skill: effort"

### Claude Model

Sonnet (default)

### Is this a regression?

Yes, this worked in a previous version

### Last Working Version

Unknown

### Claude Code Version

2.1.12

### Platform

Anthropic API

### Operating System

macOS

### Terminal/Shell

Terminal.app (macOS)

### Additional Information

Same issue -> https://github.com/anthropics/claude-code/issues/33000

Start by reproducing the failure with Claude Code v2.1.12 using `/effort` and `/effort high`, then compare the documented behavior in the linked Claude blog and documentation pages. Check whether the command is implemented and available in this version; done means the command works as documented or the public documentation no longer claims it is available.

Written by the indexing model from the issue text.