# Reference

## Slash commands

These commands are available in your agent after installing the NeoHive plugin. Run them directly in your agent session.

| Command                              | What it does                                                                                                                                            |
| ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `/neohive:getting-started`           | First-time setup wizard. Verifies the MCP connection, creates a project, and optionally migrates existing context files. Run once per machine.          |
| `/neohive:load-context`              | Pre-loads relevant context for your current task. Run at the start of a session, or when switching tasks mid-session.                                   |
| `/neohive:capture-session-learnings` | Scans the current conversation and stores corrections, conventions, decisions, and insights into NeoHive. Also runs at session end via the plugin hook. |
| `/neohive:migrate-memory`            | Imports knowledge from `CLAUDE.md`, `AGENTS.md`, `.cursor/rules`, and `.claude/rules` into NeoHive. See [Migrating from CLAUDE.md](/migration.md).      |
| `/neohive:generate-claude-md`        | Generates a NeoHive topology block in your project's `CLAUDE.md`. Re-run when hives are added or renamed.                                               |
| `/neohive:enable-smart-prompts`      | Installs a hook that rewrites your prompts with a small model before searching NeoHive, improving recall relevance.                                     |


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.neohive.ai/reference.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.