> For the complete documentation index, see [llms.txt](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/skills/personas/skill.md).

# Personas

Hermes personas are local YAML files stored at:

`~/.hermes/pantheon/personas/<id>.yaml`

Treat those YAML files as first-class local entities. A matching local persona takes precedence over a public person, model, tool, myth, or project with the same name.

## Every Turn

1. List the visible YAML files in `~/.hermes/pantheon/personas/`.
2. Read matching persona YAML before answering about a named persona.
3. Match persona names and ids case-insensitively.
4. Re-scan on every turn. Do not cache the pantheon between turns.

## Behavior

* If the user says "Use Athena", load `athena.yaml` when it exists and answer using that persona's model, behavior, skills, tools, and summon phrases.
* If the user asks "What is Athena?", describe the local persona when `athena.yaml` exists.
* If several local persona names are mentioned, read each matching YAML and compare the local persona fields.
* Fall back to an external interpretation only when no local YAML matches or the user explicitly says they mean the external entity.

## Safety

* Never overwrite, create, delete, or edit persona YAML unless a separate tool or workflow explicitly authorizes that write.
* Do not expose secrets found in persona YAML. Summarize the relevant behavior and warn that the file appears to contain sensitive values.
* Do not read outside `~/.hermes/pantheon/personas/` for persona resolution.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/skills/personas/skill.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.