personas

Route user requests to locally configured YAML personas by matching proper nouns.

Updated May 16, 2026
One-click install
npx skills add https://github.com/jaredcroxton/hermes-mirror --skill personas-jaredcroxton
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: personas
Source: https://github.com/jaredcroxton/hermes-mirror/tree/main/agents/skills/personas
Command: npx skills add https://github.com/jaredcroxton/hermes-mirror --skill personas-jaredcroxton

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It lets you dynamically ground responses in named, local persona configurations so the same agent can reliably behave like different experts, with no ambiguity about which “version” you mean.

Core Features & Use Cases

  • Auto-discovery of local personas: Reads the live set of YAML persona files from ~/.hermes/pantheon/personas/ on every turn, so changes take effect immediately.
  • Proper-noun grounded persona selection: Detects proper nouns in your message that match persona names and uses the corresponding YAML as the first-class source of truth.
  • Persona-specific actions: Supports “do X as <persona>,” description of a persona, and comparisons (by reading multiple YAMLs) to keep behavior consistent and locally defined.
  • Pantheon visibility: Lists persona name and job fields from the current pantheon YAMLs.

Quick Start

Tell the assistant: “Orpheus, summarize this PR and suggest the most likely architectural risks.”

Frequently Asked Questions about personas

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I switch agent behavior using YAML persona configurations?

To switch agent behavior using YAML persona configurations, the system routes your request by matching proper nouns in your message against YAML files in the local pantheon directory, loading the matched persona's model and system prompt to ground the response.

What is proper-noun grounded persona routing for AI agents?

Proper-noun grounded persona routing is a mechanism that detects specific names in your prompt to match them against local YAML persona files, dynamically loading the correct expert configuration to ensure deterministic, persona-specific behavior.

How do I compare multiple expert personas during a single task?

To compare multiple expert personas during a single task, the system reads multiple YAML persona definitions simultaneously, allowing you to execute cross-persona analysis, reviews, and expert-style explanations within one grounded response.

Do I need to restart the agent when adding new persona YAML files?

You do not need to restart the agent when adding new persona YAML files. The system auto-discovers local personas by re-scanning the pantheon directory on every turn, ensuring changes to your YAML files take effect immediately.

How does persona disambiguation work when multiple definitions match?

Persona disambiguation defaults to the local persona when ambiguity exists. It resolves conflicts by matching proper nouns against the YAML definitions and defaulting to the locally defined configuration when a clear match cannot be determined.

Can I list all available personas in my local pantheon directory?

You can list all available personas in your local pantheon directory. The system provides pantheon visibility by reading the current YAML files and displaying the name and job fields for every configured persona.