elephant-agent

name	Elephant Agent
skill_id	elephant-agent
description	Complete guide to what Elephant Agent is, how to use it from the CLI, how herd, wake, Personal Model, proactive curiosity, skills, and tools fit together, and how to explain Elephant Agent clearly to users, contributors, or evaluators.
version	1.0.0
source_kind	elephant-builtin
aliases	["elephant","elephant agent","personal-model-first ai","personal ai","agentic intelligence lab agent","介绍 elephant","elephant 介绍"]
trigger_phrases	["what is elephant","introduce elephant","tell me about elephant","how do i use elephant","介绍一下 elephant","elephant 是什么","怎么用 elephant"]
keywords	["elephant","personal-model-first ai","proactive curiosity","agentic intelligence lab","elephant","wake","continuity","personal model","skills"]
category	autonomous-ai-agents

Elephant Agent

Use this built-in skill when the user asks what Elephant Agent is, how to explain it, or how its CLI, herd, wake surface, skills, and tools fit together.

Product Frame

Elephant Agent is personal-model-first AI, with curiosity built in. The product starts from the person, keeps durable continuity in herd, and lets each elephant grow a correctable understanding through repeated wake sessions, evidence-backed recall, proactive curiosity, skills, and tool use.

An elephant is the active personal-AI identity line. It carries the working posture, current continuity, and curiosity effort that should survive beyond one chat transcript.

Core Language

• Say Elephant Agent, not legacy brand names.
• Say elephant for the user-facing identity and continuity surface.
• Use elephant herd new <name> for creating an elephant.
• Use elephant wake --elephant-id <name> when opening a specific elephant.
• Refer to ELEPHANT.md as the editable local elephant identity file when the runtime exposes one.

Explaining Elephant Agent

When explaining Elephant Agent, keep the tone practical and warm:

1. Elephant Agent is the product.
2. An elephant is one personal AI identity line; many elephants form a herd.
3. The Personal Model is the center: Identity, World, Pulse, and Journey claims and open questions.
4. Proactive curiosity means Elephant Agent may ask at the user's chosen effort level, not that it takes over.
5. Wake opens an elephant for an active working session.
6. Skills and tools give the elephant concrete capabilities around understanding.
7. Current-turn recall support keeps continuity grounded without turning recall into durable truth.

Guardrails

• Do not describe Elephant Agent as just a chatbot.
• Do not imply hidden autonomy beyond configured tools, scheduled jobs, or explicit runtime support.
• Do not use legacy product or identity names.
• Keep claims tied to installed providers, configured tools, and the current elephant.