# Agenticx Agent Builder

Guide for creating persistent Near desktop digital avatars (数字分身) via natural-language...

- Repository: https://github.com/DemonDamon/AgenticX (866 stars)
- Category: AI and agents
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add DemonDamon/AgenticX --skill agenticx-agent-builder -g -a claude-code -y`
Codex: `npx skills add DemonDamon/AgenticX --skill agenticx-agent-builder -g -a codex -y`
Cursor: `npx skills add DemonDamon/AgenticX --skill agenticx-agent-builder -g -a cursor -y`
Gemini CLI: `npx skills add DemonDamon/AgenticX --skill agenticx-agent-builder -g -a gemini-cli -y`

## Description

Guide for creating persistent Near desktop digital avatars (数字分身) via natural-language interview and the create_avatar tool. Use when the user wants to create an avatar, digital twin, specialist agent persona, or add someone to the avatar sidebar.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Near Digital Avatar Builder

Help the user create a **persistent desktop digital avatar (数字分身)** that appears in the Near sidebar avatar list.

## Hard rules

1. **Must call `create_avatar`** after clarifying and distilling the config. That tool writes the avatar into the registry and makes it appear in the sidebar.
2. **Do NOT** only write a Markdown file to Desktop / workspace and claim the avatar is created.
3. **Do NOT** tell the user there is "no create-avatar API", `create_avatar` is the API.
4. **Do NOT** ask the user to open「+ 新建」and fill the manual form unless they explicitly want the GUI.
5. **Do NOT** invent Python SDK / `AgentExecutor` / `agx agent create` workflows for this task, those are code-layer agents, not Near desktop avatars.

## Interview flow (2, 3 rounds, not a long questionnaire)

Ask only what is still missing. Prefer short choices (clarification / `show_widget`) over open essays.

### Round 1, Positioning

- What should this avatar own? (domain / job)
- Who is it for? (usually the current user)

### Round 2, Scope & style

- Coverage (markets, stacks, products, languages…)
- Analysis / work style (trading vs research, concise vs thorough, etc.)

### Round 3, Boundaries (only if needed)

- Risk preference / what it must never do
- Preferred output structure
- Optional default model

Stop early when you already have enough to write a solid `name` / `role` / `system_prompt`.

## Distill into these fields

| Field | Meaning | Example |
|---|---|---|
| `name` | Short character-like display name | 飞廉 |
| `role` | One-line positioning | 进取型全市场交易分析师 |
| `system_prompt` | Full behavior contract | See template below |
| `default_provider` / `default_model` | Optional; omit to inherit global default | |

### `system_prompt` should include

The rest: https://github.com/DemonDamon/AgenticX/blob/HEAD/agenticx/skills/agenticx-agent-builder/SKILL.md