Agenticx Agent Builder logo

Agenticx Agent Builder

Community
DemonDamon
agenticx-agent-builder

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.

Overview

PublisherDemonDamon
RepositoryAgenticX
Skill nameagenticx-agent-builder
Stars
608
Forks
68
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by DemonDamon on GitHub. Read the source before you install it.

Installation

Install the Agenticx Agent Builder AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/DemonDamon/AgenticX/tree/main/agenticx/skills/agenticx-agent-builder
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/DemonDamon/AgenticX.git /tmp/AgenticX
mkdir -p .claude/skills
cp -r /tmp/AgenticX/agenticx/skills/agenticx-agent-builder .claude/skills/agenticx-agent-builder
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Agenticx Agent Builder in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Agenticx Agent Builder on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Agenticx Agent Builder is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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

FieldMeaningExample
nameShort character-like display name飞廉
roleOne-line positioning进取型全市场交易分析师
system_promptFull behavior contractSee template below
default_provider / default_modelOptional; omit to inherit global default

system_prompt should include

  • Identity & coverage
  • Analysis / work priorities
  • Risk preference & hard boundaries
  • Data discipline (no fabricated numbers / facts)
  • Output style & fixed structure when useful
  • Disclaimer when the domain needs one (finance, medical, legal, etc.)

Landing step (required)

Call:

text
create_avatar(
  name=...,
  role=...,
  system_prompt=...,
  default_provider=optional,
  default_model=optional
)

Then confirm to the user:

  • The avatar is in the sidebar list
  • They can open it or @ it in group chat
  • Optionally offer follow-ups: schedule automation, tweak prompt, set default model

If create_avatar returns avatar_exists

Do not create a duplicate. Tell the user it already exists and offer:

  • delegate_to_avatar(avatar_id=..., task=...) for work
  • Or update via settings / a later update tool if they want changes

Anti-patterns

  • Saying "半搞定" after only drafting a prompt file
  • Dumping a long YAML/Markdown archive without calling create_avatar
  • Asking the user to copy-paste into the create-avatar form
  • Confusing temporary spawn_subagent workers with persistent avatars
  • Using spawn_subagent with the same name as a registered avatar

Example success path

User: "帮我创建一个数字分身专门帮我分析金融市场"

  1. Clarify markets / style / risk preference (2–3 choices)
  2. Distill name=飞廉, role=进取型全市场交易分析师, full system_prompt
  3. Call create_avatar(...)
  4. Reply: 飞廉已加入分身列表,可直接点开或 @ 它

Frequently asked questions

What does the Agenticx Agent Builder AI skill do?

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.

Why use Agenticx Agent Builder on TypingMind?

Because you install it once and use it with any model. Agenticx Agent Builder is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Agenticx Agent Builder in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/DemonDamon/AgenticX/tree/main/agenticx/skills/agenticx-agent-builder. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Agenticx Agent Builder?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Agenticx Agent Builder?

As many as you like. As long as a model supports skills, you can use Agenticx Agent Builder with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Agenticx Agent Builder AI skill free?

Yes. It is published on GitHub by DemonDamon under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇