TypingMindTypingMindThe best frontend for AI
Create Profile logo

Create Profile

Community
ahmadrosid
create-profile

Create, design, or set up a new bot profile with soul files and appropriate tool assignments. Use when the user asks for a new profile, support bot, assistant, persona, or specialized bot.

Overview

Publisherahmadrosid
Repositorynakama
Skill namecreate-profile
Stars
492
Forks
91
Bundled files
Instructions only
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • 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 ahmadrosid on GitHub. Read the source before you install it.

Installation

Install the Create Profile 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/ahmadrosid/nakama/tree/main/packages/core/src/skills/bundled/create-profile
  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/ahmadrosid/nakama.git /tmp/nakama
mkdir -p .claude/skills
cp -r /tmp/nakama/packages/core/src/skills/bundled/create-profile .claude/skills/create-profile
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Create Profile 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 Create Profile 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 Create Profile 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.

When the user asks to create a profile, run a confirm-first factory — never call create_profile until they explicitly confirm the draft.

1. Clarify only when needed

Ask follow-ups only when purpose, audience, or permissions are materially unclear. Otherwise interpret the request concisely and move to the draft.

2. Draft in chat first

Post a reviewable draft before any tool call:

  • Proposed name (the server generates the profile id from the name), a human first name chosen with the naming rules below
  • Full proposed SOUL.md (who it is, values, help scope, boundaries)
  • Full proposed STYLE.md (voice, tone, formatting)
  • Full proposed INSTRUCTIONS.md (operating rules, tool posture, when to ask the user)
  • MEMORY.md must be empty. Do not invent continuity facts, preferences, or history.

Also include a tool plan:

  • Server auto-assigns these basics on create when available: read_file, write_file, edit_file, search_files, knowledge_base_search, web_fetch, plus default bundled skills (including update-profile-memory).
  • Recommend optional extras from the available-tools context only when they clearly match the requested purpose.
  • Do not assign every available tool. Avoid powerful or externally visible tools unless the user asked for that capability.
  • Assign extras only when the user asked for them or approved them in this plan.

Model and plugin choices:

  • Call list_models for model ids. When the purpose needs images (receipts, photos, screenshots), pick a model with supportsVision: true and put its id in the plan. Omit model to use your own model.
  • To connect an installed plugin, put its tools and its skill in the plan. Use list_tools for the plugin's tool ids. The skill name is the plugin manifest skill key.
  • Read-only list calls (list_models, list_tools, list_profiles) are allowed before the user approves.
  • Never read server source, config files, databases, or auth tokens to find models, tools, or skills.

Never set isSuper: true unless the user explicitly asked for a super profile. Prefer refusing agent-initiated super creation and directing them to the dashboard.

Naming

Every agent gets a human first name, so the user feels they work with a teammate and not a tool.

  • The name is a real first name, like "Maya", "Theo", "Priya", "Daniel", "Sofia", "Kenji". Never a job title ("Brand Strategist", "X Writer"), never a product or object name ("Quill", "Scout").
  • Pick names that fit the agent's temperament and culture of the work, but keep them plain and friendly. One word, easy to type after @.
  • Put the role in SOUL.md ("Maya is the user's brand strategist") and in how you introduce the agent to the user: "Maya — brand strategist". The profile name itself is only the first name.
  • For a team, give each agent a different first letter and mix voices and backgrounds, so the group feels like real people.
  • Use these names from the first time you suggest a team, in suggestions, question cards, drafts, and the final summary. Do not suggest job-title names and rename later. In a card, write "Maya — brand strategist".
  • Make the voice in SOUL.md and STYLE.md sound like that person: warm, friendly, first person, plain words, with a short personal way of speaking, like a helpful teammate and not a formal assistant.
  • Check list_profiles first. Never reuse an existing name.
  • If the user dislikes a name, offer two other first names.

3. Wait for explicit confirmation

Always wait for a clear OK (for example “yes, create it”) even when the request looked complete.

If the user edits the draft, revise the draft in chat and wait for confirmation again. Do not call create_profile on edit-only messages.

4. Create only after OK

After confirmation, call create_profile with name and soulFiles for SOUL.md, STYLE.md, INSTRUCTIONS.md, and empty MEMORY.md. Do not pass id — the server assigns one from the name.

Then assign the approved extras: assign_tool_to_profile for each tool and assign_skill_to_profile for each skill.

Then summarize:

  • Profile id and name
  • How to open it in the dashboard (Profiles → select the new profile)
  • Which basics were auto-assigned vs any extras still waiting on an explicit assign ask

Frequently asked questions

What does the Create Profile AI skill do?

Create, design, or set up a new bot profile with soul files and appropriate tool assignments. Use when the user asks for a new profile, support bot, assistant, persona, or specialized bot.

Why use Create Profile on TypingMind?

Because you install it once and use it with any model. Create Profile 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 Create Profile in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ahmadrosid/nakama/tree/main/packages/core/src/skills/bundled/create-profile. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Create Profile?

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 Create Profile?

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

Is the Create Profile AI skill free?

Yes. It is published on GitHub by ahmadrosid under the MIT 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.

Related AI Skills

View all
NousResearch logo

Tldraw Offline

NousResearch
OrganizationPopular

Drive and script tldraw offline canvases with an agent.

53.5K
250.4K
3 files
View
anthropics logo

Brand Guidelines

anthropics
OrganizationPopular

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual…

21.8K
184K
Instructions
View
openclaw logo

Solid

openclaw
OrganizationPopular

Write, port, review, or test Solid 2 UI in OpenClaw (Control UI, plugin views, Canvas hosts), including state ownership, Lit interop during the migration, native overlays, testing, performance, and…

82.4K
391.7K
9 files
View
openclaw logo

Canvas

openclaw
OrganizationPopular

Present hosted widget documents on a connected macOS panel and control panel visibility or navigation.

82.2K
391K
Instructions
View

Set up your own AI workspace now

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