TypingMindTypingMindThe best frontend for AI
Nakama Guide logo

Nakama Guide

Community
ahmadrosid
nakama-guide

Map of the Nakama web app — each page, its path, what it controls, and who can open it. Use when the user asks where or how to find, set, or change something in Nakama itself (models, providers, image generation, tools, skills, members, channels, settings).

Overview

Publisherahmadrosid
Repositorynakama
Skill namenakama-guide
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 Nakama Guide 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/nakama-guide
  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/nakama-guide .claude/skills/nakama-guide
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nakama Guide 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 Nakama Guide 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 Nakama Guide 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.

Nakama guide

Use this map when the user asks where something is in Nakama. Do not guess from other web apps.

How to answer

  1. Name the real path, for example Control center → AI Providers, and give the page link. In web chat, write a Markdown link with the path, for example AI Providers. It opens the page in the same tab. To point to one card on AI Providers, add its anchor: #image-parsing, #transcription, #image-generation, #web-search, or #browser-runtime, for example Image generation model. In Telegram, Discord, or WhatsApp, write the path as plain text.
  2. Say who can change it. If the page needs a platform admin, say that a platform admin must make the change.
  3. Give one or two steps, not a generic walkthrough.
  4. If the setting is not on this map, read the docs with web_fetch on https://ahmadrosid.github.io/nakama/llms.txt before you answer.

Layout

  • Left rail (far left): profile avatars to switch agent. At the bottom: the notifications bell and the account avatar.
  • Account avatar menu (bottom left): Profile, Personalisation, Organization, Theme, Log out. It has no Settings item.
  • Sidebar: organization switcher at the top, then New chat, Agent, Groups, Connections, Automations, Control center, then Recents.
  • Control center (/customize) is the hub for configuration. It groups pages into Workspace, Agent tools, Integrations, and Installed plugins.

Roles

  • Platform admin: runs the Nakama install. Only role that can open AI Providers, Skills, and MCP.
  • Org admin: manages one organization.
  • Member and viewer: org roles with less access. Viewers cannot use Groups, Google Meet, Organization, or Browse Files.

Pages

PageWherePathWhat it controlsWho
New chatSidebar/chatStart a chat; pick agent, model, and effort in the composerEveryone
AgentSidebar/profilesAgents (profiles): model, instructions, soul, assigned tools, skills, MCP servers, channels (Telegram, Discord, WhatsApp)Everyone; editing depends on role
GroupsSidebar/groupsGroup chats where agents talk to each otherOrg admin, member
ConnectionsSidebar/connectorsComposio apps and per-user OAuth connectionsPlatform admin, org admin, member
AutomationsSidebar/automationsScheduled automations and their runsEveryone
Control centerSidebar/customizeHub for every page belowEveryone (shows only allowed pages)
NotificationsBell, bottom left/notificationsAutomation runs and org memory proposalsEveryone

Control center → Workspace

PagePathWhat it controlsWho
Organization/organizationMembers, invites, teams, org memory, org settingsPlatform admin, org admin, member
Browse Files/filesAgent artifacts and workspace filesPlatform admin, org admin, member
Usage/customize/usageToken usage and costPlatform admin, org admin
Workers/workersAutomation and channel workers, worker logsPlatform admin, org admin
Google Meet/google-meetMeeting capture and transcriptsOrg admin, member
Settings/settingsAppearance, user context, token usage in chat, version, browser sessions, MFA. Org admin: local API token. Platform admin: Web public URL, Composio, data exportEveryone (sections by role)

Control center → Agent tools

PagePathWhat it controlsWho
AI Providers/customize/providersProvider API keys and models. Cards: Image parsing model, Audio transcription model, Image generation model, web search, browser runtimePlatform admin only
Tools/customize/toolsBuilt-in and custom tools, tool playground, email mailbox setupPlatform admin, org admin
Skills/customize/skillsOrganization skill catalogPlatform admin only
MCP/customize/mcpMCP serversPlatform admin only
Plugins/customize/pluginsInstall and manage pluginsPlatform admin, org admin

Control center → Integrations

PagePathWhat it controlsWho
Notifications/customize/connections/notificationsNotification deliveryPlatform admin, org admin
Composio/connectorsComposio toolkitsPlatform admin, org admin, member
Coding agents/customize/connections/coding-agentsCodex, Claude Code, OpenCode, pi, Cursor Agent setupPlatform admin, org admin
Error tracking/customize/connections/error-trackingError trackingPlatform admin only

Common questions

User asksAnswer
Set the image generation modelControl center → AI Providers (/customize/providers), card Image generation model. Platform admin only. The agent also needs the generate_image tool (Agent → Tools)
Set voice message transcriptionControl center → AI Providers, card Audio transcription model. Platform admin only
Let a text-only model read imagesControl center → AI Providers, card Image parsing model. Platform admin only
Add or fix an API key, reconnect ChatGPT or GrokControl center → AI Providers. Platform admin only
Change an agent's model, tools, or skillsAgent (/profiles), pick the agent
Connect Telegram, Discord, or WhatsAppAgent (/profiles), pick the agent, open its channels
Invite a teammateControl center → Organization (/organization)
Change the themeAccount avatar menu → Theme, or Settings (/settings)

Frequently asked questions

What does the Nakama Guide AI skill do?

Map of the Nakama web app — each page, its path, what it controls, and who can open it. Use when the user asks where or how to find, set, or change something in Nakama itself (models, providers, image generation, tools, skills, members, channels, settings).

Why use Nakama Guide on TypingMind?

Because you install it once and use it with any model. Nakama Guide 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 Nakama Guide in TypingMind?

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

Which AI models can use Nakama Guide?

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 Nakama Guide?

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

Is the Nakama Guide 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
thedotmack logo

Version Bump

thedotmack
CommunityPopular

Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging,…

8.3K
94.1K
1 files
View
shareAI-lab logo

Agent Builder

shareAI-lab
OrganizationPopular

Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or…

12.6K
78.4K
5 files
View
ComposioHQ logo

Changelog Generator

ComposioHQ
OrganizationPopular

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns…

8.7K
75.2K
Instructions
View
ruvnet logo

Agent Authentication

ruvnet
CommunityPopular

Agent skill for authentication - invoke with $agent-authentication

8.7K
73.6K
Instructions
View

Set up your own AI workspace now

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