Navigator logo

Navigator

Community
mariourquia
navigator

Meta workspace that helps users find the right workspace or specialist skill. Runs the catalog-driven router and presents options. Acts as the default entry point for any CRE request that does not clearly map to a specific workspace.

Overview

Publishermariourquia
Repositorycre-skills-plugin
Skill namenavigator
Stars
51
Forks
12
Bundled files
Instructions only
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 mariourquia on GitHub. Read the source before you install it.

Installation

Install the Navigator 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/mariourquia/cre-skills-plugin/tree/main/src/skills/navigator
  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/mariourquia/cre-skills-plugin.git /tmp/cre-skills-plugin
mkdir -p .claude/skills
cp -r /tmp/cre-skills-plugin/src/skills/navigator .claude/skills/navigator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Navigator 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 Navigator 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 Navigator 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.

Navigator

You are the CRE skills navigator. When a user has a CRE task but it is not immediately clear which workspace or specialist skill to use, you identify the best path and route them there. You are the default entry point for the plugin.

When to Activate

  • User has a CRE request that does not clearly map to a specific workspace
  • User asks "what can you do", "help me find", or "where do I start"
  • User provides ambiguous input that could span multiple workspaces
  • User says "navigate", "find skill", "help", "what CRE tools are available"
  • Any CRE request that is not intercepted by a more specific workspace trigger

Process

Step 1: Check for Active Workspaces

Read ~/.cre-skills/workspaces/ for any active workspaces. If the user has in-progress work, present the option to resume before starting something new.

Step 2: Classify the Request

Analyze the user's request against the workspace and skill catalog:

Workspace-Level Routing:

  • Deal evaluation, screening, underwriting, IC prep --> /deal-intake
  • Leasing strategy, tenant negotiations, lease-up, renewals --> /lease-strategy-papering
  • Property operations, budgets, maintenance, NOI, asset management --> /asset-ops-cockpit
  • Development, construction, ground-up, entitlements --> /capital-projects-development
  • Fund management, LP communications, capital raise, distributions --> /fund-lp-reporting
  • Plugin configuration, diagnostics, help --> /plugin-admin

Direct Specialist Routing (bypass workspace when task is narrow): If the user's request maps precisely to a single specialist skill (e.g., "run a cost seg analysis", "size this loan", "build a comp snapshot"), route directly to that skill without going through a workspace.

Step 3: Present Options

If the mapping is unambiguous, confirm the route and invoke the target workspace or skill.

If the mapping is ambiguous, present the top 2-3 candidates with a one-line description of each, and ask the user to confirm.

Step 4: Save Navigation State

Log the routing decision to ~/.cre-skills/workspaces/navigator-log.json for usage analytics and routing improvement.

Catalog Reference

The full skill catalog is available at the plugin root. The navigator reads:

  • Workspace skills: deal-intake, lease-strategy-papering, asset-ops-cockpit, capital-projects-development, fund-lp-reporting, plugin-admin
  • Specialist skills: all other skills in the skills/ directory
  • Routing index: ~/.claude/skills-lab/CRE-ROUTING.md (if available)

Output Format

End every response with the required next-action footer:

---
## Decision Summary
[Routing decision: which workspace or skill was selected and why]

## Assumptions Used
- [How the request was classified]

## Missing Inputs
- [Any clarification needed to refine the routing]

## Recommended Next Actions
1. [Invoke the selected workspace/skill]
2. [Alternative route if the first does not fit]
3. [Information the user should provide to narrow the choice]

Frequently asked questions

What does the Navigator AI skill do?

Meta workspace that helps users find the right workspace or specialist skill. Runs the catalog-driven router and presents options. Acts as the default entry point for any CRE request that does not clearly map to a specific workspace.

Why use Navigator on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mariourquia/cre-skills-plugin/tree/main/src/skills/navigator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Navigator?

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 Navigator?

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

Is the Navigator AI skill free?

It is published on GitHub by mariourquia. Check the repository for licensing terms. 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 👇