Tool Catalog

Organization

AlpacaLabsLLC

tool-catalog

Show Arch Studio help, available skills, agents and host-specific commands. Use for help, how do I use Arch Studio, what is Norma, or a capability directory.

Overview

Publisher	AlpacaLabsLLC
Repository	`skills-for-architects`
Skill name	`tool-catalog`
Stars	386
Forks	81
Bundled files	1
License	MIT
Links	Skill source Repository Homepage

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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by AlpacaLabsLLC on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/tool-catalog
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.

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/AlpacaLabsLLC/skills-for-architects.git /tmp/skills-for-architects
mkdir -p .claude/skills
cp -r /tmp/skills-for-architects/skills/tool-catalog .claude/skills/tool-catalog

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tool Catalog 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 Tool Catalog 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 Tool Catalog 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.

tool-catalog

Before acting, read the host contract and this component’s declaration (skill:tool-catalog). Load only applicable modes from the shared catalog; declarations do not grant access or permission. Use the actual host’s delivery route.

Provide read-only help for “help”, “how do I use Arch Studio”, “what is Norma”, available skills, agents and commands. Start with the actual delivery channel and known workspace state when relevant; do not run setup just to answer help.

Read the current component registry and generated practice discovery. Select the requested scope and show names, short purposes and actual host-discovered entry points. A directory is generated from maintained metadata, not a second static skill list. For a broad help request give two or three useful next actions; a focused capability question gets a focused answer.

For Arch Studio onboarding or troubleshooting beyond a directory answer, the Norma support procedure owns that support outcome; its presence does not imply an active email service or shared chat history.

Norma coordinates work; direct skill invocation remains valid. A substantial task may benefit from a workplan and approved team; a quick task needs no extra gate. Records require accessible selected workspace files. For workflows explicitly declared harness-native, the host follows the owner's complete procedure using its actual capabilities; no Arch Studio runner or executable installation is required. Report the selected workflow's actual declaration and any unresolved capability gap; do not infer catalog-wide execution support. A hosted connection or a displayed skill alone proves neither file access nor completed work. Optional agent profiles are available only when actual host registration/delegation is observed, including the Norma worker after context and approval are resolved.

This directory procedure has no registered operation IDs or record effects. Read its maintained metadata through the actual delivery channel and use the completion contract. Do not invent dispatch operations, run an installer, activate another workflow or perform setup merely to answer a help question. Report unknown host capabilities as unknown.

For external-source directories use the source catalog with geography/topic filtering. Return matching original links, distinguish code sources from related datasets, and state available-manifest coverage. No content retrieval, studio setup or permission is required for listing. Missing LA routes do not substitute NYC. See moments for state facts and the source contract for interpretation boundaries.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

host-contract.json1 KB

Frequently asked questions

What does the Tool Catalog AI skill do?

Show Arch Studio help, available skills, agents and host-specific commands. Use for help, how do I use Arch Studio, what is Norma, or a capability directory.

Why use Tool Catalog on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AlpacaLabsLLC/skills-for-architects/tree/main/skills/tool-catalog. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Tool Catalog?

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 Tool Catalog?

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

Is the Tool Catalog AI skill free?

Yes. It is published on GitHub by AlpacaLabsLLC 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.

View all

Faiss

NousResearch

OrganizationPopular

Fast vector similarity search at billion scale.

Serving Llms Vllm

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Huggingface Hub

HuggingFace hf CLI: search/download/upload models, datasets.

Pytorch Lightning

Clean training loops with built-in distributed support.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

tool-catalog

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now