Catalyst Basics

Organization

catalystbyzoho

catalyst-basics

Core Catalyst project setup — directory structure, environments, CLI commands, and all Catalyst IDs (Project ID, ZAID, Table ID, Segment ID, Org ID). Trigger on 'start a Catalyst project', 'what is .catalystrc', 'where do I find my Table ID', 'difference between Development and Production', or any Catalyst ID or CLI question.

Overview

Publisher	catalystbyzoho
Repository	`agent-skills`
Skill name	`catalyst-basics`
Stars	70
Forks	17
Bundled files	8
License	Apache-2.0
Links	Skill source Repository

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

Installation

Install the Catalyst Basics 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/catalystbyzoho/agent-skills/tree/main/skills/catalyst-basics
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/catalystbyzoho/agent-skills.git /tmp/agent-skills
mkdir -p .claude/skills
cp -r /tmp/agent-skills/skills/catalyst-basics .claude/skills/catalyst-basics

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

Use it in TypingMind

Enable Catalyst Basics 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 Catalyst Basics 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 Catalyst Basics 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.

⚠️ PRE-FLIGHT CHECK: Before creating any project files, confirm that .catalystrc and catalyst.json exist in the project directory. If they don't:

Use MCP (CatalystbyZoho_List_All_Organizations → CatalystbyZoho_List_All_Projects) to get the org ID and project ID.

Run: catalyst init --org <orgId> -p <projectId> -ni

Never ask the user to run catalyst init interactively. Never create these files manually — they are CLI-generated and must come from the CLI.

How It Works

MCP check first — Before reading any local files, look for CatalystbyZoho_* tools. If available, use MCP to get org ID, project ID, and all resource IDs instead of asking the user.
Account alignment check — do this before catalyst init — MCP and CLI can be authenticated as different accounts. Before running catalyst init --org <id>, verify they match:
```
bash
catalyst whoami
```
Compare the org name shown to the result of CatalystbyZoho_List_All_Organizations. If they differ, run catalyst login --force to re-authenticate the CLI before proceeding.
New to Catalyst? — If the user is setting up Catalyst for the first time or asking "how do I start", load references/quick-start.md for the full walkthrough.
Console navigation — If the user asks how to find IDs, create tables, set permissions, or configure CORS in the console, load references/console-ui-guide.md.
Pre-flight — Confirm .catalystrc and catalyst.json exist. If missing, use MCP to get org/project IDs and run catalyst init --org <orgId> -p <projectId> -ni. Never use interactive catalyst init.
Project structure — Load references/project-basics.md for directory layout, catalyst.json, IDs, and dev-to-prod checklist.
CLI questions — Load references/cli.md for the exact command, flags, and safety rules.
Answer — Provide the specific ID path or CLI command needed. Never ask the user to manually look up IDs when MCP is connected.

Triggers

Use this skill for: "how do I start a Catalyst project", "what is .catalystrc", "where do I find my Table ID / ZAID / Segment ID / Project ID", "difference between Development and Production", "Catalyst project structure", "catalyst.json explained", catalyst init, catalyst deploy, catalyst serve, catalyst login, "how do I set up Catalyst with Claude", "how do I use Catalyst in Cursor", "how do I use Catalyst with GitHub Copilot", "which service should I use", "what Catalyst service for X", or any question about Catalyst IDs, environments, organizations, IDE setup, architecture decisions, or CLI subcommands.

MCP Connection Check (Do This Before Anything Else)

Before reading .catalystrc, asking the user for IDs, or doing anything project-related — check whether Zoho MCP tools are available in your tool list.

Look for tools prefixed with CatalystbyZoho_ (e.g., CatalystbyZoho_List_All_Projects, CatalystbyZoho_List_All_Tables).

If MCP tools ARE available:

Use CatalystbyZoho_List_All_Organizations to get the org ID
Use CatalystbyZoho_List_All_Projects to get the project ID
Use MCP tools to fetch table names, bucket names, ZAIDs, and all other project details directly — do NOT ask the user to copy-paste IDs from the console

If MCP tools are NOT available:

Prompt the user to connect Zoho MCP before proceeding
Guide them to: VS Code → Settings → MCP (or Claude Desktop claude_desktop_config.json) and add the Catalyst MCP server
Fall back to reading .catalystrc and catalyst.json from the local project directory only as a last resort

Never ask the user to manually look up IDs from the console if MCP is connected. Every project detail — org ID, project ID, table IDs, ZAIDs, bucket names — is retrievable via MCP tools. Asking the user to hunt for IDs when MCP is available wastes time and introduces copy-paste errors.

References

Load the relevant reference file for detailed information:

Reference	Contents
`references/quick-start.md`	First-time setup — install CLI, `catalyst init`, find org/project IDs, add a function, serve locally, deploy, create a Data Store table, configure CORS/Authorized Domains
`references/console-ui-guide.md`	Console navigation — finding Project ID/ZAID/Table ID, creating tables with typed columns, enabling App User permissions (Scopes and Permissions), Authorized Domains + CORS toggle
`references/project-basics.md`	Project directory structure, `catalyst.json`, `.catalystrc`, `catalyst-config.json`, environments, dev-to-prod checklist, all Catalyst IDs (Project ID, ZAID, Table ID, Segment ID, etc.)
`references/cli.md`	Full CLI command reference — all subcommands with flags, Slate/AppSail non-interactive setup, `catalyst serve` port behavior, deploy scoping, safety rules, resource-first development order
`references/architecture.md`	Service selection guide — which Catalyst service to use for which pattern, typical stack combinations, DC availability table for regionally restricted services
`references/setup/claude-code.md`	Installing skills and connecting Zoho MCP in Claude Code (Claude Desktop)
`references/setup/cursor.md`	Installing skills and connecting Zoho MCP in Cursor
`references/setup/github-copilot.md`	Installing skills and connecting Zoho MCP in GitHub Copilot (VS Code)

Bundled files

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

Frequently asked questions

What does the Catalyst Basics AI skill do?

Why use Catalyst Basics on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/catalystbyzoho/agent-skills/tree/main/skills/catalyst-basics. 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 Catalyst Basics?

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 Catalyst Basics?

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

Is the Catalyst Basics AI skill free?

Yes. It is published on GitHub by catalystbyzoho 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

Qdrant

NousResearch

OrganizationPopular

Vector search engine for production RAG systems.

Tensorrt Llm

High-throughput LLM inference on NVIDIA GPUs.

Internal Comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal…

Claude Opus 4 5 Migration

anthropics

OrganizationPopular

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

How It Works

Triggers

MCP Connection Check (Do This Before Anything Else)

References

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now