Catalyst Datastore logo

Catalyst Datastore

Organization
catalystbyzoho
catalyst-datastore

Catalyst Data Store — relational cloud database with ZCQL, CRUD operations, table permissions, and result pagination. Requires MCP connection — check for CatalystbyZoho_* tools before any operation. Trigger on 'Data Store', 'ZCQL', 'create table', 'executeZCQLQuery', 'table permissions', 'ROWID', 'boolean column', 'boolean always true', 'truthy string', 'boolean stored as string', or 'DataStore data types'. You MUST load this skill whenever writing code that reads or writes Data Store data — ZCQL result wrapping, boolean-as-string behavior, and App User permissions are non-obvious and cause silent bugs if skipped.

Overview

Publishercatalystbyzoho
Repositoryagent-skills
Skill namecatalyst-datastore
Stars
70
Forks
17
Bundled files
1
LicenseApache-2.0
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.

  • 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 catalystbyzoho on GitHub. Read the source before you install it.

Installation

Install the Catalyst Datastore 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/catalystbyzoho/agent-skills/tree/main/skills/catalyst-datastore
  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/catalystbyzoho/agent-skills.git /tmp/agent-skills
mkdir -p .claude/skills
cp -r /tmp/agent-skills/skills/catalyst-datastore .claude/skills/catalyst-datastore
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Catalyst Datastore 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 Datastore 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 Datastore 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.

PREREQUISITES — READ THIS FIRST

Before ANY Data Store operation, you MUST verify MCP connectivity.

  • Search for CatalystbyZoho_* tools in your available tool list.
  • If NOT found: STOP. Do NOT write any code, scaffold files, or instruct Console steps. Load catalyst-zoho-mcp skill and guide the user through MCP setup. Do NOT proceed until the user confirms CatalystbyZoho_* tools are visible.
  • If found: Run CatalystbyZoho_List_All_Organizations → CatalystbyZoho_List_All_Projects to set project context, then continue to "How It Works".

Execution Checklist (MUST follow in order)

  • Step 0: Confirm CatalystbyZoho_* tools visible → if none found → STOP, set up MCP first
  • Step 1: Run CatalystbyZoho_List_All_Organizations
  • Step 2: Run CatalystbyZoho_List_All_Projects
  • Step 3: For table creation → CatalystbyZoho_Create_Table | For existing tables → CatalystbyZoho_List_All_Tables
  • Step 4: Proceed with the operation

How It Works

  1. Create or locate the table via MCP — Creating a table? Use CatalystbyZoho_Create_Table directly. Do NOT instruct the user to open the Catalyst Console or create the table manually. Reading/writing data? Use CatalystbyZoho_List_All_Tables to get table IDs. Never ask the user to copy table IDs.
  2. Load references/datastore-basics.md — for CRUD operations, ZCQL syntax, result unwrapping, and permissions setup.
  3. Unwrap ZCQL results — Always remind: rows.map(r => r.TableName). Raw ZCQL results are wrapped; accessing without unwrapping is the #1 Data Store bug.
  4. Permissions — App User permissions are OFF by default. If the query involves a logged-in user reading data, check Console → Table → Scopes & Permissions.
  5. Pagination — ZCQL max 300 rows per query. Use LIMIT offset, count for larger datasets.

Hallucination Guards

Never assert project-specific values from an empty or unread directory. If the working directory has no project files, do not invent or assume timezone, table names, project ID, environment names, or any other project-specific detail. Ask the developer to supply them.

  • Timezone: do not state a timezone for ZCQL date queries unless you have read it from a real project config file. Ask the developer what timezone their project uses.
  • Table names / column names: only use names returned by CatalystbyZoho_List_All_Tables or explicitly provided by the user.

Default to native Node.js response syntax. When writing function code alongside Data Store operations, use res.writeHead() + res.end() — not Express methods (res.status(), res.json()), unless the user explicitly chose the Express template.

Security Checklist

  • App User write permissions are off by default. The App User role has SELECT enabled by default, but INSERT, UPDATE, and DELETE must be manually enabled per table. Go to Console → Table → Scopes and Permissions → App User role → check Insert/Update/Delete for any table your authenticated users need to write.
  • App Administrator has all permissions by default. Never assign the App Administrator role to regular end-users — it grants full read/write/delete access to all tables.

Triggers

Use this skill for: "Data Store", "ZCQL", "catalyst table", "create table", "query data", executeZCQLQuery, "table permissions", "App User permissions", "ROWID", "CREATEDTIME", "Data Store CRUD", "JOIN in ZCQL", "pagination ZCQL", "data store column types", "insert row", "update row", "delete row", or "relational data on Catalyst".

References

ReferenceLoad when the query is about…
references/datastore-basics.mdCRUD, ZCQL queries, result unwrapping, pagination, column types, App User permissions setup, CREATEDTIME timezone gotcha, emoji limitation

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 Datastore AI skill do?

Catalyst Data Store — relational cloud database with ZCQL, CRUD operations, table permissions, and result pagination. Requires MCP connection — check for CatalystbyZoho_* tools before any operation. Trigger on 'Data Store', 'ZCQL', 'create table', 'executeZCQLQuery', 'table permissions', 'ROWID', 'boolean column', 'boolean always true', 'truthy string', 'boolean stored as string', or 'DataStore data types'. You MUST load this skill whenever writing code that reads or writes Data Store data — ZCQL result wrapping, boolean-as-string behavior, and App User permissions are non-obvious and cause...

Why use Catalyst Datastore on TypingMind?

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

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

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 Datastore?

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

Is the Catalyst Datastore 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

Set up your own AI workspace now

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