Catalyst Functions logo

Catalyst Functions

Organization
catalystbyzoho
catalyst-functions

Catalyst serverless functions — all 7 types (Basic I/O, Advanced I/O, Event, Cron, Job, Integration, Browser Logic), handler signatures, catalyst-config.json, Security Rules, API Gateway routing, file uploads, busboy, Express middleware, environment variables, function URL, and function testing. Requires MCP connection — check for CatalystbyZoho_* tools before any operation. Trigger on 'write a function', 'catalyst function', 'API Gateway', 'Security Rules', 'function not found', 'function returns 401', 'busboy', 'middleware', 'function URL', 'environment variable in function', 'duplicate CORS headers', 'CORS error in browser', 'Access-Control-Allow-Origin multiple values', 'function URL 404', 'execute suffix', 'function timeout', 'function hangs', or any function type question. Do NOT use for persistent servers, long-running processes, or Docker deployments — use catalyst-appsail instead.

Overview

Publishercatalystbyzoho
Repositoryagent-skills
Skill namecatalyst-functions
Stars
70
Forks
17
Bundled files
4
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.

  • 4 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 Functions 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-functions
  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-functions .claude/skills/catalyst-functions
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Catalyst Functions 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 Functions 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 Functions 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.

How It Works

Intent check — do this first:

  • If the user is asking a how-to or conceptual question ("how do I write a function", "show me a Basic I/O handler", "how does Security Rules work"), answer directly with the correct code or explanation. Do NOT inspect the working directory, do NOT generate a CLAUDE.md, do NOT switch into codebase-analysis mode. Empty directory = fine for how-to questions.
  • Only inspect the filesystem when the user explicitly asks to scaffold, add, or deploy something in their project.
  1. Verify local scaffold (only when scaffolding, not for how-to questions) — both catalyst init and functions:add support non-interactive mode (CLI v1.27.0+). Check whether .catalystrc exists. If missing, use MCP tools to get the org ID and project ID, then run:

    bash
    catalyst init --org <orgId> -p <projectId> -ni

    Never ask the user to run catalyst init interactively. NI mode can only link an existing project — if none exists, tell the user to create one in the console first. catalyst.json does not exist yet after init -ni — that is expected. Add functions next (this creates catalyst.json):

    bash
    catalyst functions:add --name <name> --type <type> --stack <stack> -ni
    # e.g. catalyst functions:add --name api --type aio --stack node20 -ni
  2. Identify the function type — Basic I/O for simple request/response, Advanced I/O for raw HTTP control, Event for trigger-based, Cron/Job for scheduled, Integration for Zoho service events, Browser Logic for Puppeteer.

  3. Load references/functions-basics.md — for the matching handler signature, catalyst-config.json keys, SDK init pattern, and CORS setup.

  4. Load references/functions-advanced.md — for file uploads (busboy), streaming responses, error handling, or chaining functions.

  5. Load references/api-gateway.md — for routing rules, rate limiting, or gateway-level CORS.

  6. Validate config — Confirm catalyst-config.json uses deployment + execution keys only. Never use function or entry_point.

Response Syntax Default

Always default to native Node.js response syntax. Advanced I/O exposes raw http.ServerResponse — Express methods (res.status(), res.json()) do not exist unless the user explicitly chose the Express template.

  • Native (default): res.writeHead(200, { 'Content-Type': 'application/json' }); res.end(JSON.stringify(data));
  • Express (opt-in only): res.status(200).json(data) — only if the user has express installed and wired as middleware

If you don't know which template the user has, ask or default to native.

Security Checklist

  • Functions are publicly accessible by default. Security Rules sets authentication to optional when a function is created — its URL is globally accessible to everyone with no restrictions. Set "authentication": "required" in the Security Rules JSON for any function that reads or writes user data or sensitive resources.
  • API Gateway replaces Security Rules — do not use both. Enabling API Gateway automatically disables Security Rules. Pick one auth/routing layer per function.

Triggers

Use this skill for: "write a function", "catalyst function", "Basic I/O", "Advanced I/O", "Event function", "Cron function", "Browser Logic", catalyst-config.json, "function handler", "API Gateway", "rate limiting", "busboy", "file upload in function", catalyst deploy --only functions:<function-name>, catalyst functions:add, "function CORS", or any function type or function configuration question.

Deployment command note:

  • Use catalyst deploy --only functions:<function-name> to deploy one function (where functions:<name> targets the function by its folder name).
  • Use catalyst deploy --only functions to deploy all functions at once.

References

ReferenceLoad when the query is about…
references/functions-basics.mdStart here for any function question. Function type selection, Basic I/O and Advanced I/O handler signatures, catalyst-config.json, user-scope vs admin-scope, CORS, Security Rules, execution limits
references/functions-advanced.mdAdvanced I/O patterns only. Express vs raw-http template differences, file uploads (busboy), streaming files from Stratus, error handling patterns, CORS for local dev, local testing, function chaining, ZCQL result unwrapping, HTTP payload limits
references/functions-templates.mdEvent, Cron, Job, or Integration functions. Handler templates for all background/scheduled types, SDK component reference, retry behavior, cold start data, and the full common errors table
references/api-gateway.mdAPI Gateway config only. Enable/disable gateway, routing rules, rate limiting, CORS via gateway

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 Functions AI skill do?

Catalyst serverless functions — all 7 types (Basic I/O, Advanced I/O, Event, Cron, Job, Integration, Browser Logic), handler signatures, catalyst-config.json, Security Rules, API Gateway routing, file uploads, busboy, Express middleware, environment variables, function URL, and function testing. Requires MCP connection — check for CatalystbyZoho_* tools before any operation. Trigger on 'write a function', 'catalyst function', 'API Gateway', 'Security Rules', 'function not found', 'function returns 401', 'busboy', 'middleware', 'function URL', 'environment variable in function', 'duplicate C...

Why use Catalyst Functions on TypingMind?

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

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

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 Functions?

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

Is the Catalyst Functions 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 👇