catalyst-quickml — Claude Code skill: features and setup
The catalyst-quickml skill guides an agent through QuickML tasks, from training prediction models to working with RAG and pricing questions. QuickML must first be activated for the project.
Apache-2.0 476 installs ★ 74 updated 2026-10-23
npx skills add catalystbyzoho/agent-skills --skill catalyst-quickml -a claude-codeWhat catalyst-quickml does
The skill points the agent to task-specific references for training or calling ML models, using LLM Serving and RAG, and checking QuickML plans and billing. For ready-made Zia models that need no training, it directs the agent to the catalyst-zia skill. Data-center availability should be checked first.
Activate QuickML once per project: open QuickML in the console and select “Start Exploring.” Until then, pipelines, models, and endpoints are inaccessible. This is a required setup step.
When a connected Catalyst MCP tool fits the task, the skill says to find it and inspect its schema before use; otherwise, use an SDK. The current JavaScript SDK uses new QuickML(app), while Node.js SDK v2 is deprecated. Prediction calls use predict(endpointKey, inputData). Generative AI is unavailable in AU, SA, and CA data centers; Zia Model Library is available only in IN.
What it helps with
- choose guidance for training or calling an ML model
- find setup steps for LLM Serving, RAG, or Knowledge Base
- check QuickML feature availability by data center
- look up QuickML plans and billing
Example prompts for the agent
- Help me train a QuickML model and publish an endpoint for predictions.
- Show me how to set up RAG and a Knowledge Base in QuickML for this project.
- Explain QuickML pricing and pay-as-you-go billing.
How to install catalyst-quickml
1Skills CLI (Vercel)
npx skills add catalystbyzoho/agent-skills --skill catalyst-quickml -a claude-code2Manually: put the files in place
~/.claude/skills/catalyst-quickml/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/catalyst-quickml/
1Skills CLI (Vercel)
npx skills add catalystbyzoho/agent-skills --skill catalyst-quickml -a codex2Manually: put the files in place
.agents/skills/catalyst-quickml/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add catalystbyzoho/agent-skills --skill catalyst-quickml -a cursor2Manually: put the files in place
.cursor/skills/catalyst-quickml/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install catalystbyzoho/agent-skills skills/catalyst-quickml2Manually: put the files in place
.github/skills/catalyst-quickml/SKILL.md1Skills CLI (Vercel)
npx skills add catalystbyzoho/agent-skills --skill catalyst-quickml -a gemini-cli2Platform CLI
gemini skills install https://github.com/catalystbyzoho/agent-skills --path skills/catalyst-quickmlManually: put the files in place
.devin/skills/catalyst-quickml/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add catalystbyzoho/agent-skills --skill catalyst-quickml -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about catalyst-quickml
How do I install catalyst-quickml in Claude Code?
Run npx skills add catalystbyzoho/agent-skills --skill catalyst-quickml -a claude-code. The skill file is at ~/.claude/skills/catalyst-quickml/SKILL.md.
What does catalyst-quickml do?
It guides an agent through QuickML topics including ML pipelines, prediction endpoints, Generative AI, and pricing. For ready-made Zia models that need no training, it routes to catalyst-zia.
Where are QuickML Generative AI and Zia Model Library available?
Generative AI is available in US, IN, EU, and JP data centers, but not AU, SA, or CA. Zia Model Library is available only in IN.
Source text
SKILL.md · Apache-2.0
--- name: catalyst-quickml description: "Catalyst QuickML — no/low-code ML, Generative AI, and ready-to-use AI platform. Covers (1) Prediction: ML pipelines, classification/regression, text analytics, recommendation, forecasting, clustering, anomaly detection, AutoML, prediction endpoints; (2) Generative AI: LLM Serving (chat, VLM), RAG, Knowledge Base, GenAI endpoints; (3) Zia Model Library: pre-built no-training models; (4) QuickML pricing — subscription plans and pay-as-you-go rates. Trigger on 'QuickML', 'AutoML', 'ML pipeline', 'train a model', 'model endpoint', 'LLM Serving', 'RAG', 'Knowledge Base', 'no-code ML', 'MLOps', or QuickML pricing/cost/billing/plan questions. DC availability: Prediction models all DCs; Generative AI (LLM Serving, RAG, Knowledge Base) NOT in AU, SA, or CA; Zia Model Library IN only." metadata: version: "2.0.0" --- ## Prerequisites Before using QuickML, activate it once per project in the console: > Console → your project → **QuickML** (left sidebar) → click **"Start Exploring"** Skipping this step prevents access to Data connectors, Pipelines, Models, Endpoints, LLM Serving, RAG, and Knowledge Base. This is a one-time activation per project. --- ## How It Works 1. **Check data-center availability first.** ML models: build & publish in US, IN, EU, AU, JP, SA, CA. Generative AI (LLM Serving, RAG, Knowledge Base): US, IN, EU, JP only — not AU, SA, or CA. Zia Model Library inside the QuickML console: IN only. If the feature is regional and the user's DC is unknown, ask before confirming it is available. 2. **Classify the task and load only the matching reference** (load several if the query spans domains): - Build, train, evaluate, or call a **trained ML model** (classification, regression, forecasting, clustering, anomaly detection, text analytics, recommendation, AutoML) → load `references/prediction-basics.md`. - **LLM chat, vision (VLM), RAG, or Knowledge Base** → load `references/generative-ai-basics.md`. - **Plans, rates, free tier, trial, or billing** → load `references/quickml-pricing-basics.md`. - A **pre-built model with no dataset or training** (OCR, face analytics, image moderation, object recognition, barcode, pre-built sentiment/NER/keywords) → STOP and load the **`catalyst-zia`** skill. The standalone Zia Services APIs have their own DC rules, separate from the QuickML-console Zia Model Library. 3. **Tool-first, then SDK, then console.** If a connected Catalyst MCP tool fits the action (pipelines, endpoints, datasets, metrics, LLM/RAG configs), discover it at runtime by name/description and read its schema before calling — do not hardcode tool names. Otherwise use the SDK: the **JavaScript SDK** (`new QuickML(app)`) is current; Node.js SDK v2 (`app.quickML()`) is deprecated. In every published SDK the prediction call is **`predict(endpointKey, inputData)`** — the `runInference` / `run_inference` names on the docs pages do not exist. The agent cannot see the console, so ask the user for UI-only values. 4. **Never fabricate QuickML specifics.** Use only the REST paths, headers, scope (`QuickML.deployment.READ`), and response shapes in the references (verified live). Do not invent response fields — there is no `likelihood_score` or `confidence` — and take anything else from the endpoint's sample in Console → QuickML → Endpoints. Do not invent pricing values the pricing reference does not list. 5. **Console steps must be exhaustive.** For every step, name the exact field, the dropdown/condition to select, the value, and any checkbox — generic steps cause silent misconfiguration (e.g. a Fill Columns rule needs its **condition** set to "missing values", not only a fill value). For anything the references do not cover, fetch the page under <https://docs.catalyst.zoho.com/en/quickml/> as Markdown (`<page-url>/index.md`); if the fetch fails, say so and give the user the URL. ## Triggers Use this skill for: "QuickML", "Catalyst QuickML", "a QuickML endpoint", "training/predicting with a Catalyst model", "no-code ML", "no-code machine learning", "deploy a model", "model endpoint", "MLOps", "AutoML", "ML pipeline", "LLM Serving", "RAG", "pre-built model / Zia model", "OCR / face / image / text model", "QuickML pricing", "QuickML cost", "how much" (for QuickML usage), "billing", "subscription plan", "pay-as-you-go", or "Catalyst plan". ## References | Reference | Load when the query is about… | |-----------|-------------------------------| | `references/prediction-basics.md` | Trained ML models — pipeline types and when to pick each, data connectors, preprocessing and operations, building and training pipelines, AutoML, evaluation metrics, SHAP, creating/publishing endpoints, prediction SDK calls (Java, Python, JavaScript, Node.js v2), limits | | `references/generative-ai-basics.md` | Generative AI — LLM Serving (models, parameters, interaction modes, tool calling), VLM, RAG (modes, retrieval scope, agentic RAG), Knowledge Base uploads (local, WorkDrive, Zoho Learn), GenAI endpoint REST calls (no GenAI SDK methods exist) | | `references/quickml-pricing-basics.md` | QuickML pricing — Catalyst subscription plans, pay-as-you-go unit rates, monthly free tier, add-ons, free trial, billing controls, and the rules for answering pricing questions |
© catalystbyzoho · Apache-2.0 · catalystbyzoho/agent-skills