catalyst-zia — Claude Code skill: OCR, faces, barcodes
Wires Zia's pretrained APIs into your agent: OCR, face analytics, object detection, barcode reading and content moderation. Useful when you need image or text extraction without training a model.
npx skills add catalystbyzoho/agent-skills --skill catalyst-zia -a claude-codeWhat catalyst-zia does
The skill tells the agent how to call Zia services over the API. It ships references/zia-services.md with Node.js and Python examples covering Text Analytics, OCR, Face Analytics, Object Detection, Barcode Reader and moderation. The agent is expected to show both SDK samples or ask which platform you use.
There is a fork in the road. For AutoML, custom model training, ML pipelines, LLM Serving or RAG, the skill stops and points you at catalyst-quickml. So don't pull it into a project that needs a custom-trained model — the routing will hand you off elsewhere.
Check the data center limits before you start. Identity Scanner Document Processing runs in IN DC only, API included. Facial Comparison works over the API from any DC, but console testing is IN DC only. If your project sits in another region, that is worth confirming early.
What it helps with
- pull text off a photo or scan
- compare two faces across images
- locate objects inside a picture
- read a barcode from an uploaded file
- screen user uploads for disallowed content
Example prompts for the agent
- extract the text from this scan with Zia OCR
- compare the faces in these two photos using Facial Comparison
- run sentiment analysis on these reviews with Zia Text Analytics
How to install catalyst-zia
1Skills CLI (Vercel)
npx skills add catalystbyzoho/agent-skills --skill catalyst-zia -a claude-code2Manually: put the files in place
~/.claude/skills/catalyst-zia/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/catalyst-zia/
1Skills CLI (Vercel)
npx skills add catalystbyzoho/agent-skills --skill catalyst-zia -a codex2Manually: put the files in place
.agents/skills/catalyst-zia/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add catalystbyzoho/agent-skills --skill catalyst-zia -a cursor2Manually: put the files in place
.cursor/skills/catalyst-zia/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install catalystbyzoho/agent-skills catalyst-zia2Manually: put the files in place
.github/skills/catalyst-zia/SKILL.md1Skills CLI (Vercel)
npx skills add catalystbyzoho/agent-skills --skill catalyst-zia -a gemini-cli2Platform CLI
gemini skills install https://github.com/catalystbyzoho/agent-skills --path skills/catalyst-ziaManually: put the files in place
.devin/skills/catalyst-zia/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add catalystbyzoho/agent-skills --skill catalyst-zia -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-zia
How do I install catalyst-zia in Claude?
Run npx skills add catalystbyzoho/agent-skills --skill catalyst-zia -a claude-code. The skill lands at ~/.claude/skills/catalyst-zia/SKILL.md.
What does catalyst-zia do?
It gives the agent instructions for calling Zia's pretrained APIs: OCR, face analytics, text analytics, object detection, barcode reading and content moderation. Node.js and Python examples are included.
How is catalyst-zia different from catalyst-quickml?
Zia covers ready-made services. AutoML, custom model training, ML pipelines, LLM Serving and RAG belong to catalyst-quickml, and catalyst-zia routes you there itself.
Source text
SKILL.md · Apache-2.0
--- name: catalyst-zia description: "Catalyst Zia Services — OCR, Face Analytics, Text Analytics, Object Detection, Barcode Reader, and Content Moderation via pre-trained AI APIs. Trigger on 'Zia', 'OCR', 'face detection', 'text analytics', 'object detection', 'barcode', 'content moderation', or 'image recognition'. DC restrictions: Identity Scanner Document Processing is IN DC only (API included); Facial Comparison works via API from any DC (console testing is IN DC only). For QuickML (AutoML, ML pipelines, LLM Serving, RAG) load catalyst-quickml instead." metadata: version: "3.0.0" --- ## How It Works 1. **Identify the capability** — OCR, Face Analytics, Text Analytics, Object Detection, Barcode Reader, Content Moderation (Zia Services). For custom-trained models, AutoML, ML pipelines, or Generative AI (LLM Serving, RAG), STOP and load the **`catalyst-quickml`** skill instead. 2. **Load `references/zia-services.md`** — for all Zia API calls with Node.js and Python examples. 3. **Show both SDK examples** — Zia reference includes Node.js and Python; provide both or ask the user which platform they're using. ## Triggers Use this skill for: "Zia", "OCR", "face detection", "text analytics", "object detection", "barcode reader", "content moderation", "sentiment analysis", "image recognition", "Zia Services", or "Zia API". Route to **`catalyst-quickml`** for: "QuickML", "AutoML", "ML model", "train a model on Catalyst", "ML pipeline", "LLM Serving", "RAG", "predict" (with a custom model). ## References | Reference | Load when the query is about… | |-----------|-------------------------------| | `references/zia-services.md` | All Zia APIs — Text Analytics, OCR, Face Analytics, Object Detection, Barcode Reader, Moderation — SDK examples in Node.js and Python | | `../catalyst-quickml/SKILL.md` | AutoML, ML pipelines, model training/prediction endpoints, LLM Serving, RAG, Knowledge Base |
© catalystbyzoho · Apache-2.0 · catalystbyzoho/agent-skills
