Venice Skills

Install

git clone https://github.com/veniceai/skills.git ~/src/venice-skills
ln -s ~/src/venice-skills/skills ~/.claude/skills/venice

This is third-party code. Review the repository files before installing.

What it does

The repository holds twenty skills, one per area of the Venice API. Each SKILL.md covers endpoints, parameters, a sample request and common pitfalls so the agent writes correct integration code without digging through docs. Dedicated skills help pick a text model by privacy tier, capabilities and cost, handle key or wallet authentication, and deal with payment and rate limit errors. A script checks the skills against the OpenAPI spec in a nightly CI run.

Who it is for. For developers integrating the Venice.ai API into their apps with an agent's help.

Example request

Write a TypeScript function that generates an image with Venice and saves it to a file

Limitations

The skills only describe the API; real requests need a Venice Pro key or a wallet with USDC. Materials are in English. Access to the Venice API from Russia without a VPN is unverified.

How to disable. Remove the venice link or folder from the agent's skills directory, for example ~/.claude/skills/venice.

Security check

• The skills consist of instructions and API references

README in short

The README lists the skills with the API areas they cover and shows where to put the skills folder for Cursor, Claude Code, Codex, OpenCode, Hermes and Cline. It suggests installing by cloning plus symlinks or as a git submodule. There is a template for new skills, an auth quick reference and a spec sync script. MIT licensed.

SKILL.md

---
name: venice-chat
description: Call POST /chat/completions on Venice. Covers the OpenAI-compatible request shape, Venice-only venice_parameters (web search, E2EE, characters, thinking control, X search), multimodal inputs (images/audio/video), tool calls, reasoning controls, streaming, prompt caching, structured output, and model feature suffixes.
---

# Venice Chat Completions

`POST /api/v1/chat/completions` is Venice's main text endpoint. It's OpenAI-compatible, plus a `venice_parameters` object for Venice-only features.

## Use when

- You need LLM text generation, with or without tools, with or without streaming.
- You want multimodal inputs (images, audio, video) to a vision/audio-capable model.
- You want Venice-specific features: web search, E2EE, characters, xAI X/Twitter search, strip-thinking, web scraping.
- You need prompt caching for large system prompts or long documents.
- You need structured (`json_schema`) output.

For the newer Alpha **Responses API**, see [`venice-responses`](../venice-responses/SKILL.md).

## Minimal request

```bash
curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org-glm-5-1",
    "messages": [{"role": "user", "content": "Why is the sky blue?"}]
  }'
```

Response shape is the standard OpenAI `chat.completion` object (`id`, `object: "chat.completion"`, `choices[].message`, `usage`). With `stream: true`, responses come as SSE `data:` lines in `chat.completion.chunk` format.

Related