Agent skill · software engineering · hkuds
cli-anything-novita
Command-line interface for Novita AI - An OpenAI-compatible AI API client for DeepSeek, GLM, and other models.
Why this skill is useful
Provides specific commands and usage patterns for interacting with the Novita API that the AI wouldn't reliably generate on its own.
What it needs
Requires cli-anything-novita, python installed locally. Requires novita account access. About 2k tokens when loaded. Last updated 2026-08-03. 46,739 stars on the source repository.
What this skill does
cli-anything-novita A CLI harness for Novita AI - an OpenAI-compatible API service for AI models like DeepSeek, GLM, and others. Installation This CLI is installed as part of the cli-anything-novita package: Prerequisites: Python 3.10+ Novita API key from novita.ai Usage Basic Commands REPL Mode When invoked without a subcommand, the CLI enters an interactive REPL session: Command Groups Chat Chat with AI models through the Novita API. Command Description --------- ------------- chat Chat with the Novita API stream Stream chat completion Session Session management for chat history. Command Description --------- ------------- status Show session status clear Clear session history history Show command history Config Configuration management. Command Description --------- ------------- set Set a configuration value get Get a configuration value (or show all) delete Delete a configuration value path Show the config file path Utility Command Description --------- ------------- test Test API connectivity models List available models Examples Configure API Key Chat with DeepSeek Test Connectivity Default Models The Novita API supports multiple model providers: Model ID Provider Description ---------- ---------- ------------- deepseek/deepseek-v3.2 DeepSeek DeepSeek V3.2 model (default) zai-org/glm-5 Zhipu AI GLM-5 model minimax/minimax-m2.5 MiniMax MiniMax M2.5 model Output Formats All commands support dual output modes: Human-readable (default): Tables, colors, formatted text Machine-readable (--json flag): Structured JSON for agent consumption For AI Agents When using this CLI programmatically: 1. Always use --json flag for parseable output 2. Check return codes - 0 for success, non-zero for errors 3. Parse stderr for error messages on failure 4. Use absolute paths for all file operations 5. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills hkuds/skills--368dff