LLM
Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.
npx skills add majiayu000/claude-skill-registry --skill llm-albertfast-radar-tinder --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides how to implement chat completions for large language models using the z-ai-web-dev-sdk. Enables building conversational AI applications, chatbots, AI assistants, and text-generation features with support for multi-turn conversations, system prompts, and context management.
How it works
- Uses the z-ai-web-dev-sdk in backend code to create chat completions via zai.chat.completions.create with a messages array containing roles like 'system'/'assistant'/'user'.
- Provides examples for Simple Chat, Custom System Prompt, and Thinking (chain-of-thought) modes via SDK calls and CLI equivalents.
- Demonstrates multi-turn conversation handling by maintaining a messages history and adding user and assistant messages before each completion call.
- Shows usage patterns for various scenarios: content generation, data analysis, code generation, debugging, and explanations by supplying role-based prompts and user content.
- Includes several concrete code blocks that initialize ZAI, construct message sequences, and extract the assistant's content from completion.
When to use it
Use this skill when you need to implement backend chat capabilities with an LLM, require multi-turn context, and want to manage system prompts and conversation history within production applications.
What it can touch
- Tools: claude-code (as declared)
- Libraries: z-ai-web-dev-sdk (imported and instantiated in examples)
- Files: references to {Skill Location}/scripts/chat.ts and various code blocks showing usage
Caveats
- z-ai-web-dev-sdk MUST be used in backend code only. Never use it in client-side code.
- Examples rely on predefined system prompts and structured messages; actual behavior depends on the SDK and model configuration.
- The guidance includes many code snippets; execution results depend on environment and API availability.
# LLM (Large Language Model) Skill This skill guides the implementation of chat completions functionality using the z-ai-web-dev-sdk package, enabling powerful conversational AI and text generation capabilities. ## Skills Path **Skill Location**: `{project_path}/skills/llm` this skill is located at above path in your project. **Reference Scripts**: Example test scripts are available in the `{Skill Location}/scripts/` directory for quick testing and reference. See ``{Skill Location}/scripts/chat.ts` for a working example. ## Overview The LLM skill allows you to build applications that leverage large language models for natural language understanding and generation, including chatbots, AI assistants, content generation, and more. **IMPORTANT**: z-ai-web-dev-sdk MUST be used in backend code only. Never use it in client-side code. ## Prerequisites The z-ai-web-dev-sdk package is already installed. Import it as shown in the examples below. ## CLI Usage (For Simple Tasks) For simple, one-off chat completions, you can use the z-ai CLI instead of writing code. This is ideal for quick tests, simple queries, or automation scripts. ### Basic Chat ```bash # Simple question z-ai chat --prompt "
- Skills Path
- Overview
- Prerequisites
- CLI Usage (For Simple Tasks)
- Basic Chat
- With System Prompt
- With Thinking (Chain of Thought)
- CLI Parameters
- When to Use CLI vs SDK
- Basic Chat Completions
- Simple Question and Answer
- Custom System Prompt
- Multi-turn Conversations
- Conversation History Management
Simple question z-ai chat --prompt "What is the capital of France?" Save response to file z-ai chat -p "Explain quantum computing" -o response.json Stream the response z-ai chat -p "Write a short poem" --stream Custom system prompt for specific behavior z-ai chat \ Enable thinking for complex reasoning
What does the LLM skill do?
Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill llm-albertfast-radar-tinder --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.