libllm
libllm - LLM API client for OpenAI-compatible endpoints. LlmApi class handles chat completions and embeddings via HTTP. Supports GitHub Models, Azure OpenAI, and standard OpenAI endpoints. Handles streaming responses, token counting, and multi-tool parallel call fixes. Use for LLM completions, embeddings, and AI model integration.
npx skills add majiayu000/claude-skill-registry --skill libllm --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.
# libllm Skill ## When to Use - Making chat completion requests to LLM providers - Generating text embeddings for vector search - Integrating with OpenAI-compatible APIs - Handling streaming LLM responses ## Key Concepts **LlmApi**: HTTP client for OpenAI-compatible endpoints. Handles authentication, streaming, and response parsing. **DEFAULT_MAX_TOKENS**: Standard token limit for completions. ## Usage Patterns ### Pattern 1: Chat completion ```javascript import { LlmApi } from "@copilot-ld/libllm"; const api = new LlmApi(config, logger); const response = await api.completion([{ role: "user", content: "Hello" }], { model: "gpt-4", maxTokens: 1000, }); ``` ### Pattern 2: Generate embeddings ```javascript const embeddings = await api.embed(["text to embed"]); // Returns array of vectors ``` ## Integration Used by LLM service. Configurable via environment for different providers (OpenAI, Azure, GitHub Models).
- When to Use
- Key Concepts
- Usage Patterns
- Pattern 1: Chat completion
- Pattern 2: Generate embeddings
- Integration
What does the libllm skill do?
libllm - LLM API client for OpenAI-compatible endpoints. LlmApi class handles chat completions and embeddings via HTTP. Supports GitHub Models, Azure OpenAI, and standard OpenAI endpoints. Handles streaming responses, token counting, and multi-tool parallel call fixes. Use for LLM completions, embeddings, and AI model integration.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill libllm --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.