litellm
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
npx skills add majiayu000/claude-skill-registry --skill litellm-bbgnsurftech-claude-skills-collec --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.
# LiteLLM Unified Python interface for calling 100+ LLM APIs using consistent OpenAI format. Provides standardized exception handling, retry/fallback logic, and cost tracking across multiple providers. ## When to Use This Skill Use this skill when: - Integrating with multiple LLM providers through a single interface - Routing requests to local llamafile servers using OpenAI-compatible endpoints - Implementing retry and fallback logic for LLM calls - Building applications requiring consistent error handling across providers - Tracking LLM usage costs across different providers - Converting between provider-specific APIs and OpenAI format - Deploying LLM proxy servers with unified configuration - Testing applications against both cloud and local LLM endpoints ## Core Capabilities ### Provider Support LiteLLM supports 100+ providers through consistent OpenAI-style API: - **Cloud Providers**: OpenAI, Anthropic, Google, Azure, AWS Bedrock - **Local Servers**: llamafile, Ollama, LocalAI, vLLM - **Unified Format**: All requests use OpenAI message format - **Exception Mapping**: All provider errors map to OpenAI exception types ### Key Features 1. **Unified API**: Single `completion()` fun
- When to Use This Skill
- Core Capabilities
- Provider Support
- Key Features
- Installation
- Llamafile Integration
- Provider Configuration
- API Base URL
- Environment Variable Configuration
- Basic Usage Patterns
- Synchronous Completion
- Asynchronous Completion
- Async Streaming
- Embeddings
Using pip pip install litellm Using uv uv add litellm export LLAMAFILE_API_BASE="http://localhost:8080/v1" export LITELLM_LOG="INFO" # Enable LiteLLM debug logging
What does the litellm skill do?
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill litellm-bbgnsurftech-claude-skills-collec --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.