langfuse-core-workflow-a
Provides end-to-end tracing of LLM calls, chains, and agents using Langfuse observability tools.
Install
mkdir -p .claude/skills/langfuse-core-workflow-a && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/8569" && unzip -o skill.zip -d .claude/skills/langfuse-core-workflow-a && rm skill.zipInstalls to .claude/skills/langfuse-core-workflow-a
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Execute Langfuse primary workflow: Tracing LLM calls and spans.Key capabilities
- →Trace OpenAI API calls automatically
- →Manually instrument RAG pipelines with spans
- →Track streaming responses for token usage
- →Integrate with LangChain for automatic tracing
- →Add metadata to traces for context
How it works
The skill integrates Langfuse to trace LLM calls and spans, either automatically wrapping OpenAI clients or through manual instrumentation for complex workflows like RAG pipelines.
Inputs & outputs
When to use langfuse-core-workflow-a
- →Add observability to OpenAI API calls
- →Track token usage and latency
- →Instrument RAG pipelines
- →Debug LLM conversation chains
About langfuse-core-workflow-a
Integrates Langfuse into applications to track LLM interactions, including model latency, token usage, and cost. It supports automated wrapping of OpenAI calls and manual instrumentation for complex agentic workflows.
Execute Langfuse primary workflow: Tracing LLM calls and spans. Use when implementing LLM tracing, building traced AI features, or adding observability to existing LLM applications. Trigger with phrases like "langfuse tracing", "trace LLM calls", "add langfuse to openai", "langfuse spans", "track llm requests".
Prerequisites
Limitations
- →Missing generations if OpenAI wrapper is not applied
- →Orphaned spans if not properly ended
- →No token usage on stream if stream usage is not requested
How it compares
This skill provides automated and manual tracing for LLM interactions, offering detailed observability that is not present in untraced LLM applications.
Compared to similar skills
langfuse-core-workflow-a side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| langfuse-core-workflow-a (this skill) | 0 | 4mo | Review | Intermediate |
| langsmith-fetch | 6 | 10mo | Review | Intermediate |
| mcp-builder | 136 | 7mo | Review | Advanced |
| swarm-advanced | 7 | 8mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
langsmith-fetch
ComposioHQ
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.
mcp-builder
anthropics
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
swarm-advanced
ruvnet
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
agentdb-memory-patterns
ruvnet
Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.
agentdb-advanced-features
ruvnet
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.
reasoningbank-with-agentdb
ruvnet
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.