Trace LLM interactions and manage prompts via Langfuse.
npx skills add https://github.com/gerald-ica/dev-tool-configs --skill langfuse-gerald-ica
Please help me install this Agent Skill. Skill: langfuse Source: https://github.com/gerald-ica/dev-tool-configs/tree/main/gemini/skills/langfuse Command: npx skills add https://github.com/gerald-ica/dev-tool-configs --skill langfuse-gerald-ica
This Skill addresses the challenge of monitoring and improving LLM applications in production by providing expert-level tracing, prompt management, and evaluation tools.
Use the langfuse skill to start tracing an LLM interaction for the chatbot 'customer-service-bot'.
High-intent search queries and answers about installing and using this skill.
LLM tracing captures interactions within your application to enable performance tuning and debugging. This Skill provides scripts to trace LLM interactions in Python or TypeScript, requiring a Langfuse account for API access to monitor and evaluate application behavior.
Prompt management handles versioning to ensure consistent communication with LLMs. This Skill offers tools to manage and track prompt iterations alongside observability features, allowing developers to correlate prompt changes with LLM output quality and application performance.
Yes, you can evaluate LLM outputs using JavaScript or TypeScript. The Skill supports both environments, providing evaluation and scoring mechanisms to assess the quality and effectiveness of model responses directly within your development stack.
Yes, a Langfuse account is required for API access to monitor LLM interactions. The Skill integrates with the Langfuse platform to provide comprehensive observability, tracing, and prompt management capabilities for your production applications.
Dedicated LLM observability tools track specific model interactions, prompt versions, and output quality that standard monitoring misses. This Skill focuses on LLM tracing, prompt management, and evaluation, addressing the unique debugging and cost-optimization needs of LLM-powered applications.
You need prompt management and evaluation when optimizing an LLM chatbot for better user engagement and reduced costs. This Skill allows you to trace interactions, version prompts, and score outputs to systematically assess and improve chatbot performance.
melikhanmutluTrace LLM applications and manage prompts with Langfuse SDKs.
gerald-icaCache LLM prompt prefixes and full responses to reduce computational costs.
JhabbigDesign evaluation frameworks for LLM applications with automated and human scoring.
Lobbi-DocsImplement structured logging, Prometheus metrics, and OpenTelemetry tracing for FastAPI applications.
