Instruments Python and TypeScript apps to capture and query LLM execution traces.
npx skills add https://github.com/jxtngx/dgx-lab --skill langsmith-trace-jxtngx
Please help me install this Agent Skill. Skill: langsmith-trace Source: https://github.com/jxtngx/dgx-lab/tree/main/.cursor/skills/langsmith-trace Command: npx skills add https://github.com/jxtngx/dgx-lab --skill langsmith-trace-jxtngx
This skill addresses the complexity of monitoring and debugging LLM-powered applications by providing a unified interface for tracing execution flows and analyzing performance metrics.
Use the langsmith-trace skill to list the last 10 traces from your current project and export them to a local directory for analysis.
High-intent search queries and answers about installing and using this skill.
LLM observability monitors application performance through trace instrumentation. It captures LLM calls and nested logic in Python or TypeScript environments, providing structured trace exports that facilitate performance analysis, cost tracking, and dataset generation.
Yes, TypeScript applications are supported for LLM tracing alongside Python. You can instrument your code to automatically capture execution flows, query the last 10 traces from your current project, and export them to a local directory for analysis.
To export traces for regression testing, query your project's trace data to locate the specific execution step where an error occurred. You can then export the filtered traces to a local directory, generating datasets that capture the failure for future testing.
The best way to monitor LLM application performance is by instrumenting your code to capture execution flows automatically. This provides a unified interface to analyze performance metrics, track costs, and identify latency bottlenecks across complex agentic workflows.
No specific dependencies are required to enable LLM trace instrumentation. The skill provides comprehensive observability for Python and TypeScript applications without external components, allowing you to capture LLM calls and query trace data via CLI immediately.
raindrop-aiAutomate Raindrop AI observability integration by installing SDKs and modifying code.
Kushal9889Evaluate LLM agents with behavioral regression, capability assessments, and reliability metrics.
Zhow01Assess and benchmark LLM outputs across automated metrics, human judgments, and safety checks.
neuron-coreTrace Neuron agent execution with Inspector APM observability.
