// Fetches aggregated trace metrics (token usage, latency, trace counts, quality evaluations) from MLflow tracking servers. Triggers on requests to show metrics, analyze token usage, view LLM costs, check usage trends, or query trace statistics.
Use this when you need to EVALUATE OR IMPROVE or OPTIMIZE an existing LLM agent's output quality - including improving tool selection accuracy, answer quality, reducing costs, or fixing issues where the agent gives wrong/incomplete responses. Evaluates agents systematically using MLflow evaluation with datasets, scorers, and tracing. IMPORTANT - Always also load the instrumenting-with-mlflow-tracing skill before starting any work. Covers end-to-end evaluation workflow or individual components (tracing setup, dataset creation, scorer definition, evaluation execution).
Instruments Python and TypeScript code with MLflow Tracing for observability. Must be loaded when setting up tracing as part of any workflow including agent evaluation. Triggers on adding tracing, instrumenting agents/LLM apps, getting started with MLflow tracing, tracing specific frameworks (LangGraph, LangChain, OpenAI, DSPy, CrewAI, AutoGen), or when another skill references tracing setup. Examples - "How do I add tracing?", "Instrument my agent", "Trace my LangChain app", "Set up tracing for evaluation"
Master dispatcher for all MLflow workflows. Use this skill when the user wants to do anything with MLflow — tracing, evaluating, debugging, or improving an agent. Routes to the right MLflow sub-skill automatically. Triggers on: "use mlflow", "help with mlflow", "mlflow agent", "add mlflow to my project", "trace my agent", "evaluate my agent", or any MLflow task without a specific skill in mind.
Analyzes an MLflow session — a sequence of traces from a multi-turn chat conversation or interaction. Use when the user asks to debug a chat conversation, review session or chat history, find where a multi-turn chat went wrong, or analyze patterns across turns. Triggers on "analyze this session", "what happened in this conversation", "debug session", "review chat history", "where did this chat go wrong", "session traces", "analyze chat", "debug this chat".
Analyzes a single MLflow trace to answer a user query about it. Use when the user provides a trace ID and asks to debug, investigate, find issues, root-cause errors, understand behavior, or analyze quality. Triggers on "analyze this trace", "what went wrong with this trace", "debug trace", "investigate trace", "why did this trace fail", "root cause this trace".
Onboards users to MLflow by determining their use case (GenAI agents/apps or traditional ML/deep learning) and guiding them through relevant quickstart tutorials and initial integration. If an experiment ID is available, it should be supplied as input to help determine the use case. Use when the user asks to get started with MLflow, set up tracking, add observability, or integrate MLflow into their project. Triggers on "get started with MLflow", "set up MLflow", "onboard to MLflow", "add MLflow to my project", "how do I use MLflow".
| name | querying-mlflow-metrics |
| description | Fetches aggregated trace metrics (token usage, latency, trace counts, quality evaluations) from MLflow tracking servers. Triggers on requests to show metrics, analyze token usage, view LLM costs, check usage trends, or query trace statistics. |
Run scripts/fetch_metrics.py to query metrics from an MLflow tracking server.
Token usage summary:
python scripts/fetch_metrics.py -s http://localhost:5000 -x 1 -m total_tokens -a SUM,AVG
Output: AVG: 223.91 SUM: 7613
Hourly token trend (last 24h):
python scripts/fetch_metrics.py -s http://localhost:5000 -x 1 -m total_tokens -a SUM \
-t 3600 --start-time="-24h" --end-time=now
Output: Time-bucketed token sums per hour
Latency percentiles by trace:
python scripts/fetch_metrics.py -s http://localhost:5000 -x 1 -m latency -a AVG,P95 -d trace_name
Error rate by status:
python scripts/fetch_metrics.py -s http://localhost:5000 -x 1 -m trace_count -a COUNT -d trace_status
Quality scores by evaluator (assessments):
python scripts/fetch_metrics.py -s http://localhost:5000 -x 1 -v ASSESSMENTS \
-m assessment_value -a AVG,P50 -d assessment_name
Output: Average and median scores for each evaluator (e.g., correctness, relevance)
Assessment count by name:
python scripts/fetch_metrics.py -s http://localhost:5000 -x 1 -v ASSESSMENTS \
-m assessment_count -a COUNT -d assessment_name
JSON output: Add -o json to any command.
| Arg | Required | Description |
|---|---|---|
-s, --server | Yes | MLflow server URL |
-x, --experiment-ids | Yes | Experiment IDs (comma-separated) |
-m, --metric | Yes | trace_count, latency, input_tokens, output_tokens, total_tokens |
-a, --aggregations | Yes | COUNT, SUM, AVG, MIN, MAX, P50, P95, P99 |
-d, --dimensions | No | Group by: trace_name, trace_status |
-t, --time-interval | No | Bucket size in seconds (3600=hourly, 86400=daily) |
--start-time | No | -24h, -7d, now, ISO 8601, or epoch ms |
--end-time | No | Same formats as start-time |
-o, --output | No | table (default) or json |
For SPANS metrics (span_count, latency), add -v SPANS.
For ASSESSMENTS metrics, add -v ASSESSMENTS.
See references/api_reference.md for filter syntax and full API details.