QU

querying-mlflow-metrics

Fetches and analyzes LLM trace metrics and quality evaluations from MLflow.

Install

mkdir -p .claude/skills/querying-mlflow-metrics && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16599" && unzip -o skill.zip -d .claude/skills/querying-mlflow-metrics && rm skill.zip

Installs to .claude/skills/querying-mlflow-metrics

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.

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.
242 charsno explicit “when” trigger
Beginner

Key capabilities

  • Query MLflow tracking servers for trace metrics
  • Analyze token usage summaries and trends
  • Retrieve latency percentiles by trace name
  • Calculate error rates by trace status
  • Fetch quality scores by evaluator
  • Obtain assessment counts by name

How it works

This skill executes the `scripts/fetch_metrics.py` script to query MLflow tracking servers, allowing users to specify metrics, aggregations, dimensions, and time intervals. It retrieves and formats data related to token usage, latency, trace counts, and quality evaluations.

Inputs & outputs

You give it
MLflow server URL, experiment IDs, metric, and aggregations
You get back
Aggregated trace metrics in table or JSON format

When to use querying-mlflow-metrics

  • Analyzing token usage trends
  • Querying LLM operational costs
  • Checking latency percentiles by trace
  • Calculating average quality scores

About this skill

MLflow Metrics

Run scripts/fetch_metrics.py to query metrics from an MLflow tracking server.

Examples

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.

Arguments

ArgRequiredDescription
-s, --serverYesMLflow server URL
-x, --experiment-idsYesExperiment IDs (comma-separated)
-m, --metricYestrace_count, latency, input_tokens, output_tokens, total_tokens
-a, --aggregationsYesCOUNT, SUM, AVG, MIN, MAX, P50, P95, P99
-d, --dimensionsNoGroup by: trace_name, trace_status
-t, --time-intervalNoBucket size in seconds (3600=hourly, 86400=daily)
--start-timeNo-24h, -7d, now, ISO 8601, or epoch ms
--end-timeNoSame formats as start-time
-o, --outputNotable (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.

When not to use it

  • When the task does not involve querying MLflow tracking servers
  • When the metrics needed are not related to traces, token usage, latency, or quality evaluations
  • When the MLflow server URL is not available

Limitations

  • The skill requires an MLflow tracking server URL
  • The skill is limited to the metrics and aggregations supported by `fetch_metrics.py`
  • The skill's output format is either table or JSON

How it compares

This skill provides a standardized script and command-line interface for querying specific MLflow metrics, offering structured access to data compared to manual database queries or custom API calls.

Compared to similar skills

querying-mlflow-metrics side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
querying-mlflow-metrics (this skill)05moReviewBeginner
weights-and-biases37moReviewIntermediate
rebuild-leaderboard01moReviewAdvanced
quant-analyst1032moNo flagsAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry