SkillsAdd

panlm/mlflow-skills · Archived

querying-mlflow-metrics

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.

First seen Apr 23, 2026

Installation

$ npx skills add panlm/mlflow-skills --skill querying-mlflow-metrics
View on skills.sh ↗ GitHub repository ↗

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

analyzing-mlflow-session Same source
panlm/mlflow-skills

Analyzes an MLflow session — a sequence of traces from a multi-turn chat conversation or intera…

1 installs
analyzing-mlflow-trace Same source
panlm/mlflow-skills

Analyzes a single MLflow trace to answer a user query about it. Use when the user provides a tr…

1 installs
searching-mlflow-docs Same source
panlm/mlflow-skills

Searches and retrieves MLflow documentation from the official docs site.

1 installs
retrieving-mlflow-traces Same source
panlm/mlflow-skills

Retrieves MLflow traces using CLI or Python API.

1 installs

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

querying-data-lake Similar name
aws/agent-toolkit-for-aws

Execute and manage Athena SQL queries across default and federated catalogs (Glue, S3 Tables, R…

5K installs
storing-and-querying-vectors Similar name
aws/agent-toolkit-for-aws

Store and query vector embeddings using Amazon S3 Vectors, a cost-effective long-term vector st…

5K installs
querying-aws-s3 Similar name
aws/agent-toolkit-for-aws

Queries S3 object metadata, tracks bucket activity, audits object changes, searches annotations…

3.8K installs
mongodb-natural-language-querying Similar name
mongodb/agent-skills

Generate read-only MongoDB queries (find) or aggregation pipelines using natural language, with…

3.8K installs
querying-aws-cloudwatch Similar name
aws/agent-toolkit-for-aws

Runs SQL queries on CloudWatch Logs data exported as Apache Iceberg tables in S3 Tables. Covers…

3.8K installs
querying-aws-sagemaker-catalog Similar name
aws/agent-toolkit-for-aws

Runs SQL analytics on SageMaker Catalog asset metadata tables exported as Apache Iceberg in S3 …

3.3K installs

Also in this package

Other skills from panlm/mlflow-skills.

npx skills add panlm/mlflow-skills
analyzing-mlflow-session 1 analyzing-mlflow-trace 1 searching-mlflow-docs 1 retrieving-mlflow-traces 1 mlflow-onboarding 1 mlflow-agent 1 instrumenting-with-mlflow-tracing 1 agent-evaluation 1

Browse all from panlm/mlflow-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Also listed on

Alternate registries and mirrors of this skill.

Repository health

Stars 1
License LICENSE
Default branch main
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,500 B
  • docs SUMMARY.md 273 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

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

Arg Required Description
-s, --server Yes MLflow server URL
-x, --experiment-ids Yes Experiment IDs (comma-separated)
-m, --metric Yes tracecount, latency, inputtokens, outputtokens, totaltokens
-a, --aggregations Yes COUNT, SUM, AVG, MIN, MAX, P50, P95, P99
-d, --dimensions No Group by: tracename, tracestatus
-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/apireference.md](references/apireference.md) for filter syntax and full API details.