菜单
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.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/mlflow/skills --skill querying-mlflow-metrics命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| 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.
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, Gemini, 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"
Drives a disciplined explore → plan → implement → verify loop for changing an AI agent's behavior with confidence — whether fixing a reported failure or introducing a new requirement, business rule, or policy. Grounds the diagnosis in MLflow traces, codifies the desired behavior as a regression test suite (`mlflow.genai.evaluate` assertions in `@mlflow.test` pytest tests), and iterates the agent — not the test — until green, resisting quick system-prompt patches when the real fix is upstream (missing tool, retrieval source, or capability). Use whenever the user wants to fix or change how an agent behaves — e.g. "fix this issue in my agent", "this answer is wrong", "the agent is hallucinating", "improve my agent based on this trace", "make the agent do X instead of Y", "I want the agent to lead with/prioritize/recommend X", "new business rule: the agent should X", "always/never do X", "change the agent's default behavior" — or shares a trace they want addressed.
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".