Stats
Actions
Tags
From mlfts
Tags an MLflow trace or session with key-value pairs. Use when the user wants to add tags, labels, or metadata to a trace after it has been logged. Triggers on "tag trace", "tag this trace", "add tag", "label trace", "tag session".
How this skill is triggered — by the user, by Claude, or both
Slash command
/mlfts:tag-traceThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run `${CLAUDE_SKILL_DIR}/scripts/trace_annotate.py` to add key-value tags to traces.
Run ${CLAUDE_SKILL_DIR}/scripts/trace_annotate.py to add key-value tags to traces.
Tag the most recent trace:
uv run python ${CLAUDE_SKILL_DIR}/scripts/trace_annotate.py tag quality=good
Multiple tags:
uv run python ${CLAUDE_SKILL_DIR}/scripts/trace_annotate.py tag sprint=42 reviewer=alice bug=true
Tag a specific trace:
uv run python ${CLAUDE_SKILL_DIR}/scripts/trace_annotate.py tag --trace-id tr-abc123 quality=good
List recent traces (to find a trace ID):
uv run python ${CLAUDE_SKILL_DIR}/scripts/trace_annotate.py list
tag subcommand| Arg | Required | Description |
|---|---|---|
tags | Yes | One or more key=value pairs (positional) |
--trace-id | No | Trace ID to tag (default: most recent trace) |
list subcommand| Arg | Required | Description |
|---|---|---|
--max-results | No | Number of traces to show (default: 10) |
info.tags dictionarymlflow traces search --filter-string "tag.<key> = '<value>'"quality:good, reviewed:true, sprint:42, bug:truenpx claudepluginhub fmurray/mlfts --plugin mlftsSearches and retrieves MLflow traces by ID, session, user, status, or execution time using CLI commands. Helps debug failed traces and filter trace data.
Queries, tags, evaluates, and manages MLflow traces via MCP tools. Used for debugging, performance analysis, feedback logging, custom scoring, and trace cleanup.
Adds LangSmith tracing to Python/JS LLM apps via LangChain auto-tracing, traceable decorators, or OpenTelemetry; queries/export traces with langsmith CLI.