Loading...
Loading...
Found 34 Skills
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".
INVOKE THIS SKILL when optimizing, improving, or debugging LLM prompts using production trace data, evaluations, and annotations. Covers extracting prompts from spans, gathering performance signal, and running a data-driven optimization loop using the ax CLI.
Search logs and codebases for error patterns, stack traces, and anomalies. Correlates errors across systems and identifies root causes. Use PROACTIVELY when debugging issues, analyzing logs, or investigating production errors.
Analyze claude-trace JSONL files for session health, patterns, and actionable insights. Use when debugging session issues, understanding token usage, or identifying failure patterns.
View Langfuse session details with all traces. Use when analyzing conversation flows, checking session costs, or debugging multi-turn interactions.
Query Scout APM performance data via REST API. Use when investigating app performance, slow endpoints, error groups, traces, or insights like N+1 queries and memory bloat.
Rust debugging skill for systems programming. Use when debugging Rust binaries with GDB or LLDB, enabling Rust pretty-printers, interpreting panics and backtraces, debugging async/await with tokio-console, stepping through no_std code, or using dbg! and tracing macros effectively. Activates on queries about rust-gdb, rust-lldb, RUST_BACKTRACE, Rust panics, debugging async Rust, tokio-console, or pretty-printers.
Query and analyze distributed traces and spans using DataPrime syntax. Use this skill whenever the user wants to investigate request latency, find slow operations, debug service-to-service calls, look up a trace ID, analyze span durations, check error spans, examine distributed traces, investigate OpenTelemetry/Jaeger tracing data, or query Coralogix spans in any way - even if they don't explicitly mention "DataPrime" or "cx spans".
Bootstrap evaluators from production traces — emit SDK code, a framework-agnostic JSON spec, or publish online LLM-judge evaluators directly to Datadog. Use when user says "bootstrap evaluators", "generate evaluators", "create evals from traces", "eval bootstrap", "write evaluators", "build eval suite", "publish evaluators", or wants to generate BaseEvaluator/LLMJudge code or online judge configs from production LLM trace data. Works with ml_app and optional RCA report or failure hypothesis.
Analyze production Agentforce agent behavior using session traces and Data Cloud. TRIGGER when: user queries STDM session data or Data Cloud trace records; investigates production agent failures, regressions, or performance issues; asks about session traces, conversation logs, or agent metrics; wants to reproduce a reported production issue in preview; runs findSessions or trace analysis queries. DO NOT TRIGGER when: user creates, modifies, or debugs .agent files during development (use agentforce-generate); writes or runs test specs (use agentforce-test); uses sf agent preview for local development iteration; deploys or publishes agents.
Fetch, organize, and analyze LangSmith traces for debugging and evaluation. Use when you need to: query traces/runs by project, metadata, status, or time window; download traces to JSON; organize outcomes into passed/failed/error buckets; analyze token/message/tool-call patterns; compare passed vs failed behavior; or investigate benchmark and production failures.
Visualize a specific transformer decoder layer from an AutoDeploy FX graph text dump as a hierarchical DOT/PNG diagram. Optionally annotate nodes with actual GPU kernel names and durations from an nsys trace. Use when the user wants to visualize, inspect, or debug a layer in an AutoDeploy model graph dump. Triggers on: "visualize layer", "show layer", "graph of layer", "layer visualization", "dump graph layer". Assumes graph dumps already exist in a directory (produced by AD_DUMP_GRAPHS_DIR).