435 skills · sorted by relevance
Inspect existing LLM application records in Arize to investigate errors, slow operations, or behavior changes. Export traces, which group related operations, or individual operations and conversation sessions as JSON using the ax command-line tool.
Configure OpenTelemetry to send AI application traces, records of execution steps, to Confident AI. Reuse existing exporters, choose the regional endpoint, and add AI-specific attributes without requiring the deepeval Python package.
Run smoke tests, or basic operational checks, for Mastra projects locally or in staging and production. Verify Studio screens, agents, tools, workflows, traces, and memory, then report results, blockers, and skipped checks.
Investigate errors, crashes, and unexpected behavior by reproducing failures, tracing execution, and comparing logs. Tests one explanation at a time, then provides a verified fix, supporting evidence, and tests or safeguards to prevent recurrence.
Inspect Claude Code execution traces in Braintrust, including tool calls and token usage. The guide explains event hooks, troubleshooting missing records, and matching separate parent and sub-agent traces using timestamps and metadata.
Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI/CD quality gates, observability, or cost optimization. Triggers on: "evaluate my agent", "add evaluator", "measure quality", "quality gate", "run evals", "agent too slow", "why is it slow", "reduce latency", "set up observability", "CloudWatch dashboard", "how much does my agent cost", "cost optimization", "logs not showing up", "logs missing", "spans not found", "eval failing", "eval error", "dev traces", "local traces", "agentcore dev traces", "traces to CloudWatch". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.
The English summary is being prepared. Showing the original description.
Collect, normalize, and structure execution traces from instrumented programs (strace, ltrace) into JSON format for downstream analysis. Use when working with system call traces, library call traces, or execution logs that need to be analyzed for debugging, test case reproduction, or verification. Supports parsing strace/ltrace output, filtering noise, extracting debug information, and preparing traces for bug analysis or reproduction workflows.
The English summary is being prepared. Showing the original description.
Investigate slow Paperclip runs, page requests, and CI suites using Honeycomb traces, which show timed operations. Find relevant traces, separate overlapping work, identify dominant delays, and configure optional tracing or add missing measurements.
Fetch execution traces, records of an agent’s actions, from LangSmith Studio to debug LangChain and LangGraph agents. Inspect errors, tool calls, memory operations, execution times, and token usage, or export records for further review.
Capture Unreal Engine traces, export timing and counter data to CSV, and summarize expensive operations. Manage ongoing recordings, browse stored traces, and open Unreal Insights for visual inspection on Windows.
Turn graded execution traces and production logs into model training examples and preferred-versus-rejected response pairs. Select useful records, remove sensitive information, exclude evaluation examples, and preserve links to the original runs.
Reconstruct Windows folder browsing activity from Shellbag registry records using SBECmd and ShellBags Explorer. Investigate traces of deleted directories, disconnected USB drives, and network shares while accounting for limits in what the records and timestamps show.
Use Phoenix to record execution traces, detailed records of an AI application's operations, and investigate problems. Evaluate answers on datasets, compare prompts and models, and set up monitoring through a self-hosted server.
Investigate slow or failing requests in Google Cloud using Cloud Trace. Filter traces by duration or error status, inspect spans representing individual operations, and retrieve related Cloud Logging entries to investigate bottlenecks and exceptions.
Fetch execution traces, records of an agent’s actions, from LangSmith Studio to debug LangChain and LangGraph agents. Inspect errors, tool calls, memory operations, execution times, and token usage, or export records for further review.
Use Phoenix to record execution traces, detailed records of an AI application's operations, and investigate problems. Evaluate answers on datasets, compare prompts and models, and set up monitoring through a self-hosted server.
Set up application monitoring with structured logs, performance metrics, and traces that follow requests across services. Build dashboards and alerts, run load tests, investigate CPU and memory bottlenecks, and estimate future infrastructure capacity.
Profile app launches and individual user flows in iOS Simulator with ETTrace. Collect traces with readable function names, identify CPU-heavy call stacks, and compare performance changes when recording conditions are consistent.
Instruments programs to capture execution traces specifically for reproducing reported bugs, enabling consistent replay and diagnosis of failures. Use this skill when you need to reproduce a bug, capture execution traces for debugging, instrument code to record program behavior, generate replay scripts for bug reproduction, diagnose hard-to-reproduce failures, or perform deterministic replay of program execution. Triggers when users ask to instrument code for tracing, capture execution traces, reproduce bugs, generate replay scripts, or enable deterministic debugging.
The English summary is being prepared. Showing the original description.
Use when you have captured session evidence — session-retro / session- observatory-live traces in .planning/patterns/, tool logs, correction records — and want to induce a reusable skill from it. Segments the traces into candidate skill units (an LLM judgment, not a deterministic parse) and decomposes each candidate into a four-part structured spec: workflow structure, execution semantics, and runtime attachments (verification, safety, rollback, state). It emits a spec object, NOT a finished SKILL.md, and hands that spec to skill-forge. It sits between skill-integration (upstream frequency detector) and skill-forge (downstream author). Backed by Agent-Trace-to-Skill Induction (arxiv 2606.06893v1). Triggers on inducing a skill from captured traces, turning a repeated pattern into a skill spec, and preparing evidence for skill-forge.
The English summary is being prepared. Showing the original description.
Evolve SKILL.md files from agent execution traces using a three-stage pipeline: trajectory collection from observed runs, parallel multi-agent patch proposal for error and success analysis, and conflict-free consolidation of overlapping edits via prevalence-weighting. Based on the Trace2Skill methodology.
The English summary is being prepared. Showing the original description.
VictoriaTraces provider for obz. Covers trace search, trace retrieval by ID, and extension commands for service and operation discovery via the Jaeger-compatible HTTP API. This skill should be used when the user mentions "VictoriaTraces", "obz trace -p vt", or needs to search distributed traces from a VT backend.
The English summary is being prepared. Showing the original description.
ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against `events.properties.$ai_input` / `$ai_output_choices` returns empty — message content lives only on the dedicated `posthog.ai_events` table.
The English summary is being prepared. Showing the original description.
Investigates distributed application performance using PostHog APM (OpenTelemetry span) data via MCP. Use when the user asks about service traces, slow HTTP/database spans, error spans, trace IDs, or span attributes — not AI observability traces or product logs. Uses posthog:query-apm-spans, posthog:apm-trace-get, posthog:apm-services-list, posthog:apm-attributes-list, and posthog:apm-attribute-values-list.
The English summary is being prepared. Showing the original description.