Diagnose recent local Codex or agent-thread token use by querying llmly's usage explorer, grouping results by raw tool and session, and…
Choose TokenLab models and fallback chains using public pricing, task fit, latency expectations, and native endpoint needs before writing…
Observability and reliability engineer — SLOs, alerting, instrumentation, and incident response.
FREE — Intelligent tool-call reliability wrapper.
Give a NVIDIA OO agent capabilities — methods as tools, built-in tools (ShellTools, TodoManager), MCP servers, agent skills…
Use this skill when working with scientific research tools and workflows across bioinformatics, cheminformatics, genomics, structural…
ToolUniverse plugin router. STEP 1 BEFORE ANY ANALYSIS: if the data folder contains `*_executed.ipynb`, run `tu run read_executed_notebook…
Use when deciding whether a project fits the Journal of Business & Economic Statistics (JBES) — the methods-with-empirics fit test.
Audit event-emission posture (structured logging, metrics, trace propagation, event-schema consistency) in a target codebase
Debug AI system behavior using traces — prompt reconstruction, output comparison, failure attribution.
Analyze NVIDIA OO Agents execution traces programmatically with the trace-explorer CLI and Python API.
Reads and filters production/traces/decision_ledger.jsonl to display a timeline of agent decisions.
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
Audit LLM observability coverage — trace gaps, logging completeness, cost attribution accuracy.
Turns a set of production traces into discovery interviews — recovering, for each behaviour pattern, the discovery question the user…
Run and use the NVIDIA OO Agents trace viewer — the web UI + OTLP receiver for browsing agent traces and eval results.
OpenTelemetry setup, span context propagation, sampling strategies, Jaeger queries
Parses local CLI transcripts and accurately attributes work packages and commits to specific AI sessions.
When the user wants to implement shipment tracking, product traceability, or supply chain visibility.
Track feature adoption, measure which features users actually use, identify churned/unused features, and surface nudges for low-adoption…
This skill enables Claude to track and optimize application response times.