Analytics & Monitoring Agent Skills for Codex CLI

Show experiment dashboard with results, active loops, and progress.

Performs ARA Seal Level 2 semantic epistemic review on Agent-Native Research Artifacts, scoring six dimensions (evidence relevance…

Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator…

Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance.

Adds Arize AX tracing to an LLM application for the first time.

Arize AI skill for production ML monitoring, embedding drift, and performance analysis.

Diagnoses Java application performance issues and JVM problems in real-time using the Alibaba Arthas toolkit.

Scan all projects for stale research, forgotten ADRs, unresolved review conditions, orphaned artifacts, missing traceability, and version…

Printing Press CLI for arXiv. Public Atom API for searching and fetching arXiv e-print metadata.

Multi-model ensemble consultation. Runs 3 models in parallel for diverse perspectives.

Execute AssemblyAI streaming transcription and LeMUR workflows.

Optimize AssemblyAI costs through model selection, feature budgeting,

Install and configure AssemblyAI SDK authentication.

Profile JVM applications with async-profiler — sampling-based CPU, allocation, lock, wall-clock, and hardware-counter profiling that…

Generate Atlas Cloud images and videos through its asynchronous media API with schema-first model selection and credential-safe polling.

Turn incident notes into an evidence-based brief with impact, timeline, causes, and follow-up actions.

Crash-safe, all-or-nothing export of measurement data — temp-file→flush→fsync→rename atomic writes for CSV/JSON/text, path-yield variants…

Collect Attio integration diagnostic evidence -- API health, scopes,

Codebase health dashboard with scores and severity for docs, testing, security, and CI/CD.

Use when an agent, harness, gateway, MCP workflow, or multi-step automation claims completion and the available traces, checkpoints…

Durable, access-scoped, append-only record of who changed what app data, when, and whether it was the agent or a human.