Analytics & Monitoring Agent Skills for OpenAI Agents SDK

Analyzes and classifies raw user feedback to generate prioritized pain points, sentiment trends, NPS calculations, and user personas.

Designs comprehensive event tracking plans and success metric funnels for product features and PRDs.

Initial time-bounded production discovery pass, run during or just after corpus kickstart when observability sources (Dynatrace, APM…

Guide production incident response for Kotlin plus Spring services from first alert through mitigation, diagnosis, and follow-up.

Query Executor's production telemetry — Axiom traces (executor-cloud dataset), prod Postgres via PlanetScale, PostHog product analytics…

Run repeated production discovery over multiple recent time slices, then cross those signals with source code, P5 catalogs, runtime…

Profile a medical-imaging dataset before any modelling decision is made — the acquisition grid, voxel spacing and orientation spread, the…

Progressive verification methodology for debugging complex systems.

Log empirical quality metrics across projects: build pass rate, rework, coverage, discovery time, gate pass rate.

Scan rough markdown, session exports, or pasted prose and isolate each core intent into a structured prompt atom — classified as law…

Adversarially reviews a draft prompt against a versioned rule set to find what will make it underperform — archetype mismatch, wrong…

Designs and optimizes structured prompts, few-shot examples, and system instructions for reliable LLM workflows.

You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional…

Author, edit, or iterate on prompts in the Phoenix prompt playground, including running experiments over a dataset.

Use when designing the proof technique, algorithm, or simulation protocol for an Operations Research (OR) manuscript — choosing the right…

Streams remote audio and manages voice interactions with customizable wake-word detection, speech recognition, and text-to-speech synthesis.

Create HTML dashboards with KPI metric cards, bar/pie/line charts, progress indicators, and data visualizations.

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files.

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data.

When to activate: ETL, data pipeline, Prefect, Airflow, DLT, Polars, batch processing, data quality

When to activate: Python logging, structlog, JSON logs, correlation IDs, log levels, observability setup