Analytics & Monitoring Agent Skills for OpenAI Agents SDK

Implement and extend PostHog Data warehouse import sources.

Analyze development-set disagreements between human annotations and one Coval text LLM judge, then propose a focused prompt revision.

Read and, after human approval, update the Linear `incident-alert` knowledge base.

Analyze an incident and turn durable findings into operational corpus knowledge.

Use when defining eligibility criteria and coding studies for a Psychological Bulletin review or meta-analysis — inclusion/exclusion…

Run 150+ AI apps (image, video, LLM) via inference.sh CLI.

Register and safely consume any information source that can enrich the corpus: APM, log database, SQL table, API, file export, wiki…

How to instrument PostHog's own Metrics product from PostHog-owned code — record counters, gauges, and histograms that land in…

Use when adding a new model or pipeline to diffusers, setting up file structure for a new model, converting a pipeline to modular format…

When the user needs to know whether the integrations wired into a customer account are actually working — per connector, per error class…

Transforms raw datasets into verified, interactive React visualization dashboards through structured design tokens and multi-layer…

Solve an interactive grid game by learning a compressed world model (encode state to a latent z, learn a predict function), planning…

Use when packaging code, models, and audio artifacts for an INTERSPEECH paper — anonymous demo pages and sample audio during double-blind…

Use when hardening the reproducibility of an INTERSPEECH paper — pinning corpus versions and official splits, publishing…

17/06: understand the Gemini/Antigravity quota limits + audit/correct your monitoring (comes back on 17/06).

Open, convert, export, and validate local and optional remote

Automate Ip2location tasks via Rube MCP (Composio).

Use when designing or auditing IROS experiments — real-robot trial counts, success criteria set in advance, reset procedures, failure…

Run a buoyancy audit — assess how well a system will improve as models improve.

Every public tool in this KI, by exact path.

Read-only Itô basket and prediction-market data skill.