Agent skills for OpenAI Agents SDK

Analyze narrative structures, character arcs, and genre conventions in reality television for academic research and content analysis.

RealityKit API reference — Entity, Component, System, RealityView, Model3D, anchor types, material system, physics, collision, animation…

Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task…

Interactive rebase onto a base branch, resolving conflicts along the way and verifying tests pass.

Use this skill when the user wants a factual reboot analysis for one Nonce mining farm over a specific time range, delivered as a…

Interactive Q&A over an existing recap document.

Post-development recap document generator.

Career forensics — reconstruct what the user actually did from the evidence they left behind (repos, files, notes, vault, old résumés)…

Data visualization with Recharts 3.x including responsive charts, custom tooltips, animations, and accessibility for React applications.

Execute materialized fullstack task files with layer-aware agent routing

Match bank transactions to invoices in Pennylane: find transactions lacking a justification and invoices left unpaid, propose pairings…

Use when drafting an ACM RecSys rebuttal during the author-response window, covering the short narrative RecSys allows, anonymity…

Designs composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect…

Use when positioning an ACM RecSys submission against recommender-systems literature and its neighbors (SIGIR, KDD, WSDM, TheWebConf…

Use when strengthening the reproducibility of an ACM RecSys paper or preparing a RecSys Reproducibility Track submission — pinning dataset…

Use when explaining or planning around ACM RecSys peer review — the mutually-anonymous model with at least three PC members and a Senior…

Use when organizing ACM RecSys supporting material under the venue's no-separate-supplement convention — how to split a recommender paper…

Use when deciding whether a project is a strong ACM RecSys fit, routing among RecSys, SIGIR, KDD, WSDM, TheWebConf, UAI, CHI, and general…

Drive a running recto diff viewer from a companion session: scroll to and highlight code, write a literate tour of prose and quoted diff…

Use when building or reviewing an HTTP service's plumbing.

Use when a query requires analysing files or documents that are too large to