PR workflow: pick the right semver label (no-release / patch / minor / major), decide when to add a changelog blog post, when to update…
Dynamic, vibrant style with thick borders, geometric shapes, high-contrast colors, and expressive typography conveying motion and vitality.
Unified task management and scheduling for AI agents.
Reads PRDs, architectural invariants, and cross-repo contracts from documentation hubs to align technical requirements before…
Use when building reusable infrastructure components with Pulumi for modular, composable cloud resources.
Use when managing multiple environments with Pulumi stacks for development, staging, and production deployments.
Convert or migrate Azure ARM (Azure Resource Manager) templates, Bicep templates, or code to Pulumi, including importing existing Azure…
Generate localized cover images and reusable image prompts from the shared Punk style library for articles, Xiaohongshu notes, WeChat…
Datadog CLI (Rust). OAuth2 auth with token refresh.
Validate, commit, and push.
Commits and pushes all changes (staged, unstaged, untracked) to remote.
When to activate: push notifications, UserNotifications framework, APNs, notification content extensions, rich notifications, notification…
Sub-skill of /pwa-build family. Scaffolds a parametric 3D-globe country-explorer PWA (built on globe.gl/Three.js) from a config.json +…
Progressive Web App patterns with Workbox 7.x, service worker lifecycle, offline-first strategies, and installability.
Generate synthetic evaluation datasets for the PXI eval harness (evals/pxi/).
When to activate: Pydantic v2, data validation, serialization, settings management, pydantic-settings, field validators
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
Python library for working with DICOM (Digital Imaging and Communications in Medicine) files.
Fast high-dimensional fixed effects: OLS, Poisson, IV with multi-way FE; DiD (TWFE, did2s, Sun-Abraham); clustered SEs…
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data.
Use pyo3asyncruntimes for async Python callbacks (~28x faster than spawnblocking for fast ops).