Agent skills for VS Code

Create valid, reliable assessment items across formats (multiple choice, constructed response, performance tasks) following psychometric…

Generate visual assets from text prompts: PNG images (Gemini / xAI Grok), GLB 3D models (Tripo3D), rigged biped characters, retargeted…

Project directory path (default current directory)

Use when the user needs to bind users or teams to a Mobile Offline Profile so they actually receive offline sync on their devices.

Makes agent reasoning visible, surfaces tradeoffs, and fades help so humans build judgment.

Assumption mapping expert that identifies, categorizes, and prioritizes product assumptions across 4-8 risk categories using devil's…

Use when the mathematical core of a Mathematical Finance (Wiley) manuscript is the bottleneck — adapted for a theory journal, this means…

Expert in Astro framework with static generation and partial hydration patterns

Astro changes since training cutoff (latest: 6.0) — Sessions API, Fonts API, live collections, CSP, route caching, responsive images, SVG…

Set up and evolve Astro content collections with typed schemas and reliable querying patterns.

Astro framework patterns, islands architecture, content collections, rendering strategies, and deployment.

Astro-specific performance optimizations for 95+ Lighthouse scores.

Automated derivation and simplification of Big-O, Big-Omega, and Big-Theta expressions for algorithm analysis

Implements a standardized asynchronous state machine pattern for long-running API tasks to prevent gateway timeouts and system instability.

Design, implement, and review frontend behavior around asynchronous operations such as data fetching, mutations, uploads, polling…

Python asyncio patterns with TaskGroup, structured concurrency, and modern 3.11+ features.

Provides file paths to language-specific extension files for the code-testing pipeline.

Use this skill before answering, planning, or editing any MSTest 3.x-to-4.x upgrade or post-upgrade failure.

Deep formal test smell audit based on academic research taxonomy (testsmells.org).

Interface with AtCoder for Japanese competitive programming contests

Design and review acceptance / end-to-end tests with the four-layer model (spec / DSL / protocol driver / SUT).