Agent skills

Extracts a user's writing voice from text samples via SICO comparative analysis.

Build a personal tone-of-voice skill ({name}-voice) for any person from their real writing and speaking corpus.

Use when enforcing brand tone, style, and localization rules across copy.

Generate tweets and threads in the style of Trung Phan.

Use when building VoltAgent projects — choose agents vs workflows, layout, memory, and observability patterns.

Use when you need VoltAgent class reference — constructor options, lifecycle, and runtime behavior.

VS Code integration for viewing diffs and comparing files.

Build VS Code extensions from scratch or convert existing JS/React/Vue apps.

This skill should be used when configuring VS Code Port Monitor extension for development server monitoring.

Register a new command in a VS Code extension by updating package.json contributes.commands and src/extension.ts activate function.

Vue 3 debugging and error handling for runtime errors, warnings, async failures, and SSR/hydration issues.

Builds Vue 3 components with Composition API patterns, configures Nuxt 3 SSR/SSG projects, sets up Pinia stores, scaffolds…

A collection of best practices and tips for developing applications using Vue.js.

Analyze live W&B Models and Weave project data using the W&B MCP server, including runs, histories, configs, traces, evaluations…

Schedule a one-shot wakeup at a given time (e.g. for rate-limit auto-resume)

Generate professional walkthrough videos from app screenshots or live sites using Remotion.

Retrieves real-time Walmart category sales reports and market intelligence via Sorftime Wenmai APIs using category node IDs.

Extracts Walmart product listings, pricing, inventory levels, and customer ratings using high-speed API scraping.

Extracts customer reviews, ratings, and feedback metadata from Walmart listings to power voice-of-customer and competitor sentiment…

Walmart integration via Apideck's Ecommerce unified API — same methods work across every connector in Ecommerce, switch by changing…

Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs).