Latest Agent Skills

Captures and analyzes Windows debug output (OutputDebugString, DbgPrint/KdPrint) from the command line, with filtering, bounded execution, and remote monitoring.

Write correct, efficient Kusto Query Language queries with coverage of syntax, joins, dynamic types, datetime pitfalls, regex, serialization, memory management, and advanced functions.

Provides Vue.js testing best practices, patterns, and solutions for common pitfalls using Vitest, Vue Test Utils, and Playwright.

Provides best practices for Vue Router 4, including navigation guards, route params, and route-component lifecycle interactions.

Review UI code for compliance with web interface guidelines, accessibility, and UX best practices.

Provides Vue.js best practices and workflow guidance, including architecture planning, component design, reactivity patterns, and performance optimization for Vue 3 projects.

Map requirements to the most suitable VueUse composable and apply correct usage patterns for concise, maintainable Vue.js/Nuxt features.

Build interfaces with UnoCSS using semantic tokens, dark mode parity, and design polish for devtools and landing pages.

Build documentation sites, configure themes, and write Markdown with Vue components using the VitePress static site generator.

Configure and optimize Turborepo monorepo build systems with task pipelines, caching, filtering, and CI integration.

Write and run unit tests with Vitest, a Vite-native testing framework offering Jest-compatible API, mocking, coverage, and snapshot testing.

Configure and use UnoCSS, an instant atomic CSS engine with presets, rules, shortcuts, and integrations for Vite and Nuxt.

Bundle TypeScript and JavaScript libraries with blazing-fast speed powered by Rolldown. Use when building libraries, generating type declarations, bundling for multiple formats, or migrating from tsup.

Create and present web-based slide decks using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features. Ideal for technical presentations, conference talks, code walkthroughs, teaching materials, or developer decks.

Manage Vue application state with Pinia's type-safe store patterns, including state, getters, actions, plugins, and SSR support.

Build and deploy web servers anywhere using Nitro's filesystem routing, caching, tasks, WebSockets, and deployment presets for Node.js, Bun, Deno, Cloudflare, Vercel, and more.

Sets up JavaScript/TypeScript projects with opinionated tooling and conventions including ESLint, TypeScript config, testing with Vitest, and monorepo setup.

Configure Vite build tool, use its plugin API, set up SSR, and migrate to Vite 8 with Rolldown.

Manage Node.js dependencies with pnpm, including workspaces, catalogs, patches, and supply-chain security.

Build full-stack Vue applications with Nuxt 4, covering SSR, file-based routing, auto-imports, server routes, and deployment.

Write Vue 3 Single-File Components using Composition API with TypeScript, covering script setup macros, reactivity system, built-in components, and lifecycle hooks.

Guides contributors through adding, updating, publishing, documenting, validating, and wiring public skills in the BuilderIO/skills repository, covering plain skills, instruction-style skills, app-backed/MCP skills, and Plan skill sync.

Keep long-running agent work within 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.

Forces web searches and reading of official docs before implementing, integrating, or debugging third-party APIs, libraries, and services to ensure accuracy and avoid guesswork.

Orchestrate expensive frontier models as reviewers and cheaper subagents for bounded, token-heavy work to optimize cost and quality.

Orchestrate token-heavy research, coding, and testing by delegating bounded tasks to cheaper subagents while reserving Claude Fable for architecture, synthesis, and final review.

Watch, audit, and fix another agent's work by reconstructing the original request, inspecting evidence, and reporting gaps.

Turn a PR, branch, commit, or git diff into an interactive visual recap with diagrams, file maps, API/schema summaries, annotated diffs, and focused review notes.

Compare, cross-review, and merge competing plans from multiple agents into one executable direction with a clear handoff.

Transform text plans into interactive visual documents with diagrams, code snippets, and review surfaces for coding agents.

Makes completion state obvious at the end of every response using a red/yellow/green status block.

Proceed through ordinary ambiguity by making reasonable assumptions, keeping momentum, validating as you go, and ending with a clear recap of decisions, changes, verification, and residual risk.

Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA, including picking the right base pipeline, designing a tailored UI, and publishing the Space.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Publish and manage research papers on Hugging Face Hub, including creating paper pages, linking papers to models and datasets, claiming authorship, and generating professional markdown-based research articles.

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware, with backend selection between vLLM, Transformers, and accelerate.

Trains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.

Creates reusable command-line scripts and utilities for the Hugging Face API, enabling chaining, piping, and intermediate data processing.

Search the Hugging Face Hub for llama.cpp-compatible GGUF models, select the right quantization, and run them locally with llama-cli or llama-server.

Train or fine-tune language and vision models using TRL or Unsloth on Hugging Face Jobs cloud infrastructure, with support for SFT, DPO, GRPO, and reward modeling, plus GGUF conversion for local deployment.

Fetch dataset metadata, paginate rows, search text, apply filters, and download parquet URLs from the Hugging Face Dataset Viewer API.

Build ML demos on Hugging Face Spaces with ZeroGPU hardware, covering @spaces.GPU decorator usage, duration and quota tuning, process isolation, CUDA availability model, concurrency safety, and build constraints.

Track and visualize ML training experiments with Trackio, including logging metrics, firing alerts, and retrieving data via CLI. Supports real-time dashboards, webhook alerts, and HF Space syncing.

Create, deploy, and debug machine learning applications on Hugging Face Spaces using Gradio, Docker, or Static SDKs, with support for ZeroGPU and dedicated hardware.

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page.

Build interactive web UIs and ML demos in Python using Gradio's core API, components, and patterns.

Queries Hugging Face benchmark leaderboards to find the best AI models for a task, filters by device constraints, and returns a ranked comparison table with scores.

Run state-of-the-art machine learning models directly in JavaScript/TypeScript across browsers and server-side runtimes using Transformers.js.

Search models, datasets, Spaces, and papers on the Hugging Face Hub, retrieve repository details and documentation, run compute jobs, and use Gradio Spaces as AI tools via the Hugging Face MCP server.

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning) with support for SFT, DPO, GRPO, KTO, RLOO, and reward model training via CLI commands.

Estimates the memory required to load Safetensors or GGUF model weights for inference from the Hugging Face Hub, using HTTP Range requests without downloading weights.

Manage Hugging Face Hub resources: download/upload models, datasets, spaces; manage repos, buckets, collections, discussions, and cache; run SQL queries on datasets; authenticate and manage tokens.

Migrates Android apps from the legacy Google Mobile Ads SDK to the Next-Gen SDK with import, class, and method mapping tables.

Uploads audience members to Google products like Customer Match and mobile device ID audiences using the Data Manager API.

Upload offline conversions, enhanced conversions for leads, click conversions, and Google Analytics events using the Data Manager API /v1/events/ingest endpoint.

Integrates Google Mobile Ads SDK interstitial ads into Android and iOS mobile applications, guiding placement at natural app transition points.

Guides through installing and integrating the Google Mobile Ads SDK for Android, iOS, or Unity applications.

Integrates Google Mobile Ads rewarded ads into Android or iOS apps, guiding through loading, callbacks, opt-in UI, and verification.

Evaluates Google Cloud workloads against the Performance Optimization pillar of the Well-Architected Framework, providing actionable recommendations for resource allocation, modular design, elasticity, and monitoring.

Automates detection engineering workflows in Google SecOps by extracting threat intelligence, generating detection opportunities, simulating attacker behavior with synthetic events, evaluating rule coverage, and creating new YARA-L 2.0 rules to close gaps.