Top Agent Skills

Load sharded datasets (npy, Parquet, HDF5, raw binary) into distributed cuPyNumeric arrays using manual partitioning and Legate task launches.

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

Train, evaluate, distill, quantize, export, and run inference for PyTorch-based TAO image classification models with support for multiple backbones.

Assesses NumPy code for cuPyNumeric migration readiness by analyzing source code against an API support manifest and GPU-scaling idioms, producing a structured verdict with per-finding reasoning.

Enables Megatron Fully Sharded Data Parallel in Megatron-Bridge with configuration overrides, code anchors, pitfalls, and verification steps.

Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data, covering correlation testing, available recipes, and multi-GPU examples.

Configure and validate CPU offloading for Megatron Bridge training, including activation offloading and optimizer state offloading with HybridDeviceOptimizer.

Provides guidance on JSX syntax differences between Vue and React, including attribute naming and plugin configuration.

Exports cookies from a local Chrome browser and saves them into a Browserbase persistent context, enabling authenticated browsing sessions via the browse CLI.

Convert browser-use (Python) browser-automation scripts to Stagehand v3 (TypeScript) on Browserbase, replacing opaque agent loops with deterministic pipelines where possible.

Scan installed skills to extract cross-cutting principles and distill them into rules files.

Reduce churn with cancellation flows, save offers, and win-back campaigns.

Conduct and synthesize customer research into actionable insights from interviews, surveys, reviews, and online communities.

Plan website page hierarchy, navigation, URL patterns, and internal linking for improved SEO and user experience.

Submit products to startup, SaaS, and AI directories to build backlinks and drive discovery traffic.

Run a comprehensive SEO audit across technical SEO, on-page SEO, schema, sitemaps, content quality, AI search readiness, and GEO. Orchestrates 12 specialized sub-skills and 7 subagents for full-site analysis.

Optimize content for AI search and LLM citations across AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and similar systems.

Write idiomatic C++ code with modern features, RAII, smart pointers, and STL algorithms. Handles templates, move semantics, and performance optimization.

Simulates Elon Musk with psychological depth and high-fidelity communication, applying first principles thinking, physics-based reasoning, characteristic humor, and authentic controversial opinions.

Write B2B cold emails and follow-up sequences that earn replies, with frameworks for subject lines, personalization, and multi-touch outreach.

Discover, audit, repair, adapt, and design bounded, verifiable AI-agent loops with explicit triggers, actions, stopping conditions, and guardrails.

Guides through client library installation and authentication setup for the Data Manager API, including ADC configuration and required scopes.

Analyze marketing pages and forms to provide actionable recommendations for improving conversion rates.

Discover, compare, audit, repair, adapt, craft, run, debrief, and publish repeatable AI-agent loops for engineering workflows.

Set up, improve, or audit analytics tracking and measurement for marketing and product decisions.

Build AI agents on Cloudflare Workers using the Agents SDK, covering stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, and browser automation.

Set up Cloudflare Turnstile end-to-end: create a widget, deploy a managed siteverify Worker, insert frontend snippets, and validate the integration.

Manage issues, projects, and team workflows in Linear using the Linear MCP server for natural-language project management.

Execute JavaScript in Figma files via the Plugin API to create, edit, and inspect design nodes, variables, and components.

Creates durable command-line tools from API docs, OpenAPI specs, SDKs, or existing scripts, installable as system commands for future use.

Scaffold, build, and refactor ChatGPT Apps SDK projects with a docs-first workflow, combining MCP servers and widget UIs.

Translates natural language data intents into syntactically valid Perfetto SQL queries and executes them against a local trace file using trace_processor.

Create MCP servers using the C# SDK and .NET project templates, covering scaffolding, tool/prompt/resource implementation, and transport configuration for stdio and HTTP.

Migrate .NET projects from per-project package versioning to NuGet Central Package Management (CPM) using Directory.Packages.props, with baseline build capture, version conflict resolution, and post-conversion validation.

Publish and deploy C# MCP servers to NuGet, Docker, Azure, and the MCP Registry.

Analyzes .NET project code coverage and CRAP (Change Risk Anti-Patterns) scores to identify risk hotspots, methods blocking coverage gains, and prioritize where to add tests.

Create or review Blazor components (.razor files) with correct architecture, covering parameters, EventCallback, RenderFragment, lifecycle, async patterns, disposal, and CSS isolation.

Diagnoses and fixes .NET MAUI development environment issues by validating .NET SDK, workloads, Java JDK, Android SDK, Xcode, and Windows SDK with version requirements discovered dynamically from NuGet.

Generates personalized greetings based on the time of day and the person's name.

Resolve IL trim and AOT analyzer warnings in .NET projects to make them compatible with Native AOT and trimming.

Build, configure, and troubleshoot GraalVM Native Image applications using native-image CLI, Maven, or Gradle Native Build Tools, including reachability metadata and issue diagnosis.

Diagnose and root-cause issues with OCI Kubernetes Engine clusters and workloads through evidence-driven investigation.

Build, configure, scaffold, and deploy OCI Functions from a local machine using a dependency-first, Fn-context-guided flow with structured confirmations.

Deploy and verify Multus-based pod multihoming on OKE clusters with existing GVA secondary VNIC node pools, including discovery, manifest generation, and connectivity validation.

Diagnose OCI Functions setup, control-plane, deployment, invocation, and observability issues using a deterministic triage workflow.

Access Expo's official library of ~70 integration examples to find canonical patterns for adding third-party services like Stripe, Clerk, Supabase, and maps to your Expo app.

Deploy, inspect, log-tail, snapshot, and troubleshoot AEM Rapid Development Environments using the Adobe I/O CLI plugin.

Configures replication agents, activates/deactivates content, uses the Replication API programmatically, and troubleshoots distribution issues for Adobe Experience Manager 6.5 LTS.

Migrates legacy AEM (6.x, AMS, on-prem) to AEM as a Cloud Service using BPA CSV or CAM/MCP target discovery, with one-pattern-per-session workflow for scheduler, replication, event listener, HTL lint, dialog, and custom widget migration.

Generate and run Jest tests for Adobe App Builder actions and React Spectrum UI components, including unit, integration, contract, and component tests with mock helpers for Adobe SDKs.

Generates project handover documentation for AEM Edge Delivery Services projects, including authoring, developer, and admin guides.

Generates Playwright-based browser end-to-end tests for Adobe App Builder SPAs and AEM extensions, including configs, test files, and CI workflows.

Initialize an Adobe App Builder project end-to-end without Developer Console UI clicks. Creates the Console project and workspace, subscribes APIs, maps user intent to the right template, runs non-interactive `aio app init`, and guides post-init customization.

Generate React Spectrum UI components for Adobe Experience Cloud Shell SPAs and AEM UI Extensions, including pages, forms, data tables, dialogs, and navigation.

Reference for producing Adobe Document Authoring (DA) and Edge Delivery Services (EDS) compatible content, covering HTML generation, media uploads, admin API usage, and silent-failure rules.

Creates a new AEM Edge Delivery site from scratch, including GitHub repository setup, aem-code-sync installation, initial content creation in DA, and preview URL generation.

Improve cache efficiency, latency, and throughput for AMS deployments using the Adobe Dispatcher Apache HTTP Server module and related HTTPD configuration.

Generate comprehensive technical documentation for developers taking over an AEM Edge Delivery Services project, covering architecture, design system, blocks, and configuration.

Compares 2–5 audience segments side by side across key metrics, identifying winners, losers, and significant differences to inform product decisions and personalization strategy.

Start AEM Workflows on AEM 6.5 LTS using all available triggering mechanisms: Timeline UI, Manage Publication, WorkflowSession API, HTTP Workflow API, and replication-linked triggers.