Top Agent Skills

Guide product managers through a complete discovery cycle from problem hypothesis to validated solution using problem framing, customer interviews, synthesis, and experimentation.

Evaluate feature investments using revenue impact, cost structure, ROI, and strategic value to make data-driven build/don't-build decisions.

Provides production-grade techniques for evaluating LLM outputs using LLMs as judges, covering direct scoring, pairwise comparison, bias mitigation, rubric generation, and confidence calibration.

Provides expert guidance for systematic backtesting of trading strategies, covering methodology, stress testing, bias prevention, and result interpretation.

Analyzes 18-month investment scenarios from a news headline by invoking two specialized agents and generating a comprehensive report with sector impacts, stock recommendations, and a critical review.

Generates high-fidelity images using reasoning-driven prompts and structured creative briefs via muapi.ai.

Generate professional-grade brand logos using geometric primitives and negative space, producing minimalist vector-style marks via muapi.ai.

Manage Azure SQL resources (servers, databases, elastic pools, firewall rules, failover groups) using the Azure Resource Manager SDK for .NET.

Provision and manage Azure Cosmos DB accounts, databases, containers, throughput, and RBAC using the .NET Azure Resource Manager SDK.

Scans agent skills for security issues including prompt injection, malicious scripts, excessive permissions, secret exposure, and supply chain risks.

Create publication-quality static, animated, and interactive plots with fine-grained control over every element using Matplotlib's pyplot and object-oriented APIs.

Generate D2 database diagrams from Entity Framework Core models by analyzing DbContext, entities, Fluent API, and migrations.

Defines service level objectives, creates error budget policies, designs incident response procedures, develops capacity models, and produces monitoring configurations and automation scripts for production systems.

Evaluate scientific manuscripts and grant proposals with structured, checklist-based peer review covering methodology, statistics, reproducibility, ethics, and reporting standards.

Frame an epic as a testable hypothesis with target user, expected outcome, and validation method. Use when defining a major initiative before roadmap, discovery, or delivery planning.

Creates, edits, and renders videos and animations from HTML compositions using the HyperFrames framework, handling project state, input adaptation, and workflow routing.

Creates Apple-style soft UI prototypes with squircle cards, spring motion, and ambient mesh backgrounds.

Documents HashiCorp's marketing design system: near-black canvas, per-product accent colors, hashicorpSans typography, and charcoal card surfaces for multi-product brand identity.

Build or update a professional-grade design system in Figma from a codebase, creating variables, tokens, component libraries, theming, and documentation.

Audits local content archives and builds a reusable, structured content engineering project with content units, topic maps, and assembly drafts for ongoing reuse.

Evaluates Google Cloud workloads against the Cost Optimization pillar of the Well-Architected Framework, identifies cost requirements and constraints, and provides actionable recommendations for building, deploying, and managing workloads cost-efficiently.

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

Create Pydantic models following the multi-model pattern with Base, Create, Update, Response, and InDB variants for clean API contracts in Python applications using Pydantic v2.

Manage Azure AI Foundry projects, connections, datasets, indexes, and evaluations using the Java SDK.

Upload, download, list, and manage blobs and containers in Azure Blob Storage using the @azure/storage-blob SDK.

Send custom logs to Azure Monitor via Data Collection Rules and Data Collection Endpoints using the Java SDK.

Manage AWS EC2 virtual machines — instances, security groups, key pairs, AMIs, EBS volumes, Auto Scaling Groups, Spot Instances, Session Manager, placement groups, and instance lifecycle automation.

Captures a read-only health snapshot from a Jetson device, reporting identity, memory, GPU, thermal, power, storage, services, and top processes.

Install and verify cuPyNumeric for Python using conda or pip, including GPU usage checks.

Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.

Trains, evaluates, exports, and runs inference for NVPanoptix3D models that perform panoptic 3D scene reconstruction from posed RGB images, producing 3D panoptic segmentation with occupancy completion.

Deploy a cuOpt REST server and solve routing optimization problems using Python or curl.

Retrieve HTML or JSON from static pages, inspect status codes and headers, follow redirects, or get page source for simple scraping without a full browser session. Supports proxies and redirect control.

Rates an agent's own output on five axes — accuracy, completeness, clarity, actionability, conciseness — producing a structured scorecard with evidence and improvement suggestions.

Design and optimize revenue operations systems that connect marketing, sales, and customer success into a unified revenue engine.

Pressure-test any business idea with a five-angle adversarial panel (Critic, Champion, Analyst, Investigator, Customer) that returns a single GO/RESHAPE/KILL verdict with the cheapest test to de-risk it.

Audit Google Business Profiles, generate neighborhood service area pages, check NAP consistency across directories, create LocalBusiness schema, and write review responses for service-area businesses.

Fetch design context, screenshots, variables, and assets from Figma, and translate Figma nodes into production code using the Figma MCP server.

Generate spoken audio for narration, voiceovers, IVR prompts, and accessibility reads using the OpenAI Audio API with bundled CLI and built-in voices.

Migrate Claude Code configuration, skills, agents, and MCP servers to Codex project and global files.

Generates and writes unit tests for any programming language using a multi-agent pipeline that researches, plans, and implements tests with build and verification steps.

Runs a three-layer verification pipeline on AI-generated output: extracts verifiable claims, finds supporting or contradicting sources via web search, and produces a structured verification report with source links for human review.

Build performant React Native and Expo mobile apps with best practices for list performance, animations, navigation, UI patterns, state management, and monorepo configuration.

Provides practical guidance for building iOS applications with UIKit, SnapKit, and SwiftUI, covering layout, typography, colors, accessibility, navigation, and privacy patterns.

Buy USDC lottery tickets, check jackpots, claim winnings, and manage LP positions on the Base blockchain via the Megapot protocol.

Run computational fluid dynamics simulations using Python, including Navier-Stokes equations, shallow water, and stratified flows with pseudospectral methods and HPC support.

Store and process large N-dimensional arrays with chunking, compression, and parallel I/O, integrating with NumPy, Dask, and Xarray for cloud-native scientific computing.

Search 10 academic literature APIs for papers, preprints, citations, and open-access full text with reproducible provenance.

Build and operate a Havoc C2 framework for authorized red-team engagements, including team server deployment, evasive Demon agent generation, and post-exploitation.

Stand up a Sliver C2 server and listeners, generate cross-platform implants and beacons, and run post-exploitation, pivoting, and BOF/.NET tooling via the armory for adversary emulation.

Hardens managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring.

Detect kernel-level rootkits in Linux memory dumps using Volatility3 plugins and live system scanners to identify hooked syscalls, hidden modules, and tampered structures.

Detect abuse of service accounts through anomalous interactive logons, privilege escalation, lateral movement, and unauthorized access patterns.

Identifies and exploits IPv6-specific vulnerabilities including SLAAC spoofing, Router Advertisement flooding, and IPv6 tunneling during authorized assessments to test dual-stack security controls and IPv6-aware network defenses.

Audit Kubernetes RBAC configurations to identify overly permissive roles, wildcard permissions, dangerous bindings, service account abuse, and privilege escalation paths using kubectl, rbac-tool, KubiScan, and Kubeaudit.

Detect business email compromise (BEC) attacks using email gateway rules, behavioral analytics, and financial process controls.

Performs privilege escalation assessments on compromised Linux and Windows systems to identify paths from low-privilege access to root or SYSTEM-level control.

Automates ingestion, normalization, deduplication, and distribution of threat intelligence feeds from STIX/TAXII, open-source, and commercial sources into SIEM platforms for real-time IOC matching and alerting.

Runs entitlement review and access certification campaigns using SailPoint IdentityIQ, including manager certifications, targeted entitlement reviews, role-based access validation, SOD violation remediation, and automated revocation workflows.

Optimizes database queries and improves performance across PostgreSQL and MySQL systems by analyzing execution plans, designing index strategies, and tuning configurations.