Top Agent Skills

Audits fuzzy goals into checkable deliverables using Wittgenstein's philosophy of language, ensuring every word does work.

Helps find and analyze competitors to imitate using a five-filter method, focusing on profitability and feasibility while eliminating personal bias.

Pressure-tests AI Management Systems against ISO 42001 with six forcing questions for certification readiness, internal audits, and new-system onboarding.

Routes research planning, funding, scoping, and synthesis inquiries to one of four sub-skills: clinical research, R&D finance, market research, or product research, using a deterministic decision tree.

Automates CI/CD pipeline setup, quality gates, test runners, and deployment strategies for GitHub Actions.

Subjects every non-trivial decision to a fresh-context adversarial review before it stands, prioritizing correctness over speed for high-stakes or unfamiliar code.

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.

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

Deploy, evaluate, fine-tune, and manage Microsoft Foundry agents end-to-end using Azure Developer CLI and MCP tools.

Manage secrets, cryptographic keys, and certificates in Azure Key Vault using the Python SDK.

Upload, download, list, and manage blobs and containers in Azure Blob Storage using the Python SDK with best-practice authentication via DefaultAzureCredential.

Publish and consume events with Azure Event Grid using the .NET SDK. Supports EventGridEvent, CloudEvent schemas, push and pull delivery, and Azure Functions integration.

Query logs and metrics from Azure Monitor and Log Analytics workspaces using the Python SDK.

Send, receive, and manage messages in Azure Queue Storage using Python with sync and async clients.

Create, manage, and use cryptographic keys in Azure Key Vault from Rust, including RSA, EC, and HSM-protected keys for encryption, signing, and wrapping operations.

Send, receive, and manage Azure Queue Storage messages using the official Rust SDK.

Manage Azure API Center resources including APIs, versions, definitions, deployments, and metadata using the Python management SDK.

Manage Azure Bot Service resources including bots, channels, and connections using the Python SDK.

Store, retrieve, and manage secrets in Azure Key Vault using the official Rust SDK.

Manage container images, artifacts, and repositories in Azure Container Registry using the Python SDK.

Send, receive, peek, and manage messages in Azure Storage Queues using the @azure/storage-queue SDK for TypeScript/JavaScript.

Manage Azure API Management services, APIs, products, subscriptions, and policies using the Python SDK.

Manage SMB file shares, directories, and files in Azure Storage using the Python SDK.

Manage Azure Bot Service resources using the .NET management SDK. Create, configure, and delete bots, channels (DirectLine, Teams, Slack), and connection settings via Azure Resource Manager.

Analyze text and images for harmful content using Azure AI Content Safety, with customizable blocklists and severity thresholds.

Centralized configuration management with feature flags, dynamic refresh, and Key Vault references using the Azure App Configuration SDK for TypeScript.

Manage Azure Data Lake Storage Gen2 with Python SDK for hierarchical file systems, big data analytics, and file/directory operations.

Create and manage persistent AI agents with threads, messages, runs, and tools using the Azure AI Agents SDK for .NET.

Manage Weights & Biases ML experiment tracking instances on Azure using the .NET SDK. Create, configure, list, update, and delete W&B instances with marketplace integration and SSO.

Send real-time messages and manage WebSocket connections using Azure Web PubSub Service SDK for Python.

Extract text, tables, and structured data from documents using Azure Document Intelligence. Process invoices, receipts, IDs, forms, or build custom document models.

Manage Microsoft Playwright Testing workspaces via Azure Resource Manager: create, update, delete workspaces, check name availability, and manage quotas using the .NET SDK.

Run Playwright tests at scale using Azure Playwright Workspaces with cloud-hosted browsers and integrated Azure portal reporting.

Manage Arize AI Observability and Evaluation resources on Azure using the .NET SDK. Create, read, update, and delete Arize organizations via Azure Marketplace.

Extend Microsoft Entra ID authentication flows with custom claims, attribute collection, and OTP delivery using Azure Functions triggers.

Diagnose and optimize slow-loading, high-memory, or low-FPS USD scenes using a structured workflow with profiling, validation, and mutation phases.

Identifies the weakest samples per ground-truth label in NVIDIA TAO VCN Classify experiments by running a Docker container that performs threshold sweep, weakness scoring, and per-lighting expansion, then surfaces top-K weak samples for downstream augmentation or relabeling.

Provides guidance for training Mixture-of-Experts models with long context windows, covering context parallelism sizing, selective recomputation, dispatcher choices, and practical patterns from recent experiments.

Facilitate a structured sprint retrospective to surface insights and produce actionable improvements with owners and deadlines.

Run a pre-mortem risk analysis on a PRD or launch plan, categorizing risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifying by urgency and creating action plans.

Plan a sprint by estimating team capacity, selecting and sequencing stories, and identifying risks.

Reviews and tailors Product Manager resumes against 10 best practices including the XYZ+S formula, keyword optimization, and job-specific customization.

Identify and evaluate the best go-to-market motions for your product across seven proven approaches, with tools and tactics to build a balanced acquisition strategy.

Map stakeholders on a power/interest grid and generate a tailored communication plan for each group.

Estimate market size using TAM, SAM, and SOM with top-down and bottom-up approaches for market opportunity assessment, investor pitches, or market entry evaluation.

Evaluate macro-environmental factors across Political, Economic, Social, Technological, Legal, and Environmental dimensions for strategic planning and market entry assessment.

Identify a North Star Metric and 3-5 supporting input metrics, classify the business game (Attention, Transaction, Productivity), and validate against seven criteria for an effective North Star.

Finds gaps between documented intent and actual implementation in codebases, catching bugs that generic scanners miss because they lack a model of intent.

Reference guide to 9 prioritization frameworks with formulas, when-to-use guidance, and templates — RICE, ICE, Kano, MoSCoW, Opportunity Score, and more.

Rank a backlog of feature ideas by impact, effort, risk, and strategic alignment to identify the top 5 to pursue.

Transform a customer interview transcript into a structured summary with Jobs to Be Done, satisfaction signals, and action items.

Generates feature ideas from PM, Designer, and Engineer perspectives for initial product discovery of a new product.

Prioritize assumptions using an Impact × Risk matrix and suggest targeted experiments for each.

Categorize, evaluate, and prioritize customer feature requests against product goals using strategic alignment, impact, effort, and risk analysis.

Generate new feature ideas for an existing product using multi-perspective ideation from PM, Designer, and Engineer viewpoints, then prioritize the best five.

Design lean startup experiments (pretotypes) for a new product by creating XYZ hypotheses and suggesting low-effort validation methods like landing pages, explainer videos, and pre-orders.

Post tweets and threads, read timelines, search content, and track analytics on X/Twitter using the official API with OAuth authentication.

Manage an Uncloud cluster — deploy services, configure Caddy ingress, add static proxy routes for non-cluster devices, publish ports, scale, inspect logs, and manage machines and volumes with the `uc` CLI.

Measure performance baselines, detect regressions before and after PRs, and compare stack alternatives using browser, API, and build benchmarks.

Scans source code repositories across C++, Android, iOS, and Web to classify files, detect embedded third-party libraries, and produce actionable four-level verdicts per module with interactive HTML reports.