Top Agent Skills

Establishes baseline coding conventions for naming, readability, immutability, and code-quality review across projects.

Review Cisco IOS and IOS-XE configurations, choose read-only show commands, check ACL wildcard masks and interface direction, and build safe change-window verification checklists.

Runs a multi-phase verification pipeline for Laravel projects including environment checks, linting, static analysis, tests with coverage, security scans, and deployment readiness.

Extract full product details from Taobao or Tmall product pages by item ID, including title, price, shop info, images, SKU variants, and attributes.

Runs a structured interview session to sharpen a plan or design through relentless questioning.

Build modern Angular applications with Signals, Standalone Components, Zoneless mode, and SSR/Hydration.

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.

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.

Manage Microsoft Fabric capacities via Azure Resource Manager: provision, scale, suspend, resume, check name availability, and list SKUs using the .NET SDK.

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

Generate user stories following the 3 C's (Card, Conversation, Confirmation) and INVEST criteria, with descriptions, design links, and acceptance criteria.

Transform technical tickets, PRDs, or changelogs into polished, user-facing release notes organized by category.

Identify and design growth loops (flywheels) for sustainable traction, evaluating five proven mechanisms: viral, usage, collaboration, user-generated, and referral.

Create a go-to-market strategy covering marketing channels, messaging, success metrics, and launch timeline for product launches or new market entry.

Analyze user engagement and retention patterns by cohort to identify trends in user behavior, feature adoption, and long-term engagement.

Map growth strategies across market penetration, market development, product development, and diversification to evaluate expansion opportunities.

Conduct a structured SWOT analysis for a product, identifying strengths, weaknesses, opportunities, and threats with actionable strategic recommendations.

Generate a Business Model Canvas with all 9 building blocks for creating, documenting, or analyzing a business model.

Brainstorm an inspiring, achievable, and emotional product vision that motivates teams and aligns stakeholders.

Design pricing strategies grounded in value delivery, competitive positioning, and willingness to pay. Recommends pricing models, tiers, and experiments.

Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to opportunities, solutions, and experiments.

Create CodeTour `.tour` files with persona-targeted, step-by-step walkthroughs anchored to real files and line ranges for onboarding, architecture, PR review, and code explanation.

Compare coding agents head-to-head on reproducible tasks with pass rate, cost, time, and consistency metrics.

Test-drive Django applications with pytest, factory_boy, and Django REST Framework, covering models, views, serializers, and API endpoints.

Manage GitHub repositories: triage issues, review PRs, debug CI/CD, prepare releases, and monitor security alerts using the gh CLI.

Write test-driven Laravel applications using PHPUnit, Pest, model factories, HTTP tests, Sanctum authentication testing, mocking, and coverage.

Turn model work into a production ML system with data contracts, repeatable training, measurable quality gates, deployable artifacts, and operational monitoring.

Browse available agent personas and compose ad-hoc teams of up to 5 agents to work in parallel on a task, then synthesize their results.

Apply comprehensive Python testing strategies using pytest, including TDD methodology, fixtures, mocking, parametrization, and coverage requirements.

Trace every user-facing button through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI inconsistent.

Optimizes Next.js 16+ development with Turbopack for faster bundling, caching, and dev startup, and clarifies when to use Turbopack vs webpack.

Uses a multi-agent generator-evaluator feedback loop to build high-quality applications from a single prompt, inspired by GANs and Anthropic's harness design.

Quick reference for PostgreSQL best practices covering query optimization, schema design, indexing, Row Level Security, and connection pooling.

Organizes 70+ React and Next.js performance optimization rules across 8 priority categories for use when writing, reviewing, or refactoring code.

Provides production-grade Kubernetes YAML patterns and kubectl debugging commands for deploying, managing, and debugging workloads reliably.

Automatically log daily development progress, archive project-specific diaries locally, and sync a fused global diary to Notion or Obsidian.

Audits components and pages for WCAG 2.2 AA accessibility issues and applies practical fixes for touch targets, focus states, contrast, labels, and reduced motion.

Review pull requests following Sentry engineering practices, covering security, performance, testing, and design.

Routes requests to design, create, update, debug, or upgrade GitHub Agentic Workflows by loading the appropriate workflow prompt or skill file.

Automate Semantic Scholar operations such as searching papers, fetching citations, and managing references through the Rube MCP interface.

Extract complete product information from any e-commerce product page using a universal multi-layer extraction strategy.

Search LinkedIn job listings with filters for work type, contract type, experience level, and date posted, then extract full job details including descriptions and salary.

Extract full article contents from WeChat using the BrowserAct API, with keyword search and date filtering.

Analyze Neuropixels extracellular recordings end-to-end with SpikeInterface, covering loading, preprocessing, drift correction, spike sorting, quality metrics, and unit curation.

Converts abstract edge concepts into concrete strategy draft variants with configurable risk profiles and optional exportable ticket YAMLs for downstream validation.

Translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai.

Set up, audit, and debug analytics tracking implementations including GA4, Google Tag Manager, event taxonomy, and conversion tracking.

Provides a foundational motion system for React/Next.js apps using motion/react, including tokens, spring presets, accessibility enforcement, SSR safety, and performance rules.

Call the Gemini API for text generation, chat, multimodal understanding, image/video/audio generation, streaming, function calling, structured output, and managed agents using the Interactions API in Python and TypeScript.

Generates a compact KPI digest showing how key metrics changed over a period and what's driving the movement, using Customer Journey Analytics data.

Extract stored credentials from compromised endpoints using the LaZagne post-exploitation tool to recover passwords from browsers, databases, system vaults, and applications during authorized red team operations.

Deploy and configure Rapid7 InsightVM Security Console and Scan Engines for authenticated and unauthenticated vulnerability scanning across enterprise environments.

Evaluate the financial impact of pricing changes using ARPU, conversion, churn risk, NRR, and payback analysis to make data-driven go/no-go decisions.

Documents Notion's brand design system including color tokens, typography hierarchy, layout spacing, and component geometry across homepage, enterprise, AI, agents, startups, and pricing surfaces.

Design stable, well-documented interfaces that are hard to misuse, including REST APIs, GraphQL schemas, module boundaries, and component props.

Generates kernel-DT overlay fragments to enable 25G/10G/1G MGBE QSFP interfaces on Jetson Thor, verifying pinmux and integrating with the BSP customization workflow.

Parse a Jetson Orin/Thor pinmux XLSM spreadsheet and generate per-pin BCT DTSI files for a custom carrier board.

Finetune the NV-Generate-CTMR MAISI VAE/autoencoder on user-supplied CT or MRI NIfTI volumes using a staged config and datalist workflow.

Add, remove, edit, list, or change the boot default of nvpmodel power modes on Jetson/Tegra platforms (Orin, Thor) by modifying the BSP-side configuration file.

Analyzes Android apps to identify user workflows for AppFunctions, generates Kotlin code to expose them to the Android system, and refines KDoc documentation for AI agent compatibility.