Newly added
The latest skills published on Agent skills.
Published Jun 17, 2026
Reviews docs and prose against Vercel's Writing Guidelines by fetching the latest rules and reporting findings in a terse file:line format.
Review UI code against Vercel's Web Interface Guidelines — accessibility, UX, and design best practices — with terse file:line findings.
Implements native-feeling animations with React's View Transition API—shared elements, Suspense reveals, list reorder, directional navigation—without third-party animation libraries.
React Native and Expo best practices across list performance, Reanimated animations, navigation, UI patterns, and monorepo config, organized by priority and impact.
Vercel Engineering's 70 React/Next.js performance rules across 8 priority categories—waterfalls, bundle size, server-side, re-renders—for writing, reviewing, and refactoring code.
Runs an observability-first Vercel cost and performance audit, collecting production metrics before investigating metric-backed candidates and producing ranked, file-grounded recommendations.
React composition patterns that scale—compound components, lifted state, context interfaces, explicit variants over boolean props—plus React 19 API changes.
Deploys and manages Vercel projects using token-based auth read from the environment, covering deploy, env vars, domains, and inspection without interactive login.
Discover and install agent skills from the open ecosystem via the npx skills CLI — when you wish you had a skill for some task.
Deploys apps to Vercel, defaulting to preview, by detecting project/git/CLI state and choosing git-push, vercel deploy, link-first, or a no-auth sandbox fallback.
A fast Rust browser-automation CLI for AI agents using Chrome via CDP with accessibility-tree snapshots; a discovery stub that loads live workflows from the CLI itself.
A portable SEO system for React/React-Native-web: one metadata source, canonical URLs, sitemap, robots, RSS, and typed JSON-LD structured data.
A framework-agnostic write-path discipline: the cancel-snapshot-patch-rollback-invalidate optimistic lifecycle, once-per-intent idempotency keys, and multi-cache coherence.
A framework-agnostic field-side observability system: one typed event taxonomy, best-effort non-blocking provider fan-out, real-user Web Vitals, error reporting, and consent gating.
A portable Lighthouse CI performance gate that blocks PRs unless the production build meets Core Web Vitals budgets and category score floors, with median-of-N runs.
A framework-agnostic discipline for type safety at the network edge: one typed API client, parse-don't-validate, a single response envelope, one ApiError type, and branded IDs.
A portable, framework-agnostic React/React Native architecture style: feature modules with page directories, barrel-only imports, server-vs-UI state split, and component-promotion rules.
Domain knowledge for building videos in React with Remotion—frame-based animation via useCurrentFrame/interpolate, sequencing, assets, audio, captions, and rendering.
Deploys Python Flask, Django, or FastAPI code to Azure App Service Linux with smart defaults, creating the resource group, plan, and web app as needed.
Quickly deploys an Azure OpenAI model to the optimal region by checking capacity across regions and using GlobalStandard SKU with sensible auto-calculated defaults.
End-to-end Azure AI Foundry agent lifecycle with azd—scaffold, deploy, invoke, evaluate, optimize, fine-tune, and troubleshoot agents—routing to specialized sub-skills per task.
Fine-tunes models on Azure AI Foundry with SFT, DPO, or RFT, covering dataset prep and validation, grader calibration, training, checkpoint selection, deployment, and evaluation.
Guides Microsoft Entra ID app registration, OAuth 2.0 setup, API permissions, client credentials, and MSAL integration via portal, CLI, or Bicep.
Provisions Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance agent identities via Graph, wiring OAuth fmi_path token exchange and per-agent permissions.
Unified Azure OpenAI deployment router that detects intent and dispatches to quick preset, full customize, or capacity-discovery modes, with shared project and quota validation.
Interactive guided Azure OpenAI deployment giving full control over version, SKU, capacity, RAI policy, and advanced options, with cross-region fallback and live quota checks.
Discovers available Azure OpenAI model capacity across all accessible regions and projects, then validates subscription quota and ranks deployment locations.
Runs pre-deployment Azure readiness checks—IaC build, RBAC, managed identity, what-if—against the deployment plan, recording proof before allowing the validated status.
Assesses and automates Azure workload upgrades between plans, tiers, and SKUs, plus Java SDK modernization and Redis-to-AMR migrations, with idempotent staged steps.
Guides Azure Storage operations and decisions across Blob, Files, Queue, Table, and Data Lake, including access tiers, redundancy, lifecycle, and SDK usage.
Analyzes an Azure resource group and produces a detailed Mermaid architecture diagram plus a markdown report mapping resource relationships, networking, and identity.
Lists and finds Azure resources across subscriptions and resource groups using Azure Resource Graph KQL, including orphaned resources and tag audits.
Assesses reliability of Azure Functions and App Service apps for zone redundancy, ZRS storage, health probes, and multi-region failover, then drives staged CLI or IaC remediation.
Finds the least-privilege Azure RBAC role for an identity and generates the CLI commands and Bicep to assign it, including custom role definitions when no built-in fits.
Checks and manages Azure service limits and capacity via az quota, mapping ARM types to quota names, comparing regions, and submitting increase requests.
Prepares apps for Azure deployment by writing a mandatory deployment plan, then generating Bicep/Terraform, azure.yaml, and Dockerfiles before handing off to validate and deploy.
Diagnoses Azure Event Hubs and Service Bus SDK problems—AMQP link errors, lock loss, idle timeouts, checkpoint resets—mapped to language-specific fixes.
Writes and runs KQL against Azure Data Explorer (Kusto/ADX) for log, telemetry, and time-series analysis, with schema discovery and az CLI fallback.
Produces a production-ready AKS cluster configuration, separating hard-to-change Day-0 choices (networking, API server) from Day-1 features across security, scaling, and cost.
Assesses existing AKS clusters or local manifests against AKS Automatic safeguards, classifying incompatibilities and generating fix diffs without ever mutating the cluster.
Scaffolds, modifies, and prepares GitHub Copilot SDK apps for Azure, auto-detecting @github/copilot-sdk markers and orchestrating prepare/validate/deploy with BYOM model config.
Turns a workload description into an enterprise Azure topology (landing zone, hub-spoke, DR) and generates validated Bicep or Terraform aligned to the Well-Architected Framework.
Systematically triages Azure production incidents across App Service, Container Apps, Functions, AKS, and messaging using resource health, logs, and AppLens.
Executes deployments for already-prepared apps (azd up/deploy, terraform apply, az deployment) with prerequisite checks, RBAC health verification, and built-in error recovery.
Queries Azure costs, forecasts future spend, and optimizes to reduce waste (orphaned resources, VM rightsizing, storage/Redis tuning) via Cost Management APIs and MCP tools.
Router for Azure VM and VMSS tasks: recommend/compare/price sizes, create/provision, troubleshoot connectivity, manage capacity reservations, and Essential Machine Management.
Runs Azure compliance and security audits with azqr plus Key Vault expiration checks, classifying findings by priority and proposing remediation across resources and certs.
Assesses and migrates cross-cloud workloads to Azure (Lambda to Functions, Beanstalk/Heroku to App Service, Fargate/K8s to Container Apps) with reports and code conversion.
Configures Azure API Management as an AI gateway: token limits, semantic caching, content safety, load balancing, token metrics, and MCP/tool rate limiting via az CLI policies.
Router and reference for Azure AI services (AI Search, Speech, OpenAI, Document Intelligence) covering full-text/vector/hybrid search, speech, and OCR via MCP, CLI, and SDKs.
Reference guidance for instrumenting ASP.NET Core, Node.js, and Python web apps with Azure Application Insights via auto-instrument or manual OpenTelemetry SDK setup.
Walks an existing AKS cluster from bare to a running AI model: verify cluster, install the AI Runway controller, assess GPUs, pick an inference provider, and deploy a first model.
Orchestrator for the design-* set that frames the brief, explores options, builds the chosen direction, gates with QA, and ships, routing each request to a sub-skill.
Rebuilds a live site as a clean editable local frontend by extracting design tokens into url-dna.md, then reconstructing in your stack and screenshot-comparing it.
Prepares a QA'd prototype to run cleanly and returns a working link plus run instructions and a review note, choosing local serve, tunnel, or deploy only with explicit consent.
Gathers outside UX signal via convention scans, 3-5 competitor reviews, and pain mining from forums, synthesizing pains/patterns/gaps into a cited research.md for ideation.
Conformance-checks a built prototype against its mockup, context, and success criteria, flagging visual, behavioral, and a11y drift with expected-vs-actual and a verdict.
Wires static screens into a clickable runnable prototype with routing, interaction states, and stubbed data, then verifies the whole happy path plus an error state in a browser.
Reproduces a reference mockup as a runnable frontend, extracting its design system then screenshot-comparing the build and iterating until the gap is minor and explained.
Generates 2-4 structurally distinct UI directions for a screen or flow, each with layout logic, component choices, and explicit optimizes/sacrifices mapped to the success criteria.