Latest Agent Skills

Captures desktop screenshots on macOS, Linux, and Windows with support for full screen, specific apps, windows, and pixel regions.

Automate real browsers from the terminal for navigation, form filling, screenshots, data extraction, and UI-flow debugging using a CLI wrapper around Playwright.

Bootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns, Windows App SDK samples, and CommunityToolkit components.

Create, repair, validate, and package Codex-compatible animated pets and spritesheets from character art, brand cues, or reference images.

Debug and fix failing GitHub Actions PR checks by inspecting logs, summarizing failures, and implementing fixes after approval.

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

Generate or edit raster images such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts for use in projects.

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

Inspect Sentry issues, events, and production errors using the Sentry CLI for read-only observability queries.

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

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

Stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI.

Read, create, and review PDF files with visual rendering checks using Poppler, reportlab, pdfplumber, and pypdf.

Plan and execute migrations from Zscaler, Palo Alto, legacy VPN, or SASE stacks to Cloudflare One with policy mapping, rollout plans, and parity analysis.

Send and receive transactional emails using Cloudflare Email Service, including Workers binding, REST API, Agents SDK integration, and email routing with deliverability setup.

Reviews and authors Cloudflare Workers code against production best practices, covering configuration, request handling, architecture, observability, code patterns, and security.

Build stateful, coordinated applications on Cloudflare's edge using Durable Objects with SQLite storage, RPC methods, alarms, and WebSockets.

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

Design, configure, troubleshoot, and review Cloudflare One Zero Trust and SASE deployments across Access, Gateway, WARP, Tunnel, and DLP.

Build secure, isolated code execution environments on Cloudflare Workers using the Sandbox SDK.

Build and manage applications on the Cloudflare platform, including Workers, Pages, storage, AI, networking, security, and infrastructure-as-code.

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.

Develop, deploy, and manage Cloudflare Workers and associated services (KV, R2, D1, Queues, etc.) using the Wrangler CLI with up-to-date commands and configuration.

Audits web performance by measuring Core Web Vitals (LCP, INP, CLS) and supplementary metrics, identifying render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps using Chrome DevTools MCP.

Plan, design, and implement A/B tests and experiments with statistical rigor, or build a growth experimentation program.

Updates StyleSeed engine files in a project by detecting the current setup, comparing versions, and safely applying additive updates without overwriting user code.

Apply named StyleSeed motion to React components using framer-motion, with personality seeds and keyword moves from a motion library.

Query, inspect, and manage Redis databases from the command line using redis-cli, covering connection, data operations, scanning, and server diagnostics.

Implements work from a PRD or set of issues using TDD, typechecking, and regular testing, then reviews and commits the changes.

Run a heuristic evaluation of interactive UIs against Nielsen's 10 usability heuristics and interaction add-ons, scoring the rendered artifact and producing a prioritized fix list.

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

Search jobs, manage applications, and run the employer job lifecycle on the WorkorAI talent marketplace with white-box candidate match explanations.

Score a UI file's design quality 0-100 against StyleSeed's design language with per-category breakdown, worst offenders, and prioritized fix list.

Build and manage Supabase projects including Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, and Queues with security best practices.

Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessions.

Use Expo DOM components to run web code in a webview on native and as-is on web, enabling incremental migration of web code to native.

Scans frontend files for common design system violations using grep-based checks.

Analyze a winning short video's formula and generate a new branded video with your product, character, and language (English or Spanish) for social media ads.

Design value-based pricing, packaging, and monetization strategies for SaaS products, including tier structures, value metrics, and price optimization.

Build native UI with the @expo/ui package: real SwiftUI on iOS and Jetpack Compose on Android rendered from React in an Expo or React Native app.

Design SDKs with APIs that feel native, error messages that guide, and experiences that reduce friction to drive adoption through exceptional developer experience.

Designs, constructs, and improves offers by applying value equation analysis, bonus stacking, guarantee design, scarcity/urgency, naming, and payment structure.

Estimates GPU memory required to load Safetensors or GGUF model weights for inference from the Hugging Face Hub using HTTP Range requests, without downloading weights locally.

Search models, datasets, Spaces, and papers on Hugging Face Hub, retrieve repository details and documentation, run compute jobs, and use Gradio Spaces as AI tools via MCP server tools.

Guides through a structured interview to fill missing fields in a .faf context file, aiming for a 100% completeness score.

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

Turns a rough request into working software via a governed build loop: align first, plan, then iterate one task at a time with deterministic backpressure and holdout-scenario judging.

Orchestrate dynamic multi-agent workflows with parallel agents and adversarial verification via a local daemon, or fall back to native agent orchestration.

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

Set up recurring, self-running marketing workflows that an AI agent executes on a cadence—weekly, daily, or on trigger—to maintain and optimize marketing operations.

Designs and reviews feedback loops for AI agents to ensure goals are machine-decidable, loops are damped, and human judgment is preserved.

Blocks Claude from finishing a session until deterministic quality checks pass: learning library freshness, disk space, and rationalization pattern detection.

Maps a described workflow to the right ECC command-group with run-order and stop condition, and browses all command-group recipe families.

Write growth logs that extract reusable patterns from complex tasks, failures, and learning moments, using a structured template and quality checklist.

Trace and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).

Create Earth2Studio prognostic model wrappers that time-step weather forecasts forward, with triple-inheritance classes, tests, and documentation.

Create Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged AutoModel diagnostics, and generative or diffusion diagnostics.

Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores like S3, GCS, Azure, HTTP, or HuggingFace.

Builds and validates DeepStream GStreamer pipelines through an interactive questionnaire and a BM25 retrieval engine over 270+ verified pipelines.

Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement.