Latest Agent Skills

Monitors a deployed URL for regressions after releases by checking HTTP status, console errors, network failures, performance metrics, content integrity, API health, static assets, and SSE streams.

Searches local, marketplace, GitHub, and web sources for existing skills before creating a new one to avoid duplication.

Test-driven development for Quarkus 3.x LTS using JUnit 5, Mockito, REST Assured, Camel testing, and JaCoCo. Use when adding features, fixing bugs, or refactoring event-driven services.

Create animated technical explainers using Manim for graphs, workflows, system diagrams, and product walkthroughs with precise motion and clear scene planning.

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

Provides Playwright patterns for building stable, fast, and maintainable E2E test suites, including Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

Write, fix, and run C++ tests using GoogleTest/GoogleMock with CMake/CTest, including TDD workflows, coverage, and sanitizers.

Provides guidance on using Bun as a JavaScript runtime, package manager, bundler, and test runner, including migration from Node.js and Vercel deployment.

Build a reusable writing style profile from real source material like posts, essays, and docs, then apply it across content, outreach, and social workflows for consistent brand voice.

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

Search the web, code, companies, and people using the Exa MCP server for current information and technical research.

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

Automates visual testing and UI interaction verification using browser automation after deploying features.

Design consistent, developer-friendly REST APIs with conventions for resource naming, HTTP methods, status codes, pagination, filtering, error responses, versioning, and rate limiting.

Build persistent multi-agent operating systems on Claude Code with kernel architecture, specialist agents, slash commands, file-based memory, and scheduled automation.

Classifies ECC components (skills, commands, rules, hooks) into DAILY and LIBRARY buckets based on evidence from the actual codebase, producing an install plan and verification report.

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

Batch-convert UI design screenshots into Vue 3 Composition API components using Vant, Element Plus, or Ant Design Vue.

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.

Provides a production-ready UI motion system for React/Next.js with performance, accessibility, and usability guidelines.

Forces AI agents to investigate before editing or running destructive commands, improving code quality by requiring concrete facts like importers, data schemas, and user instructions.

Organize email inbox, draft replies, send messages, and verify delivery with evidence-based confirmation.

Navigate and understand Everything Claude Code by reading the live repository surface to answer questions about agents, skills, commands, hooks, rules, install profiles, and project onboarding.

Adapts and distributes content across X, LinkedIn, Threads, and Bluesky while preserving the author's voice and platform-specific constraints.

Periodically scans Claude Code configuration for redundant, stale, or orphaned items and walks the user through a confirm-each-deletion cleanup.

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.

Generate a step-by-step construction plan from a one-line objective, with dependency graphs, parallel step detection, and adversarial review for multi-session engineering projects.

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

Ingest, index, search, edit, and generate video and audio content from files, URLs, live streams, or desktop capture.

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.

Record polished UI demo videos using Playwright with visible cursor, natural pacing, and storytelling flow.

Convene a four-voice council of advisors to surface structured disagreement and tradeoffs for ambiguous decisions, go/no-go calls, and multi-path choices.

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

Provides a creative-direction layer for music videos and short-form edits in the angelcore/cloud-trance/hyperpop visual family, encoding aesthetic vocabulary, mood/color/light system, and beat-synced editing grammar to produce intentional, stylistically coherent video content.

Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy.

Persists project context across Claude Code sessions. Auto-loads project summaries on startup, tracks session progress, and saves structured state via deterministic Node.js scripts.

Transform articles or scripts into click-driven 16:9 web presentations that look like videos, with optional AI voiceover synthesis.

Craft polished visual web artifacts — pages, dashboards, prototypes, slide decks, animations, UI mockups, and data visualizations — using HTML, CSS, JavaScript, and React.

Transforms source materials (URLs, PDFs, DOCX, Markdown, text, screenshots) into a single-file HTML web article that is visually polished, offline-accessible, and shareable, using a structured editorial workflow with checkpoints and quality reviews.

Retrieves and answers questions from a local knowledge base directory by navigating hierarchical index files, then progressively searching Markdown, PDF, and Excel files using grep, Read, pdfplumber, and pandas.

Generates and edits images using GPT Image 2 across three modes: direct generation via OpenAI-compatible API, prompt engineering for host-native image tools, or pure prompt advisory. Includes 80+ structured templates for posters, UI mockups, product visuals, maps, slides, and more.

Convert browser-use (Python) browser-automation scripts to Stagehand v3 (TypeScript) on Browserbase, replacing opaque agent loops with deterministic pipelines where possible.

Discovers competitors via search API, deeply researches each with a multi-lane pattern, and compiles an HTML report with overview, per-competitor deep dives, feature/pricing matrix, and mentions feed.

Takes a conference or event speakers URL, extracts the people, filters their companies against the user's ICP, and deep-researches only the speakers at ICP-fit companies. Outputs a person-first HTML report with a 'why reach out' rationale per person.

Discovers and researches companies matching an ideal customer profile, using Browserbase Search API and a Plan→Research→Synthesize pattern to produce scored reports and CSV exports.

Run multiple AI agents against a product, SDK, or docs site to score setup friction, speed, efficiency, error recovery, and doc quality from a minimal prompt.

Manage Browserbase platform resources, Functions, and API workflows through the `browse` CLI.

Generate an OpenAPI 3.1 specification from a browser-trace capture by analyzing observed HTTP traffic, templating URLs, and inferring JSON schemas from request/response samples.

Capture a full DevTools-protocol trace of any browser automation, bisect the stream into per-page searchable buckets, and attach a trace to an in-progress session for debugging.

Build a local browser agent that enforces a domain allowlist via CDP Fetch interception, using a safe_browser tool that owns the Playwright session and blocks off-domain requests.

Exports cookies from a local Chrome browser and saves them into a Browserbase persistent context, enabling authenticated browsing sessions via the browse CLI.

Create, compile, and validate site-specific WebMCP init scripts from a target URL and desired tool capability.

Builds reliable browser automation skills through iterative experimentation, running an inner agent to browse sites and improving navigation instructions until tasks pass consistently.

Deploy serverless browser automation as cloud functions using Browserbase. Run browser automation on a schedule, create webhook endpoints, or run automation in the cloud instead of locally.

Runs adversarial UI tests in a real browser using the browse CLI, analyzing git diffs to test only changed areas or exploring the full app to find bugs in functionality, accessibility, responsive layout, and UX.

Automate web browser interactions using natural language via CLI commands. Supports local and remote Browserbase sessions with CAPTCHA solving, residential proxies, and session persistence.

Search the web and return structured results with titles, URLs, authors, and dates — no browser session required.

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.

Design low-effort experiments to test product assumptions for an existing product, including prototypes, A/B tests, spikes, and other validation methods.

Stress-test a feature idea for an existing product by surfacing risky assumptions across Value, Usability, Viability, and Feasibility using multi-perspective devil's advocate thinking.