Search Skills

Provides HTTP API for browser automation including tab management, content extraction, script execution, and cookie handling.

Enables browser automation via HTTP API for tab management, content retrieval, script execution, and cookie operations.

Provides quick understanding of project architecture, code details, and key concepts through the llmdoc documentation system without reading source code.

Automates the creation of reusable Claude Code skills from recurring workflows and domain knowledge patterns.

Installs official tech brand logos (e.g., Vercel, GitHub, OpenAI) for UI/UX design, landing pages, and integrations showcases.

Creates a logo component with multiple variants (icon, wordmark, logo) and light/dark mode support from SVG files.

Creates new UI components for tryelements.dev registry with scaffolding, registry schema, and shadcn-style patterns. Requires Context7 MCP for dependency docs.

Automates web browser interactions including navigation, form filling, screenshot capture, and data extraction for testing and information gathering.

Comprehensive toolkit for programmatically processing PDF documents, including text extraction, form handling, and document merging/splitting at scale.

Generates a Product Requirements Document (PRD) for new features or projects upon request, including specifications and requirements.

Enables creation, editing, and analysis of .docx files with tracked changes, comments, and formatting preservation for professional document workflows.

Generates distinctive, production-ready frontend interfaces with high design quality, avoiding generic AI aesthetics for web components and applications.

AI-assisted workflow following Plan → Work → Review → Compound loop to streamline feature development, code execution, and knowledge codification in software engineering.

Autonomous feature development assistant guiding through task creation, dependencies, and iterative implementation until completion.

Explains ev-node architecture, including block production, DA layer, sequencing, and censorship resistance for technical comprehension.

Automates iOS app testing, building, and simulator lifecycle management with semantic UI navigation and accessibility testing.

Automates migration of documentation and commands from 'bd' (beads) to 'br' (beads_rust), including AGENTS.md updates and command conversion.

Comprehensive guide for building Agentic RAG systems using Microsoft Agent Framework in C#, including semantic search, document indexing, and multi-agent orchestration.

Converts Office documents (Word, Excel, PowerPoint, PDF) to Markdown format upon explicit user request for file conversion.

Decomposes tasks into parallel sub-agents for multi-step operations and batch processing.

Detects whether a project uses jj (Jujutsu) or git for version control to ensure correct tool usage in subsequent commands.

Converts markdown Product Requirements Documents (PRDs) into executable JSON format for autonomous task processing and system integration.

Enables deep exploration of multi-repository codebases to research library internals, find patterns, and compare implementations across GitHub, npm, PyPI, and crates.

Automates adding AI session summaries to GitHub PR and GitLab MR descriptions for better documentation of AI-assisted development.