vincenthopf

vincenthopf/My-Claude-Code

Command Claude Code

Perform web research using the Parallel API.

vincenthopf/My-Claude-Code

Plugin Claude Code

Bundles 1 skill, 1 command, 4 hooks · 47 tokens together

Voice notifications for Claude Code using edge-tts with macOS banner alerts and click-to-focus.

vincenthopf/My-Claude-Code

Skill Claude Code

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

vincenthopf/My-Claude-Code

Skill Claude CodeCodex

Run deep research tasks using the Parallel.ai Task API and write results directly to markdown files without loading them into context. Use when the user asks to research a topic, investigate a question, perform deep research or parallel research, or to gather web intelligence on any subject. Triggers on research…

vincenthopf/My-Claude-Code

Skill Claude CodeCodex

Manage Huly issues and cards with full CRUD operations, status changes, and chat/comments. Use when Claude needs to (1) list, create, update, or delete issues in Huly, (2) change issue status or priority, (3) add or read comments on issues/cards, (4) search for issues, or (5) manage projects. Triggers on requests…

vincenthopf/My-Claude-Code

Skill Claude CodeCodex

Dispatch tasks to the pi coding agent as a background sub-agent. Use when you want to run a coding task in parallel using a different model/provider (e.g., GPT-5, Gemini, Codex) via the pi CLI. Supports any task pi can handle — code generation, refactoring, analysis, file operations. Progress streams to stderr, final…

vincenthopf/My-Claude-Code

Skill Claude CodeCodex

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

vincenthopf/My-Claude-Code

Skill Claude CodeCodex

Help users create high-quality skills by discovering and incorporating proven methodologies from domain experts. Use this skill BEFORE skill-creator when users want to create a new skill - it enhances skill-creator by first identifying expert frameworks and best practices to incorporate. Triggers on requests like…

vincenthopf/My-Claude-Code

Skill Claude CodeCodex

Transcribe YouTube videos with high accuracy. Downloads audio via yt-dlp and auto-routes to parakeet-mlx (local, Apple Silicon) or AssemblyAI (speaker diarization for podcasts). Use when the user asks to transcribe a YouTube video, get a transcript from a YouTube URL, or extract text from a YouTube link. Also…

vincenthopf/My-Claude-Code

Agent Claude Code

Rigorously compares candidate solution approaches during the design phase. Analyzes tradeoffs, failure modes, and real-world outcomes for each approach. Does not pick a winner — presents the analysis so the user can decide informed by their principles.

vincenthopf/My-Claude-Code

Agent Claude Code

Surfaces invisible assumptions embedded in a problem definition. Every problem framing carries unstated beliefs about what's true, what's possible, and what matters. This agent makes them explicit so they can be examined. Use during problem definition alongside the devil's advocate and context analyst.

vincenthopf/My-Claude-Code

Agent Claude Code

Verifies implementation work by running code, executing tests, and generating adversarial test cases. Checks against the problem definition and principles, not against the proposal document. Approval is gated on execution results, not code reading.

vincenthopf/My-Claude-Code

Agent Claude Code

Maps the landscape around a problem definition. Examines what already exists in the codebase, what's been tried before, and how the problem connects to the broader system. Use during problem definition to ground the framing in reality before committing to it.

vincenthopf/My-Claude-Code

Agent Claude Code

Adversarial reviewer that attacks problem definitions. Use during problem definition to stress-test the framing before committing to it. This agent critiques — it does not propose solutions or alternative framings.

vincenthopf/My-Claude-Code

Agent Claude Code

Checks whether pieces built by parallel sub-agents actually fit together as a system. Runs after all build-verifiers pass. Looks for interface mismatches, assumption conflicts, and gaps between pieces that no single agent owned.

vincenthopf/My-Claude-Code

Agent Claude Code

Reads two independently generated proposals and selects the stronger one as the base, pulling in specific pieces from the other only when they address genuinely separate concerns. Justifies every choice. Use during planning after dual Codex agents have proposed.

vincenthopf/My-Claude-Code

Agent Claude Code

Evaluates research quality and identifies gaps. Sits after deep-research returns results. Determines whether the research actually answers the question, identifies missing angles, and dispatches follow-up research if needed. Uses analytical reasoning to assess rigor, not just coverage.

vincenthopf/My-Claude-Code

Skill Claude CodeCodex

Full bug-fix pipeline from root cause analysis through implementation. Separates investigation, proposal, alignment, and execution into distinct agent responsibilities. Also applies to features and refactors by skipping root cause analysis and starting at proposal.

vincenthopf/My-Claude-Code

Skill Claude CodeCodex

Explore the solution space after the problem is defined. Evaluate approaches, form project-specific principles, and pick a direction. Sits between problem definition and planning. Use when the problem is defined but the approach isn't decided yet.

vincenthopf/My-Claude-Code

Skill Claude CodeCodex

Execute the approved proposal. Sub-agents build in parallel, each assigned a domain scope. Verification checks against the problem and principles, not the proposal document. Two-round iteration limit on failures. Use after planning has produced an approved proposal.

vincenthopf/My-Claude-Code

Skill Claude CodeCodex

Turn a defined problem and chosen direction into a concrete proposal. Two Codex agents propose independently, Opus synthesizes the best parts, user approves. Use after problem definition (and design, if applicable), before implementation.

vincenthopf/My-Claude-Code

Skill Claude CodeCodex

Frame and clarify problems before any planning or implementation begins. Use when starting new work, when requirements are unclear, or when the user describes what they want built. This is the first step — before planning, before code.

vincenthopf/computer-use-mcp

MCP server Claude CodeCodexCursor +2

Production-ready MCP server providing AI-powered web browsing automation using Gemini 2.5 Computer Use API. Runs locally from the computer-use-mcp Python package.