Agent skills for Claude Code

Resume and take over an in-progress coding session left by an AI agent — this same tool in a previous session, or a different agent…

Automate Browserhub tasks via Rube MCP (Composio).

Automate Browserless tasks via Rube MCP (Composio).

Automate Hackernews tasks via Rube MCP (Composio).

Automate Microsoft Clarity tasks via Rube MCP (Composio): session recordings, heatmaps, and user behavior analytics.

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including…

Automates talking-head video editing by detecting speech errors, cutting pauses, proofreading subtitles, and assembling final video…

Use when managing server state with TanStack Query v5.

Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner.

Fine-tune any HuggingFace CV, VLM or LLM model on local NVIDIA GPUs inside an NGC PyTorch container.

Three.js asset loading - GLTF, textures, images, models, async patterns.

Preserves and restores long-running project task state, architectural decisions, and execution progress across Claude Code sessions and…

Creates implementation, refactoring, and test tasks from templates.

Maintains structured, resumable task documentation across multi-step AI coding sessions to preserve context and track progress.

Fixes tasks in To Rework by applying reviewer feedback, then returns to To Review.

Implement or adjust VMark frontend <-> Tauri v2 integration.

Test-Driven Development (TDD) and Incremental Implementation discipline.

Enforce true RED/GREEN TDD workflow with fail-first testing methodology

Phase-agnostic orchestrator for parallel multi-agent work — brainstorm, plan, implement, review, research, or test.

Merge completed parallel agent work and trigger GitHub sync per increment.

Unified team skill for code review. 3-role pipeline: scanner, reviewer, fixer.