Plugins

Research-backed visual design principles for websites, presentations, documents, and any visual medium — grounded in VisAWI, Gestalt psychology, and empirical aesthetics research

Fully local visual plans and recaps — the agent writes markdown, a bundled zero-dependency server renders it in your browser with Mermaid diagrams, rich diffs, styled DB migrations, API call cards, and a read-only OpenAPI view, with live reload and a comment feedback loop. No remote services.

Generate beautiful HTML pages for diagrams, diff reviews, plan reviews, slides, and data tables

Generate beautiful HTML pages for diagrams, diff reviews, plan reviews, slides, and data tables

Concept → interactive HTML explainer → GitHub Pages. /explain <topic>.

Image generation, vector art, generative art, and motion/video production (Remotion, Blender, After Effects).

Writes a durable, committed Markdown ADR/plan as the source-of-truth record, and — only when the content needs visuals markdown can't express (wireframes, annotated split-diffs, before/after columns) — also emits a self-contained rich plan.html to /tmp. Markdown canonical, HTML disposable; no backend.

Generates a Playwright spec that crawls a sitemap and checks every route at 375/768/1440 viewports for horizontal overflow, clipped fixed elements, zero-height containers. CLI emits the spec; user invokes Playwright.

Visual regression testing with screenshot comparison

Visual diff testing with Percy, Chromatic, BackstopJS - catch unintended UI changes

Produce a single self-contained HTML visual report — an explainer, writeup, or diagram-heavy document built with Tailwind and Mermaid via CDN plus hand-crafted CSS/SVG.

Use when someone wants a montage with transitions between shots — action-sequence reel or multi-scene piece where narration is optional.

Visual expression system for AI personas with emotion-based face switching

Data visualization using D3.js, Leaflet and AG Grid - charts, network graphs, timelines, trees, calendars, flowcharts, kanban boards, tables and maps

Interactive HTML visualization companion — push diagrams, mockups, and explorers to a browser window

Interactive HTML visualization companion — push diagrams, mockups, and explorers to a browser window

Vite + React SPA 패턴 - React Router, Zustand, 코드 스플리팅

Vitest TDD workflow, test conventions and patterns

Plugin from spencerbeggs/bot

Vivado FPGA 풀스택 개발 도구: 13개 스킬 + 6개 에이전트. RTL 설계, 시뮬레이션, 합성, Implementation, Bitstream, 코드 리뷰, 핀 배치 검증, KiCad 연동을 한 번에 설치합니다.

Agent skills for natural prose, cross-model code review, and type-driven refactoring

Report and figure generation: Vizuara PDF/HTML reports and Wisprflow chart figures.

Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment, quantization-aware model configuration (tensor parallelism, KV cache), OpenAI-compatible API serving, throughput and latency benchmarking, continuous batching tuning, GPU operation, and upgrade/rollback. Use when deploying or running a vLLM server (vllm serve, vllm/vllm-openai), sizing a model and its KV cache for GPUs, selecting quantization and parallelism, serving via /v1 endpoints, measuring serving throughput or latency, tuning batching, or diagnosing GPU, OOM, or startup failures in a vLLM deployment. Do not use for model training, fine-tuning, evaluation-set design, or engine-selection methodology (that is ml-engineering), or for operating the llama.cpp stack with GGUF models (that is llama-cpp); other inference engines (TGI, Ollama, Triton) are out of scope.

vLLM operator reference suite — deployment, configuration, quantization, caching, KV, tool parsers, reasoning parsers, chat templates, benchmarking, performance tuning, observability, omni, input modalities, speculative decoding, NVIDIA hardware, and a Gemma 4 31B operating-point serve recipe.

Benchmark a **running vLLM-XPU OpenAI-compatible server** on an Intel GPU using `vllm bench`. Measures TTFT (time-to-first-token), TPOT (time-per-output-token), ITL (inter-token latency), end-to-end latency, and throughput under concurrency. Covers online (`vllm bench serve`) and offline (`vllm bench throughput`) modes; concurrency sweeps and quant comparison live in `references/sweep-and-compare.md`. Use after **vllm-xpu-run** when the user asks "how fast is this?".

Profile a running vLLM-XPU server with torch.profiler around a window of real requests, either via /start_profile and /stop_profile HTTP endpoints or via vllm bench --profile for offline runs. Use to find the dominant op under real concurrent traffic. Not for pure PyTorch (use torch-xpu-profile), SYCL kernel-level signal (use xpu-profile-unitrace), throughput numbers (use vllm-xpu-bench), or non-vLLM servers.

Serve a Hugging Face safetensors model on an Intel GPU with upstream vLLM-XPU's OpenAI-compatible API. Covers image choice, container launch, the right vllm serve flags (dtype, enforce-eager, model-impl fallback, attention backend, quant + KV-cache pairing), and the transformers-backend fallback for unsupported architectures. Use for /v1/chat/completions or /v1/completions on an Intel GPU. Not for pure PyTorch without a server (use torch-xpu-run), throughput numbers (use vllm-xpu-bench), or NVIDIA (use vllm-project/vllm-skills).

VLM benchmark CLI for running, comparing, and reproducing VLM inference benchmarks. Supports vLLM, Ollama, and SGLang backends with automatic platform detection, concurrency sweeps, and HuggingFace dataset integration.

from xiaolai/vmark

Complete Vietnamese stock trading toolkit — 11 MCP tools (price, history, financials, news, screener, portfolio, insider trades), 10 auto-trigger skills (TA, FA, news impact, portfolio review, sector compare, morning brief, session summary, portfolio monitor, watchlist), 8 slash commands (/analyze, /screen, /portfolio, /news, /compare, /report, /alert, /trading-session), 4 specialized agents (market-watcher, news-analyst, portfolio-manager, research-agent)