Plugins

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

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)

from vocalbridgeai/vocal-bridge-claude-plugin

Route every response element to exactly one voice: prose to human-voice (verdict-first, confidence-tagged), machine-read artifacts to machine-voice (compressed traces, logs, status lines); plus second-opinion, an offer-only subagent validation pipeline that never runs unbidden.

Communication-style skills: outbound team-facing writing in a warm, hedged, emoji-aware engineering voice; plain-language plan pitches before exiting plan mode.

Phone voice remote for your interactive Claude Code session — types your speech into the cmux pane and speaks replies back.

Talk to Claude Code and hear it answer: a Stop hook speaks marker-tagged lines, a push-to-talk script dictates into the prompt, and /voice-setup installs it all. Local, LAN, or cloud speech backends.

Voice notifications for Claude Code lifecycle events.

Replace voice in audio using MiniMax TTS, with audio separation and precise timing alignment

Grep-strength brand-voice scanner against a configurable JSON profile. Flags banned phrases, stale stat-claims, and missed reframes. Pure static analysis — no LLM, no paid APIs.

Voice notes, dictation, translation and transcription

Turn rough thoughts into finished writing that reads as genuinely human -- in your voice, without the AI tells.

Audio feedback when Claude Code agent completes tasks using pocket-tts

Embedded & IoT engineer — firmware, microcontrollers, edge computing, device protocols

Product management and business analysis - product strategy, project management, UX research

Product management and business analysis - product strategy, project management, UX research

from fubotv/smo-subagents

Essential development subagents for everyday coding tasks - backend, frontend, fullstack, mobile, and API design