В каталоге 181 320 навыков в 14 категориях.
How to programmatically configure, control, and verify VLC media player state using Python (vlcrc config, HTTP interface...
Use when planning a VLDB project on the PVLDB rolling calendar, covering month-picking strategy, the volume-to-conferenc...
Interacts with vLex legal APIs for document search, anonymization, citation extraction, and classification. Use when nee...
Deploy, tune, and query vLLM high-throughput inference engines; configure PagedAttention, continuous batching, chunked p...
You are an expert in vLLM, the high-throughput LLM serving engine. You help developers deploy open-source models (Llama,...
Use when self-hosting an open-weight LLM for high-throughput concurrent serving with vLLM — running an OpenAI-compatible...
Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment, quantization-a...
Deploy self-hosted LLMs with vLLM, PagedAttention, continuous batching, and tensor parallelism.
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM...
vLLM is a high-throughput inference and serving engine for large language models that exposes an OpenAI-compatible HTTP...
vLLM: high-throughput LLM serving, OpenAI API, quantization.
Route vLLM tasks across offline inference, OpenAI-compatible serving, structured/tool/reasoning, multimodal/LoRA/pooling...
Tuning request concurrency and queue parameters.
Deploy and manage vLLM for high-throughput LLM inference. Configure continuous batching, tensor parallelism, quantizatio...
Configuring vLLM servers for fast throughput.
Generate slack summaries of vLLM CI SIG Slack channel activity for the RHAIIS midstream release team
Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze im...
实现基于视觉的 AI 对话能力，支持分析图像、描述视觉内容并进行多模态交互。
OCR scanned or image-only corpora with vision-language models, in three phases. Use `evaluate` to compare candidate OCR...
Run the GPU part of a $vlm-ocr pipeline on Leiden University's ALICE cluster: decide whether a corpus needs ALICE, pick...
Compare OCR systems before a bulk run: candidate set, stratified ground truth, CER/WER, normalization, per-language and...
Design VLM-based OCR pipelines. Use for model selection, prompting, architecture, multilingual documents, structured out...
Use when creating vlog content for Xiaohongshu, documenting daily life or experiences, storytelling through video, or bu...
The numbers and rules that make a transcript-based cut feel natural instead of "popping" - silence detection, word pads,...
LibreOJ题目抓取与解题工作流。用户输入形如loj1/loj001或https://loj.ac/p/1 等题号或URL时触发；创建以题号命名的空文件夹，使用Chrome DevTools MCP读取题面并保存为md文件，最后用C++生...
LibreOJ题目抓取与解题工作流。用户输入形如loj1/loj001或https://loj.ac/p/1 等题号或URL时触发；创建以题号命名的空文件夹，使用Chrome DevTools MCP读取题面并保存为md文件，最后用C++、...
QCOW2 virtual machine management using libvirt. Creates VMs from pre-built images downloaded from R2 CDN with cloud-init...
Maintains the ansible/roles/guest_agent Ansible role (this skill is named vm_guest_agent, but the actual role directory...
Linux VM bootstrap verification skill. MUST BE USED when setting up new VMs or verifying environment.Supports modes: che...
虚拟机开发专家，专注于字节码设计、指令实现、栈帧管理、内存管理和垃圾回收。
Troubleshoot and manage GCP e2-micro VM running eth-realtime-collector. Use when VM service is down, systemd failures oc...
Exploiting custom interpreters and virtual machines
Parallels macOS VM lab: GUI automation, Peekaboo, TCC, Ghostty.
Runs a clean Parallels macOS VM lab to test GUI automation, TCC permission prompts, screenshots, clicking, and typing, v...
Safe VM operations (start, stop, destroy) via protected wrapper script
Provision and integrate new VMs into the NixOS Proxmox fleet
Create, configure, and manage VM templates in Proxmox. Build reusable VM images for rapid deployment of standardized env...
VMware vSphere / vCenter Server external attack matrix — version fingerprinting, the high-impact CVE chain (CVE-2021-219...
Creates visual novel dialogue content for Shadow Work including companion conversations, quest dialogues, NPC interactio...
面向第 91/2025/QH15 号法律及实施细则第 356/2025/ND-CP 号法令（2026 年 1 月 1 日生效）的越南个人数据保护法（PDPL）合规专家顾问。使用本技能进行对照越南 PDPL 的差距分析、数据主体权利履行工作流...
Expert Vietnam Personal Data Protection Law (PDPL) compliance advisor for Law No. 91/2025/QH15 and implementing Decree 3...
Best practices for using vnstock3 Quote class with VCI source. Use when fetching Vietnamese stock price data, implementi...
VNX orchestration infrastructure guardian - maintains dispatcher, smart tap, receipt processor, intelligence systems, an...
Sync an animation, captions, or cues to a voiceover so visuals land on the spoken words, and pace the timeline tightly t...
Voc namespace for Netsnek e.U. vocabulary and language learning tools
Use when extracting Voice-of-Customer themes from existing artefacts — GH issues, PR threads, Sentry patterns. Triggers...
Pesquisa de Voz do Cliente (VOC) antes de escrever qualquer copy — coleta a linguagem literal do público em avaliações,...
Vocabulary learning strategies and retention science for any language -- frequency-based word selection, spaced repetiti...
Word learning strategies, vocabulary instruction, and lexical development for reading comprehension. Covers Beck's three...
Ubiquitous language guard: harvests identifiers from code, schema and API definitions, has the LLM cluster synonyms that...
Diagnose mixed abstraction levels in functions and determine whether an abstraction earns its existence. Use when review...
This prompt instructs the AI to act as a language-teaching assistant and, using the specified language, topic, learner l...
Requirements for formatting and structuring the notes field in je-dict-1 entries. Covers formatting, content organizatio...
Pick key academic vocabulary from a topic or passage, with tiers and definitions. Do NOT use for vocabulary quizzes (use...
Tier vocabulary from a text or topic into everyday, academic, and technical categories with teaching priorities. Use whe...
Guidelines for assigning vocabulary to the three-tier system (basic, core, general). Covers tier criteria, word counts,...
Use when the user has recorded vocals and wants a processing chain set up. Examples - "set up my vocal chain", "process...
Handles voice-to-voice conversations on WhatsApp. Automatically transcribes incoming audio and responds with local TTS a...
Master vocal recording techniques including microphone placement, studio setup, acoustic treatment, and signal processin...
Query and manage Odoo ERP data (helpdesk tickets, projects, tasks, CRM leads, knowledge articles) via the vodoo CLI
Design cloud-native systems using Werner Vogels' principles of failure-first design, eventual consistency, and API-drive...
Text-to-Speech (TTS), voiceover, narration placement/sync, and custom sound effects (SFX) generator. Use when the user w...
Voice recognition, wake words, and voice-controlled trading
Transcribe local audio / Discord voice messages with the deployed Breeze ASR 26 HTTP service. Use when the user says /vo...
Text-to-Speech (TTS), voice cloning, voiceover, narration placement/sync, and custom sound effects (SFX) generator. Use...
When the user asks to hear an answer spoken, for a voice memo or recording, or for something meant to be heard (a poem,...
Plant Sprachaufnahme, Transkription und Sprachausgabe mit optionalen, austauschbaren Werkzeugen.
Narration and text-to-speech on the user's machine through Guaardvark's Audio Foundry (Chatterbox, Kokoro, Piper) and co...
Apply to every piece of prose: replies, docs, commit messages, PR descriptions, emails, chat messages, skill files. Cut...
Collects user feedback, designs NPS surveys, analyzes reviews and sentiment, classifies feedback, and generates insight...
Collecting user feedback via NPS surveys, review analysis, sentiment analysis, feedback classification, and insight extr...
Voice-driven invocation of Maxim — voice command, hands-free request, /mxm-voice, spoken "Maxim, ..." or "Hey Maxim". Wr...
Pick the right writing voice for a task — which voice playbook applies, nk-writer invocation, brand-writer invocation, /...
Alexa/Siri/voice SEO optimization
Choose or design a new speaking voice when the user asks for a new, different, custom, invented, or generated voice.
Provides the static system voice catalog used by Jarvis. It does not define a user-facing workflow.
台词声音、重音、气口与呼吸控制。指导配音与 lip-sync，消除机械朗诵感。
Add OpenAI Realtime API voice agent to a Next.js presentation. Use when adding voice interactivity, realtime audio, AI p...
Zoom AI Services Voice Agent V2 for real-time microphone conversations over WebSocket, including VAD, PCM audio, speech-...
Build, fix, or check a CloudTalk AI Voice Agent: its v2 "Expert Mode" configuration. Connected to CloudTalk, it creates,...
Check whether a CloudTalk AI Voice Agent is ready to go live, and what to fix first. Reads the agent's setup, its knowle...
Design a voice AI agent for phone or in-app conversations — call flows, interruption handling, escalation to humans, and...
Improve a live CloudTalk AI Voice Agent from its real calls. Reads the agent's setup and a sample of its recent calls, f...
Test a CloudTalk AI Voice Agent v2 config by simulating a phone conversation against it: a subagent plays the agent stri...
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't j...
ElevenLabs voice agent creation for client discovery and feedback calls. Use this skill when creating AI voice agents, s...
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems.
Voice AI architecture and implementation guide. Covers two architectures: speech-to-speech (OpenAI Realtime API, lowest...
Use when voice AI — text-to-speech (ElevenLabs, OpenAI TTS), speech-to-text (Whisper), voice cloning, real-time voice ag...
Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API...
Build real-time conversational AI voice engines using async worker pipelines, streaming transcription, LLM agents, and T...
Build and debug end-to-end speech pipelines with Whisper-style models and ffmpeg - ingestion and validation, preprocessi...
Expert guide for Ultra-Low Latency Conversational Voice AI (<300ms), WebRTC bidirectional streaming, OpenAI Realtime API...
Production voice AI agents with sub-500ms latency. Groq LLM, Deepgram STT, Cartesia TTS, Twilio integration. No OpenAI....
Develop and maintain a distinctive authorial voice. Transform generic prose into compelling, personal expression. Master...
Extract and document a writer's distinctive voice patterns for consistent reproduction. Use when you need to capture wri...
Reverse-engineer voice profiles from sample content by analyzing writing patterns. Use when relevant to the task.