Каталог навыков агентов

MANDATORY: Always Use Backslashes on Windows for File Paths

MANDATORY: Always Use Backslashes on Windows for File Paths

MANDATORY: Always Use Backslashes on Windows for File Paths

MANDATORY: Always Use Backslashes on Windows for File Paths

MANDATORY: Always Use Backslashes on Windows for File Paths

视频逆向复刻 — 分析参考视频(FFmpeg帧提取+Vision LLM) + 生成复刻Seedance 2.0 Prompt + 4种素材替换模式。支持单个和批量。Use when: '复刻这个视频', '分析爆款视频', 'replic...

MANDATORY: Always Use Backslashes on Windows for File Paths

Write viral X/Twitter posts using 23 proven plug-and-play formulas optimized for the 2025-2026 algorithm. Covers single...

Write and diagnose YouTube Shorts that hold attention on the Shorts Feed and route viewers into your long-form. Use when...

Generate viral YouTube titles optimized for clicks, engagement, and algorithm performance using proven formulas, psychol...

Find what is already working in a niche, then rewrite it in the user's own voice for their audience and hand back a shoo...

Plan, script and review short-form videos (Instagram Reels, TikTok, YouTube Shorts) so they actually get watched, with h...

Build trading systems in the style of Virtu Financial, the leading electronic market maker and execution services firm....

---name: virtual-lab-agent

Virtual Screening Pipeline - Virtual screening: search PubChem by substructure, compute similarity, filter by drug-liken...

Build ServiceNow Virtual Agent — sys_cs_topic conversations, topic blocks (text/prompt/script/decision/handoff), NLU utt...

Zoom Virtual Agent skill pack for web campaigns/chat embeds, Android and iOS WebView bridge integrations, and knowledge-...

Zoom Virtual Agent Android integration via WebView. Use for Java/Kotlin bridge callbacks, native URL handling, support_h...

Zoom Virtual Agent iOS integration via WKWebView. Use for Swift/Objective-C script injection, message handlers, support_...

Zoom Virtual Agent SDK for web embeds. Use for campaign or entry ID chat launch, event-driven controls, user context upd...

Give Lu (or any AI agent) a visible avatar presence in Discord video calls and streaming. Covers the full pipeline for a...

Check and create virtual environments for projects that need them. Use when starting Python/Node projects, or when depen...

Mandates the use of virtual environments for isolating project dependencies and ensuring reproducibility.

处理超过 1000 条数据的大型列表渲染时的性能优化方案，包含定高和不定高两种策略。

Create, manage, and optimize virtual machines in Proxmox. Control VM lifecycle, monitor performance, adjust resources, a...

Performs structure-based virtual screening using AutoDock Vina 1.2 for molecular docking. Prepares receptor PDBQT files,...

AI导购的技能。帮助用户创建和管理店铺试衣间，包括初始化店铺、获取二维码、装扮店铺、管理SKU/上传衣服、切换数据源、写穿搭笔记。 当用户提到"创建店铺"、"虚拟试衣"、"试衣间"、"上传衣服"、"写穿搭笔记"、"店铺管理"、"衣橱管理"、...

Put one supplied garment on a supplied person or suitable generated model, or replace clothing already worn, while prese...

GPU passthrough and virtualization for Bazzite. KVM/VFIO setup, Looking Glass (kvmfr),USB hotplug for VMs, and libvirt c...

· Create/troubleshoot VMs and hypervisors: Proxmox, QEMU/KVM, libvirt, XCP-ng, vSphere. Triggers: 'proxmox', 'qemu', 'kv...

Implement high-performance virtualization strategies for massive datasets without sacrificing UX.

Render only visible rows for long lists (1k+ rows) using intersection observer or lightning-datatable virtual scroll. NO...

Render only visible rows for long lists (1k+ rows) using intersection observer or lightning-datatable virtual scroll. Tr...

Implements WPF UI virtualization for large data sets using VirtualizingStackPanel. Use when displaying 1000+ items in It...

Your Own AI Personal Assistant, Set Up in 24 Hours. Managed OpenClaw hosting and setup service.

Virtuals Protocol AI Agent marketplace (Base chain)

Virtuals Protocol - Build, tokenize, and deploy autonomous AI agents on Base/Solana. Use for creating agents with GAME f...

Hire specialised agents to handle any task — data analysis, trading, content generation, research, on-chain operations,...

Virus Genomics Analysis - Analyze virus genomics: NCBI virus dataset, annotation, taxonomy, and literature search. Use t...

VirusTotal API v3 reference. File, IP, domain, and URL analysis endpoints.

Create an educational MicroSim using the vis-network JavaScript library. Each MicroSim is a directory located in the /d...

Use when auditing an IEEE VIS full-paper submission for PCS readiness, covering the abstract-then-paper two-deadline str...

Use when planning an IEEE VIS project timeline from area fit through the abstract and full-paper deadlines, the two-phas...

Visa application guidance with document tracking and timeline management. Use when user mentions travel visas, visa appl...

Look up visa requirements, application fees, processing time, and official application links for any country. Use when t...

Translate visa application documents (images) to English and create a bilingual PDF with original and translation

Writes, audits and reviews Brazilian Portuguese copy in Visant's voice, from landing to signed post, and runs copy-lint,...

End-to-end UI/UX: removes AI slop, redesigns screens around what they must achieve, and verifies on the real screen. Use...

Frontend decision system where every interface choice names the business variable it moves; the required deliverable is...

Single UI audit door: runs detectors as a hard gate, applies frontend/motion/refine judgment, ends with an adversarial i...

Connects and operates the Visant Labs MCP (requires a Visant Labs account): brand guidelines, mockups, creative studio,...

Visant's official brand-building methodology: 9 stages in 3 phases and the dependency cascade between them. Use to gener...

Visant motion and micro-interaction system: easing/duration tokens mirrored in CSS and framer-motion, plus motion-lint a...

Preflight for a large client project: one question round with whoever owns the work, plus five premise checks (brand sou...

Assembles a rough cut in Premiere Pro via premiere-pro-mcp from a JSON cut plan: frame-exact cuts, markers, punch-ins, c...

One shared anatomy for charts, gauges, sparklines, simulation sliders, metric tiles and control panels, so a screen look...

Edits vlogs, event videos and video lessons from raw footage: breakdown, silence cuts that never clip a word, loudness a...

Visao 360 de produto - agrega dados de cadastro, estoque, custo, faturamento, carteira e producao em uma consulta unific...

Preservation and sustenance — maintaining working state under perturbation, memory anchoring, consistency enforcement, a...

For anyone who suspects their most valuable contributions aren't showing up in the systems that matter.Helps identify wh...

Enforces visibility pattern for testability by detecting private methods that prevent unit testing (causes 20-40% covera...

Rebuild or restyle editable Microsoft Visio diagrams from reference images and existing .vsdx files, then export deliver...

Analyze images, screenshots, diagrams, and visual content - Use when you need to understand visual content like screensh...

Define team vision, values, and the culture you want to build

Product Discovery Facilitator - Conduct a comprehensive interview to crystallize a fuzzy project vision into a complete...

这个技能接收用户给出的图片文件，按照用户的要求进行文字提取、图片描述、图片内容综述、图片内容解释、界面截图复刻等功能。

这个技能接收用户给出的图片、pdf文件，按照用户的要求进行描述、综述、解释、界面截图复刻等功能。

Turn a business goal into the seed of the product model — a detailed domain grounding doc, directional capability ground...

Creative direction for UI/UX, complete redesigns, new designs, and trend application. Used when design direction, Design...

Image parsing, bounding boxes, visual validation, and graphic layouts.

Directing UI/UX creative work — redesigns, new designs, trend application, Design System construction, Muse/Palette/Flow...

Analyzes and processes images using Claude's vision capabilities. Supports OCR, image classification, diagram comparison...

Call vision models (Doubao, Qwen, DeepSeek, OpenAI) to analyze images. Use when you need to understand screenshots, UI l...

Parses and analyzes project vision to extract structured requirements. Use at project start to understand goals, scope,...

Especialista em depuração e melhoria dos workers de Visão Computacional (Python/Node).

Advanced visibility analysis using head pose, face mesh, and temporal patterns. Use for face-visible vs body-only breakd...

Audit project alignment with VISION.md, identify SDLC gaps, and generate feature proposals. Use when reviewing strategic...

Score and compare images using vision LLMs as judges. YAML-defined criteria presets for 11 use cases (text-to-image, pho...

Builds project visions through interactive guided conversation. Use when users have vague ideas needing structure. Trigg...

Computer vision-based mouse and keyboard control that enables AI to interact with the user's screen through visual under...

Create the customer-facing Vision Document (IIBA Business Need/Solution Vision) from a discovery session. Triggers: crea...

This skill should be used when the user asks to "discover vision", "create a vision", "define product vision", "document...

Creates vision documents through structured 5-phase discovery process. Guides through problem discovery, solution explor...

Lightweight baseline elicitation pass that fills in `docs/product-vision.md` and the five `docs/architecture.md` elicita...

Expert in analyzing images, diagrams, UI screenshots, charts, and visual content. Use for image analysis, UI-to-code con...

Implement computer vision features including text recognition (OCR), face detection, barcode scanning, image segmentatio...

Image understanding guidance for agents with vision enabled. Instructs agents to use read_file for viewing images direct...

Understand videos, screen recordings, and time-based visual evidence by turning media into timestamped observations, key...

GPT-5/4o, Claude 4.5, Gemini 2.5/3, Grok 4 vision patterns for image analysis, document understanding, and visual QA. Us...

Use when creative leadership, content strategy, marketing direction, creative technology implementation, or user experie...

Extracting structured text coordinate boundaries from screenshots.

MCP server extending Design System Sidekick with programmatic vision-based compliance scoring. Replaces manual Northcote...

Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a visual...

Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory),...

This skill supports three modes: Create, Update, and Find.

视觉子代理。当主模型不支持图像输入时，用 workflow 派生一个指定当前环境可用视觉模型的子代理，通过 read_image 查看或核验图片内容并结构化返回结论。适用于"需要看图、但主模型读不了图"的任何会话。