设计与多媒体 Skills - 设计与多媒体 Agent Skills推荐与安装 - 第43页 - AI导哈

tao-finetune-cosmos-embednvidia/skillsCosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to "fine-tune Cosmos-Embed1", "run cosmos-embed inference", "export Cosmos-Embed1", "embed videos", or "search videos with text".1641 product-taste-intuitionrefoundai/lenny-skillsHelp users develop product taste and intuition. Use when someone wants to improve their product judgment, struggles to evaluate design quality, needs to make decisions without complete data, or wants to build better product instincts.1640 ttscnagents365-ai/365-skillsMulti-platform Chinese & multilingual TTS text-to-speech via Edge/Doubao/CosyVoice/Qwen3/StepFun/GLM-TTS/Azure/Tencent/Baidu/MiniMax/Xunfei plus ElevenLabs/OpenAI/Google/Atlas Cloud — 15 backends, word-level timestamps, [PAUSE:x] pause markers, pinyin pronunciation overrides1639 webgl-3d-objectmengto/skillsCreate a real 3D WebGL object with geometric mesh depth, physically based material, directional and ambient lighting, perspective camera, subtle rotation, and floating motion. Use when a page needs a faceted 3D hero object or product-like visual with real lighting instead of CSS transform tricks.1639 tao-finetune-cosmos-reasonnvidia/skillsShared Cosmos3 frontend that explicitly routes Cosmos Framework and Cosmos-RL, validates runtime model/video-dataset/SLURM inputs, consumes an SQSH or packaged backend image, optionally plans explicit clean source builds, prepares checkpoints, validates the first update in-process, and returns token-weighted losses and task-aware accuracy.1638 mmx-climinimax-ai/skillsUse mmx to generate text, images, video, speech, and music via the MiniMax AI platform. Use when the user wants to create media content, chat with MiniMax models, perform web search, or manage MiniMax API resources from the terminal.1638 brand-manifestoarnabbagxd/bran…g-skillsWrite a brand manifesto — a bold, belief-driven declaration of what the brand stands for, fights against, and exists to change. Use when the user says "brand manifesto", "manifesto", "what we believe", "brand declaration", "brand belief statement", "rally the team around the brand", "inspire the team", "internal brand document", "culture document", "why we exist statement", "brand credo", "brand creed", or wants to write something that goes beyond a mission statement to express the brand's conviction and worldview.1636 qwencloud-textqwencloud/qwencloud-aiGenerate text, have conversations, write code, reason, and call functions with Qwen models and third-party models available on QwenCloud. TRIGGER when: user asks to chat with Qwen, generate text, write code with Qwen, use Qwen function calling, call third-party models (deepseek, kimi, glm, etc.) via QwenCloud, or explicitly invokes this skill by name (e.g. use qwencloud-text). DO NOT TRIGGER when: using non-QwenCloud platforms (direct OpenAI API, Google Gemini API, etc.), general coding questions unrelated to QwenCloud, image/video understanding (use qwencloud-vision), image/video/audio generation.1633 scroll-world-storytellingmengto/skillsTurn an article, case study, brand narrative, product journey, or long-form story into a cinematic scroll-driven landing page using one of three renderers: scrubbed video, a real-time Three.js world, or semantic HTML/SVG data and typography. Use when the user asks for a scroll world, fly-through landing page, article-to-website transformation, animated planet, data scrollytelling, video-scrubbed page, connected visual journey, or story-led alternative to ordinary stacked sections.1632 tao-finetune-clipnvidia/skillsCLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image embeddings, or deploying CLIP to ONNX/TensorRT. This is a single-action model skill; do not use it for an iterative weak-attribute improvement loop that keeps retraining and evaluating until progress stops, which belongs to tao-run-deft-pas.1629 om-mockup-prototypeopen-mercato/skillsBuild a neutral clickable low-fi prototype from a product brief during discovery, after the first synthetic panel and before refreshing the brief or drafting a backlog. Preserve business rules and explicit assumptions, simulate the chosen flow locally, and verify navigation and relevant states in a browser. Use for discovery wireframes or testing a flow before detailed design.1629 tao-run-automlnvidia/skillsRun container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation hooks. Use when the user mentions TAO AutoML, hyperparameter optimization, HPO, automl, automl_settings, AutoMLRunner, tao_automl, bayesian search, hyperband, ASHA, LLM-guided search, autoresearch, or wants to tune train/evaluate/inference/distill/prune/quantize for a TAO network. Model actions use the resolved image; venv training requires an explicit request. Platform-agnostic — runs on any SDK (Brev, SLURM, Kubernetes, Docker). Do not use generic "keep improving" language alone to override a matching domain-specific DEFT workflow; attribute-labelled CLIP / SigLIP image-retrieval loops belong to tao-run-deft-pas unless HPO is explicit.1625 tao-generate-video-reasoning-annotationsnvidia/skillsMulti-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants to "create video training data", "generate video QA datasets", "build CoT reasoning traces from videos", "auto-label videos", or run the video_reasoning_annotation pipeline. Triggers include "video annotation", "video CoT", "video QA", "chain-of-thought", "video captioning pipeline", "video distillation".1622 icon-retrievalantvis/chart-vi…n-skillsSearch icons through HTTP API and retrieve SVG strings with curl.1621 critique-affordanceowl-listener/de…r-skillsCritique a rendered screen's affordances — what looks clickable, state visibility, CTA clarity, and action discoverability. Use when reviewing an existing screen. For sizing and positioning targets in new work, use `fitts-law` (interaction-design).1619 tao-train-image-classificationnvidia/skillsPyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for deployment. Use when training, evaluating, distilling, quantizing, exporting, or running inference for a TAO image-classification (PyT) model. Trigger phrases include "train image classifier", "TAO classification", "ResNet/EfficientNet/FAN backbone classifier", "classification-pyt".1618 running-design-reviewsrefoundai/lenny-skillsHelp users run effective design reviews and critiques. Use when someone is giving design feedback, establishing design review processes, struggling to evaluate designs, or wants to improve how their team discusses design work.1617 deepseek-ocrreason-machines/trending-skillsExpert skill for using DeepSeek-OCR, a vision-language model for optical character recognition with context optical compression supporting documents, PDFs, and images.1616 cangjie-skillkangarooking/ca…ie-skillDistill a book, long-video transcript, podcast, course, or interview into a coherent set of executable skills. Use when the user asks to "拆书" / "蒸馏一本书" / "把 XX 书做成 skill" / "把这个视频/播客/课程蒸馏成 skill" / "turn a book or video into skills" — i.e. wants the frameworks, principles, and methodologies in long-form content extracted into atomic, reusable Claude skills that an agent can invoke in real-world situations. NOT for simple summarization, book reviews, or role-playing as the author (that is nuwa-skill's job).1615 unsplash-asset-imagesmengto/skillsUse when you need to pick high-quality Unsplash images for product/design assets (avatars, headshots, portraits, large website backgrounds, and abstract wallpapers) and output real Unsplash URLs plus practical instructions for producing the right resolutions and aspect ratios (1:1, 4:5, 3:4, 16:9, 9:16).1615 tao-generate-image-groundingnvidia/skillsTwo-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM. Use when the user wants to ground captions to bboxes, generate phrase-grounded annotations, auto-label images for grounding, or run the image_grounding pipeline. Triggers include 'image grounding', 'phrase grounding', 'ground captions', 'auto-label image grounding', 'image_grounding'.1614 tao-train-ocrnetnvidia/skillsOCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and attention-based decoders. Use when training, evaluating, exporting, pruning, quantizing, retraining, or running inference for a TAO OCRNet model. Trigger phrases include "train OCRNet", "scene text recognition", "OCR cropped text", "CTC / attention text decoder".1613 typegpusoftware-mansio…s/skillsTypeGPU is type-safe WebGPU in TypeScript. Use whenever the user writes, debugs, or designs TypeGPU code: 'use gpu' shader functions, tgpu.fn, buffers, textures, bind groups, compute and render pipelines, command encoders, render passes, render bundles, vertex layouts, slots, accessors, @typegpu/react hooks (useRoot, useFrame, useUniform), React Native worklet rendering, and any TypeGPU API. Shader logic and CPU-side resources are tightly coupled - handle both sides here even if the user only mentions one (e.g. "how do I write a shader", "how do I create a buffer"). Trigger on any mention of typegpu, tgpu, "use gpu", TypedGPU, or WebGPU code written using TypeGPU's schema API (d.*, tgpu.*, std.*). Do NOT trigger for raw WebGPU (using GPUDevice/GPURenderPipeline directly without tgpu), WGSL-only questions, Three.js, Babylon.js, or WebGL.1612 scroll-scrubbed-visual-sequencemengto/skillsBuild reversible scroll-controlled visual transformations with a pinned or sticky stage, normalized progress, and video, image-sequence, canvas, SVG, or DOM renderers. Use for hero transformations, product assembly, interface state walkthroughs, object rotation, diagrams, or photo sequences that must move forward and backward with native scrolling.1611 tao-run-inference-servicenvidia/skillsStart, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the appropriate platform skill. Handles container image resolution, job-payload JSON construction, and the service registry. Use when the user wants to run inference on a TAO model checkpoint using a microservice container, deploy a TAO inference endpoint, or stop a running inference container.1610 minimax-music-genminimax-ai/skillsUse when user wants to generate music, songs, or audio tracks. Triggers on any request involving music creation, song writing, lyrics generation, audio production, or covers. Also triggers when user provides lyrics and wants them turned into a song, or describes a mood/scene and wants background music. Supports multilingual triggers — match equivalent phrases in any language. Do NOT use for music playback of existing files, music theory questions, or music recommendation without generation.1610 brand-measurementarnabbagxd/bran…g-skillsDefine KPIs, metrics, and tracking systems to measure brand health, awareness, perception, and equity over time. Use when the user says "brand measurement", "brand metrics", "how do we measure the brand", "brand KPIs", "brand health tracking", "brand awareness metrics", "brand equity measurement", "is our brand working", "brand ROI", "brand performance", "brand tracking", "brand health score", "prove brand value", "brand dashboard", or needs to show stakeholders whether brand investment is delivering results.1610 platform-strategyrefoundai/lenny-skillsHelp users design and execute platform business strategies. Use when someone is building a marketplace, creating an ecosystem, deciding on API strategy, thinking about multi-sided network effects, or building developer platforms.1609 cross-functional-collaborationrefoundai/lenny-skillsHelp users work effectively across functions. Use when someone is navigating PM-engineering relationships, resolving cross-team conflicts, building product trios, or improving handoffs between design, engineering, and product.1606 qwencloud-video-generationqwencloud/qwencloud-aiGenerate videos using Wan models. Supports text-to-video, image-to-video, first+last frame, reference-based role-play, and video editing (VACE). TRIGGER when: user wants to create, generate, or edit video content, mentions video generation/animation/video clips/Wan models, or explicitly invokes this skill by name (e.g. use qwencloud-video-generation). DO NOT TRIGGER when: user wants to generate images (use qwencloud-image-generation), understand/analyze existing videos (use qwencloud-vision), text-only tasks.1606