Multimodal AI
Vision-language models, image generation, and multimodal reasoning systems.
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
Vision-language models, image generation, and multimodal reasoning systems.
Write writestory content from the user's input.
Step-by-step guidance for retailed automation.
Use when designing custom voices with Alibaba Cloud Model Studio CosyVoice customization models, especially cosyvoice-v3.5-plus or cosyvoice-v3.5-flash, from a voice prompt plus preview text before us…
Use when tasks require all-in-one multimodal understanding or generation with Alibaba Cloud Model Studio Qwen Omni models, including image-plus-audio interaction, voice assistants, and realtime multim…
Manage Alibaba Cloud ApsaraVideo for Media Processing (MPS/MTS) resources and workflows via OpenAPI/SDK. Use for media ingest and metadata tasks, transcoding/snapshot jobs, pipeline/template/workflow …
Minimal CosyVoice voice design smoke test for Model Studio voice-enrollment.
Minimal voice cloning TTS smoke test for Model Studio Qwen TTS VC.
Generate project intro slides with Nano Banana Pro. Use when user mentions slide, project slide, 1-page summary, or visual introduction. Do NOT load for: video generation, presentation decks.
This skill should be used when working with genomic interval data (BED files) for machine learning tasks. Use for training region embeddings (Region2Vec, BEDspace), single-cell ATAC-seq analysis (scEm…
Extract reusable knowledge from AI coding sessions into structured, Obsidian-compatible documents. Use when the user wants to distill experience after completing a project, fixing bugs, refactoring co…
Voice design workflows with Alibaba Cloud Model Studio Qwen TTS VD models. Use when creating custom synthetic voices from text descriptions and using them for speech synthesis.
Use when text embeddings are needed from Alibaba Cloud Model Studio models for semantic search, retrieval-augmented generation, clustering, or offline vectorization pipelines.
Manage Alibaba Cloud Intelligent Cloud Editing (ICE) media workflows via OpenAPI/SDK. Use for media processing jobs, template/workflow orchestration, editing and production pipelines, and job status t…
Minimal live speech translation smoke test for Model Studio Qwen LiveTranslate.
Minimal CosyVoice voice clone smoke test for Model Studio voice-enrollment.
Translate books and long-form documents into a target language while preserving structure, formatting, and terminology consistency.
Step-by-step guidance for AI context.
Generate Unsloth training notebooks and scripts. Use when the user wants to create a training notebook, configure fine-tuning parameters, or set up SFT/DPO/GRPO training.
Use when visual reasoning is needed with Alibaba Cloud Model Studio QVQ models, including step-by-step image reasoning, chart analysis, and visually grounded problem solving.
Use when reranking search candidates is needed with Alibaba Cloud Model Studio rerank models, including hybrid retrieval, top-k refinement, and multilingual relevance sorting.
Minimal realtime ASR smoke test for Model Studio Qwen ASR Realtime.
Use when the user needs an end-to-end article illustration workflow in this repository that preserves Type x Style planning, loads article-illustration preferences, recommends Alibaba Cloud image back…
Minimal image-understanding smoke test for Model Studio Qwen VL.