MLOps
模型部署、评估与运维
ai-avatar-video
alfredang
Create AI avatar and talking head videos with OmniHuman, Fabric, PixVerse via inference.sh CLI. Models: OmniHuman 1.5, OmniHuman 1.0, Fabric 1.0, PixVerse Lipsync. Capabilities: audio-driven avatars, lipsync videos, talking head generation, virtual presenters. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human
vargdown
wassname
Verified Argdown maps with credences and source quotes.
c4-model-architecture-diagrams
Agentient
[STUB - Not implemented] C4 model diagrams for layered architecture visualization (Context, Container, Component, Code). PROACTIVELY activate for: [TODO: Define on implementation]. Triggers: [TODO: Define on implementation]
venice-ai
asgarth
Generate and manipulate images and videos using Venice.ai's privacy-first, uncensored AI API. Use when the user needs to create images from text prompts, edit/inpaint existing images, upscale/enhance image quality, remove backgrounds, or generate videos from text or images. Triggers on requests like "generate an image of...", "upscale this photo", "remove background", "create a video from this image", etc.
dspy-prompting
eyadsibai
Use when "DSPy", "declarative prompting", "automatic prompt optimization", "Stanford NLP", or asking about "optimizing prompts", "prompt compilation", "modular LLM programming", "chain of thought", "few-shot learning"
distill
corygabrielsen
Strip overspecified instructions from an artifact. Trust the model's intuition — prescribe intent, not format.
llm-inference
eyadsibai
Use when "LLM inference", "serving LLM", "vLLM", "llama.cpp", "GGUF", "text generation", "model serving", "inference optimization", "KV cache", "continuous batching", "speculative decoding", "local LLM", "CPU inference"
runpod-serverless-builder
AvivK5498
Build production-ready RunPod serverless endpoints with optimized cold start times. Use when creating or modifying RunPod serverless workers for (1) vLLM-based LLM inference, (2) ComfyUI image/video generation, or (3) custom Python inference. Supports both baked models (fastest cold starts) and dynamic loading (shared models). Generates complete projects including Dockerfiles, worker handlers, startup scripts, and configuration optimized for minimal cold start latency.
designing-monitoring
sumik5
Designs monitoring and observability systems covering anti-patterns, design patterns, layer-based strategy (6 layers), alerting, on-call operations, incident management, telemetry pipeline architecture, observability concepts (structured events, core analysis loop), SLO-based reliability, sampling strategies, and observability maturity model. Use when designing monitoring strategy, setting up alerting, choosing monitoring tools, building observability systems, implementing SLOs, or adopting observability practices. For OpenTelemetry SDK/API implementation, use implementing-opentelemetry instead. For green software carbon metrics and sustainability monitoring, use building-green-software instead. For Google Cloud monitoring (Cloud Logging, Security Command Center, Cloud Run), use developing-google-cloud instead. For LLM-specific evaluation and monitoring, use practicing-llmops. For application logging design, structured logging, and log collection pipelines, use implementing-logging instead.
load-topology
nicholasf
Read the local system topology to discover available machines and models. Triggers on "load topology", "what models are available", "which machines are running", "start a model", "show me the topology", "sync topology", "refresh topology", "benchmark llm", "benchmark model", "test llm", "run benchmark", "help", "show help", "list subcommands".
concept-cartographer
PrakharMNNIT
"Generate visual concept maps, flowcharts, architecture diagrams, and relationship diagrams from structured notes or technical content using Mermaid syntax. Use when the user has lecture notes, study materials, or technical documentation and wants visual diagrams to aid understanding. Produces multiple diagram types: concept hierarchy maps, process flowcharts, architecture diagrams, comparison matrices, timeline diagrams, and mind maps. Trigger phrases: 'create diagrams from notes', 'visualize concepts', 'concept map', 'make flowcharts', 'diagram this', 'visual notes'."
transcript-pipeline
PrakharMNNIT
This skill should be used when the user asks to "process this transcript", "convert lecture to notes", "run transcript pipeline", "generate class tutorial from Zoom captions", "validate transcript coverage", or "enrich class resources" (Notion/Canva/Drive links) for bootcamp notes.
douyin-downloader
MgOxides
Use when needing to download and transcribe Douyin/抖音 videos to text. Supports single video URLs (/video/xxx) and user profile URLs (/user/xxx) with auto-detection. Triggers on Douyin links, 抖音 transcription requests, Chinese short video audio extraction, or batch video downloading.
backend-principle-eng-python-ml-pro-max
PrakharMNNIT
"Principal backend engineering intelligence for Python AI/ML systems. Actions: plan, design, build, implement, review, fix, optimize, refactor, debug, secure, scale ML services and pipelines. Focus: data quality, reproducibility, reliability, performance, security, observability, model evaluation, MLOps."
scvi-tools
Victory-Hugo
单细胞组学深度生成模型。当需要概率批次校正(scVI)、迁移学习、带不确定性的差异表达或多模态集成(TOTALVI, MultiVI)时使用。最适合高级建模、批次效应、多模态数据。标准分析管道请使用scanpy。
ai-model-orchestrator
famaoai-creator
Dynamically selects the optimal AI model based on task complexity, cost, and latency. Routes requests to Gemini, GPT-4, Claude, or local LLMs to maximize efficiency.
shap
eyadsibai
Use when "SHAP", "Shapley values", "feature importance", "model explainability", or asking about "explain predictions", "interpretable ML", "feature attribution", "waterfall plot", "beeswarm plot", "model debugging"
converting-epub-images
sumik5
Converts image-based EPUB files to Japanese text via LM Studio OCR. Use when user has an EPUB composed of scanned page images and wants plain text output. For skill creation from EPUB, use authoring-skills instead.
experiment-tracking
eyadsibai
Use when "experiment tracking", "MLflow", "Weights & Biases", "wandb", "model registry", "hyperparameter logging", "ML experiments", "training metrics"
eld-debug
CAPHTECH
ELD的デバッグ手法 - 法則（Law）視点でバグを分析・修正する。 バグを「法則からの逸脱」として捉え、証拠ループで系統的に解決する。 トリガー条件: - 「ELDでデバッグして」「法則視点でバグを調査して」 - 「証拠ベースでバグ修正して」「デバッグを体系的に進めて」 - バグ修正、障害調査、根本原因分析
llm-training
eyadsibai
Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient checkpointing"
designing-training
sumik5
Training program design and facilitation methodology covering needs analysis (participant analysis, stakeholder mapping), KSA framework, instructional design theory (ADDIE, TOTE, Gagné, mastery learning), objective setting, activity catalog, training operations (instructor, space, logistics), brain science principles (7±2 rule, long-term memory, habit formation), learner-centered facilitation (90/20/8 rule, EAT), online/hybrid delivery, skill map creation, and training material development. Use when designing training programs, facilitating workshops, creating training materials, building skill maps, or managing training operations. For behavior design→applying-behavior-design. For presentation content→improving-presentations. For design thinking process methodology (empathize/define/ideate/prototype/test)→practicing-design-thinking.
creating-flashcards
sumik5
Creates Anki flashcards from EPUB/PDF files by converting to markdown, auto-detecting content structure, and batch-importing via Anki MCP. Use when converting textbooks, question banks, or study materials into spaced repetition flashcards. For Anki MCP setup and direct card management, use using-anki-mcp instead.
scikit-learn
eyadsibai
Use when "scikit-learn", "sklearn", "machine learning", "classification", "regression", "clustering", or asking about "train test split", "cross validation", "hyperparameter tuning", "ML pipeline", "random forest", "SVM", "preprocessing"