MLOps
模型部署、评估与运维
starwave:tasks
ArjenSchwarz
Create Task List
Financial Analysis
zircote
This skill should be used when the user asks to "analyze financials", "revenue model", "unit economics", "pricing analysis", "cost structure", "profitability analysis", "financial projections", "business model economics", or needs guidance on financial metrics, revenue analysis, or economic viability assessment.
starwave:design
ArjenSchwarz
Create Feature Design Document
nano-banana
Roasbeef
Generate and edit images using Gemini's image generation API (Imagen 3). This skill should be used when creating images, illustrations, diagrams, editing existing images, or iteratively refining visual content through multi-turn conversations.
classification-helper
dkyazzentwatwa
Quick classifier training with automatic model selection, hyperparameter tuning, and comprehensive evaluation metrics.
discover-ml
rand
Automatically discover machine learning and AI skills when working with machine learning, PyTorch, training, inference, RAG, embeddings, fine-tuning, LLM, DSPy, HuggingFace, or diffusion models. Activates for ML development tasks.
mlops
williamzujkowski
MLOps engineering covering ML pipeline design, model versioning, experiment tracking, deployment strategies, drift detection, and monitoring for production ML systems with tools like MLflow, Kubeflow, and model registries
model-development
williamzujkowski
Model-Development standards for model development in Ml Ai environments.
model-deployment
williamzujkowski
Model-Deployment standards for model deployment in Ml Ai environments.
handoff
blacktop
Generate optimized handoff prompts for delegating tasks to LLM agents. Use when needing to hand off work to another agent (GPT-5.2/Codex, Claude Opus 4.5/Sonnet 4, or Gemini 3 Pro/Flash), whether for a sub-task/parallel task within the same project or a fresh start handoff to a new agent context. Triggers on requests like "create a handoff prompt", "delegate this task to another agent", "hand this off", or "prepare context for another agent".
tinygrad
av
Deep learning framework development with tinygrad - a minimal tensor library with autograd, JIT compilation, and multi-device support. Use when writing neural networks, training models, implementing tensor operations, working with UOps/PatternMatcher for graph transformations, or contributing to tinygrad internals. Triggers on tinygrad imports, Tensor operations, nn modules, optimizer usage, schedule/codegen work, or device backends.
run-llms
av
Guide for setting up and running local LLMs using Harbor. Use when user wants to run LLMs locally, set up Ollama, Open WebUI, llama.cpp, vLLM, or similar local AI services. Covers full setup from Docker prerequisites through running models, configuration, profiles, tunnels, and advanced features.
whisper-test
TrevorS
Transcribe WAV audio files using OpenAI Whisper for intelligibility testing. Triggers on: "transcribe audio", "whisper test", "test audio output", "is the audio intelligible", "check speech quality", "run whisper", "speech to text test", "check if audio sounds right"
qwen3-tts-profile
TrevorS
Profile and benchmark qwen3-tts-rs inference. Runs e2e_bench with chrome tracing, flamegraph, or Nsight Systems inside a CUDA Docker container. Triggers on: "profile", "benchmark", "run profiling", "chrome trace", "flamegraph", "nsys", "perf trace", "how fast", "what's slow", "performance", "bottleneck"
HuggingFace Model Download
TrevorS
When downloading models from HuggingFace, use this skill to get the correct
design-of-experiments
jkitchin
Expert guidance for Design of Experiments (DOE) in Python - interactive goal-driven design selection, classical DOE (factorial, response surface, screening), Bayesian optimization with Gaussian processes, model-driven optimal designs, active learning, and sequential experimentation; includes pyDOE3, pycse, GPyOpt, scikit-optimize, statsmodels
python-regression-statistics
jkitchin
Expert guidance for regression analysis, statistical modeling, and outlier detection in Python using statsmodels, scikit-learn, scipy, and PyOD - includes model diagnostics, assumption checking, robust methods, and comprehensive outlier detection strategies
idaes
jkitchin
Comprehensive guidance for using IDAES (Institute for the Design of Advanced Energy Systems) for process systems engineering. Covers flowsheet modeling, property packages, unit models, optimization, scaling, initialization, and diagnostics. Use when working with chemical process simulations, energy systems modeling, power plant design, material and energy balances, or process optimization. Triggers include 'IDAES', 'flowsheet', 'process model', 'unit operation', 'process optimization', 'property package', 'energy systems', or process engineering tasks.
python-optimization
jkitchin
Expert guidance for mathematical optimization in Python - systematic problem classification, library selection (scipy, pyomo, cvxpy, GEKKO), solver configuration, and implementation patterns for LP, QP, NLP, MIP, convex, and global optimization problems
cloudflare-workers-ai
jackspace
Complete knowledge domain for Cloudflare Workers AI - Run AI models on serverless GPUs across Cloudflare's global network. Use when: implementing AI inference on Workers, running LLM models, generating text/images with AI, configuring Workers AI bindings, implementing AI streaming, using AI Gateway, integrating with embeddings/RAG systems, or encountering "AI_ERROR", rate limit errors, model not found, token limit exceeded, or neurons exceeded errors. Keywords: workers ai, cloudflare ai, ai bindings, llm workers, @cf/meta/llama, workers ai models, ai inference, cloudflare llm, ai streaming, text generation ai, ai embeddings, image generation ai, workers ai rag, ai gateway, llama workers, flux image generation, stable diffusion workers, vision models ai, ai chat completion, AI_ERROR, rate limit ai, model not found, token limit exceeded, neurons exceeded, ai quota exceeded, streaming failed, model unavailable, workers ai hono, ai gateway workers, vercel ai sdk workers, openai compatible workers, workers ai vectorize
odoo-security
ahmed-lakosha
"Comprehensive Odoo security auditor for model access rules, HTTP route authentication, sudo() usage, SQL injection risks, and record rule completeness across Odoo 14-19."
image-to-3d-pipeline
guia-matthieu
"Transformez une image 2D en modèle 3D animé prêt pour le web ou le jeu en moins de 30 minutes, en utilisant le workflow Dilum Sanjaya (Hunyuan3D + Mixamo). Use when: Créer un personnage 3D pour un site web - Mascotte, avatar, illustration interactive; Prototyper un asset de jeu - Character design, props, environnements; Produire du contenu marketing 3D - Produits rotatifs, personnages animés; Convertir des illustrations existantes - Logo, mascotte, character design → 3D; **Tes..."
prompt-version-editor
WiseWong6
严格变更控制下编辑、版本化并存储提示词。用于用户要求小改/局部优化/补丁式修订、修复提示词失败、添加或维护版本头、对比版本，或基于输入/思路/输出诊断问题时。强制版本控制、作者签名，并将版本保存到 /Users/wisewong/Documents/Developer/prompts。
code-security-audit
ssrsec
AI 驱动的生产级代码安全审计协议。面向企业内部授权审计，默认使用结构化 harness：项目画像、攻击面枚举、Sink/Control 双轨候选发现、验证队列、能力链、质量门、报告渲染和完整证据交付。支持 PHP、Java、C# / ASP.NET、Go、Python、JavaScript / TypeScript Node.js、Ruby、Rust、Kotlin、Deno/Bun，以及 JVM/.NET 编译产物反编译计划。用户说「开始审计 / 对 XXX 做安全审计 / 代码审计 / 安全扫描 / 找漏洞 / security audit / 红队审计」时触发。