MLOps
模型部署、评估与运维
openrouter
rawveg
OpenRouter API - Unified access to 400+ AI models through one API
ollama
rawveg
Ollama API Documentation
write-test
aviflombaum
Writes comprehensive RSpec tests for Rails applications. Use when writing model specs, request specs, system specs, job specs, mailer specs, channel specs, or storage specs. Triggers on "write tests for", "add specs to", "test the User model", "create request specs", "write RSpec", "add test coverage".
BMAD Method
daffy0208
Business Model and Architecture Design methodology for aligning technical architecture with business model sustainability and scalability
summarize
goldengrape
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
flyway-migration
martinellich
Creates versioned Flyway database migration scripts (V*.sql) with sequences, tables, constraints, and foreign keys from the entity model. Use when the user asks to "create a migration", "generate SQL scripts", "set up database tables", "write a Flyway migration", or mentions schema migration, DB migration, database versioning, or SQL migration files.
paper-reading
yishuai778
"Read research papers and turn them into clear, decision-oriented notes, comparisons, and implementation takeaways. Use this skill whenever someone wants to read, summarize, analyze, compare, or review papers; build a literature overview; extract methods, datasets, benchmarks, or limitations; judge whether a paper is worth reproducing; or turn papers into actionable notes. Also trigger on requests like '读这篇论文', '帮我总结 paper', '精读这篇', '对比这几篇论文', '做文献综述', '提炼贡献/局限/实验设置', '这篇值不值得复现', or '把论文讲明白'."
openai-image-gen
malue-ai
Batch-generate images via OpenAI Images API. Random prompt sampler + index.html gallery.
implement-paper-from-scratch
GhostScientist
Guides you through implementing a research paper step-by-step from scratch. Use when asked to implement a paper, code up a paper, reproduce research results, or build a model from a paper. Focuses on building understanding through implementation with checkpoint questions.
cloudrouter
manaflow-ai
Manage cloud development sandboxes with cloudrouter. Create, sync, and access remote VMs with GPU support, Docker, and browser automation. Use when asked to create a sandbox, spin up a dev environment, run code in the cloud, use GPUs, automate a browser, or interact with remote VMs.
gemini-gen
ttmouse
Generates images using Google's Gemini model. Prioritizes standard resolution to save quota. Automatically opens images on macOS.
transcribe-and-analyze
buddyh
Transcribe audio and video from URLs (YouTube, direct media links) using WhisperKit locally. Optionally analyze transcripts with AI when explicitly requested. Use when users provide URLs to media content and request transcription or speech-to-text conversion.
Networking Essentials
zebbern
The assistant provides comprehensive networking fundamentals including OSI model, TCP/IP, cabling, VLAN configuration, and Cisco router/switch commands. Activate when users ask about "network basics," "OSI model," "TCP/IP addressing," "subnetting," "VLAN configuration," "Cisco commands," or "network infrastructure."
sequelize-patterns
joneqian
Sequelize Node.js ORM for SQL databases. Use for database models, migrations, associations, queries, transactions, validations, hooks, and working with PostgreSQL, MySQL, MariaDB, SQLite, SQL Server.
pricing-packaging
elliottrjacobs
Design pricing models, packaging tiers, and monetization strategy. Use when the user says "pricing", "packaging", "monetization", "how should we price this", "pricing model", "pricing strategy", "tiers", or needs to figure out how to charge for a product.
experimenting-edge
Git-Fg
"Optimizes AI models for edge deployment through quantization, lazy loading, and memory management. Use when deploying models to resource-constrained environments, mobile devices, or edge computing scenarios. Do not use for cloud deployment, model training, or data preprocessing."
scikit-survival
kjgarza
Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library.
Video Editing
Surojit16
Output: always tell the user the output file path and duration
ai-engineer
ncdevshiv
"Build production-ready LLM applications, advanced RAG systems, and
veo3-prompter
leegonzales
Craft professional video prompts for Google Veo 3.1 using cinematic techniques, audio direction, and timestamp choreography. Use when generating AI videos, creating video prompts, or working with Veo 3.
openrouter-typescript-sdk
OpenRouterTeam
Complete reference for integrating with 300+ AI models through the OpenRouter TypeScript SDK using the callModel pattern
codex-config
outfitter-dev
This skill should be used when configuring Codex CLI, setting up profiles, or when "config.toml", "sandbox mode", "Codex config", or "approval policy" are mentioned.
ml-ablation-design
dongzhuoyao
Use when designing ablation studies to compare model components, loss functions, or architectural choices. Covers synthetic data experiments, variant loops, production metrics, and W&B grouping. Triggers: "ablation", "ablation study", "variant comparison", "controlled experiment", "synthetic data experiment"
hydra-experiment-config
dongzhuoyao
Use when structuring ML experiment configs with Hydra, adding new config groups, or debugging config resolution. Applies to any project using Hydra for hyperparameter management. Triggers: "Hydra", "config", "yaml config", "OmegaConf", "config groups", "defaults list", "config override"