MLOps
模型部署、评估与运维
rodin3d-skill
DeemosTech
Converts input images or prompt to 3D models using Hyper3D Rodin Gen-2 API. Use this skill when users want to generate 3D models from images or text, such as product designs, architectural elements, or object reconstructions. This skill handles API communication, task status polling, and 3D model retrieval.
ai-cost-check
breethomas
Calculate AI feature costs and challenge if you actually need it. Invokes ai-cost-analyzer agent for detailed economics modeling.
ai-health-check
breethomas
Pre-launch health check that blocks you from shipping broken AI features. Grades 6 dimensions (model selection, data quality, cost, monitoring, failure UX, optimization).
pm-frameworks
breethomas
Expert knowledge of proven product management frameworks for discovery, growth, measurement, planning, and AI-era practices.
prompting-pattern-library
Exploration-labs
Comprehensive library of proven prompting patterns, frameworks, and examples for different use cases. This skill should be used when creating prompting guides, analyzing prompt effectiveness, teaching prompting techniques, or troubleshooting prompting issues. Use when writing about prompting, explaining prompting concepts to others, or improving existing prompts.
gemini-imagegen
ratacat
This skill should be used when generating and editing images using the Gemini API (Nano Banana Pro). It applies when creating images from text prompts, editing existing images, applying style transfers, generating logos with text, creating stickers, product mockups, or any image generation/manipulation task. Supports text-to-image, image editing, multi-turn refinement, and composition from multiple reference images.
agentic-development
Exploration-labs
Conversational guidance for building software with AI agents, covering workflows, tool selection, prompt strategies, parallel agent management, and best practices based on real-world high-volume agentic development experience. Use this skill when users ask about setting up agentic workflows, choosing models, optimizing prompts, managing parallel agents, or improving agent output quality.
onboarding-specialist
ncklrs
Expert customer onboarding guidance for accelerating time-to-value and ensuring successful implementations. Use when designing onboarding programs, creating kickoff frameworks, building implementation plans, or optimizing customer activation. Use for training delivery, go-live readiness, sales-to-CS handoffs, early warning detection, and tech-touch automation.
magento-model-developer
maxnorm
Designs and implements data layer architecture for Magento 2. Use when creating data models, designing database schemas, implementing repositories, or working with EAV/flat table structures. Masters entity design, repository patterns, collections, and database optimization.
sqlmesh
jpoutrin
SQLMesh patterns for data transformation with column-level lineage and virtual environments. Use when building data pipelines that need advanced features like automatic DAG inference and efficient incremental processing.
ai-judge
reguorier
Local-first multi-model AI jury system with v3.3 fixed persona seats, evidence tracing, and dissent. Query 9 AI seats, score claims with auditable functions, detect bluff risk and echo-chamber consensus, profile cognitive proxy signals, render reasoning trees, and keep final authority with the human.
codex-review
yelban
跨模型對抗式審查：用 Codex 審查 Claude 的計畫或程式碼產出。 異質模型產生真正的對抗張力，抓住同模型自審遺漏的問題。 自動 VERDICT 迴圈（最多 3 輪），產出結構化 issues 清單。 支援 --model 參數切換模型（預設 gpt-5.3-codex）。 觸發詞：/codex-review、cross-review、對抗審查
midnight-concepts
mzf11125
Foundational knowledge about Midnight Network zero-knowledge blockchain technology, privacy mechanisms, and architecture. Use when users need to understand zero-knowledge proofs, privacy mechanisms like Zswap and selective disclosure, partner chain architecture, real-world use cases for private DeFi and voting, when to use Midnight for privacy-preserving applications, and core concepts of the Midnight ecosystem.
cheap-model-testing
almeidamarcell
When working on any application that integrates with LLMs or pay-per-usage APIs, always use the cheapest available model during development and testing. Remind to upgrade to a production model before deployment.
speech-to-text
martinholovsky
"Expert skill for implementing speech-to-text with Faster Whisper. Covers audio processing, transcription optimization, privacy protection, and secure handling of voice data for JARVIS voice assistant."
llm-integration
martinholovsky
"Expert skill for integrating local Large Language Models using llama.cpp and Ollama. Covers secure model loading, inference optimization, prompt handling, and protection against LLM-specific vulnerabilities including prompt injection, model theft, and denial of service attacks."
model-quantization
martinholovsky
"Expert skill for AI model quantization and optimization. Covers 4-bit/8-bit quantization, GGUF conversion, memory optimization, and quality-performance tradeoffs for deploying LLMs in resource-constrained JARVIS environments."
blockbench-mcp-overview
jasonjgardner
Overview of the Blockbench MCP server tools, resources, and prompts. Use to understand the full MCP capability set, learn how tools work together, or when starting a new Blockbench project. Covers all domains (modeling, animation, texturing, PBR, UI, camera) and their MCP interfaces.
dev-buddy-feature-implement
Z-M-Huang
Dev Buddy multi-AI pipeline. Plan -> Review -> Implement (loop until reviews approve). Configurable pipeline with Codex final gate.
dev-buddy-once
Z-M-Huang
Run a single task using a specific AI provider and model. Supports subscription, API, and CLI presets.
dev-buddy-manage-presets
Z-M-Huang
Dev Buddy AI provider presets management (list, add, update, remove)
data_transform
vuralserhat86
Transform raw data into analytical assets using ETL/ELT patterns, SQL (dbt), Python (pandas/polars/PySpark), and orchestration (Airflow). Use when building data pipelines, implementing incremental models, migrating from pandas to polars, or orchestrating multi-step transformations with testing and quality checks.
llm-fine-tuning-guide
qodex-ai
Master fine-tuning of large language models for specific domains and tasks. Covers data preparation, training techniques, optimization strategies, and evaluation methods. Use when adapting models for specialized applications, reducing inference costs, or improving domain-specific performance.
replicate-cli
rawveg
This skill provides comprehensive guidance for using the Replicate CLI to run AI models, create predictions, manage deployments, and fine-tune models. Use this skill when the user wants to interact with Replicate's AI model platform via command line, including running image generation models, language models, or any ML model hosted on Replicate. This skill should be used when users ask about running models on Replicate, creating predictions, managing deployments, fine-tuning models, or working with the Replicate API through the CLI.