ML Ops
Machine learning operations
langchain-tool-calling
by christian-bromann
How chat models call tools - includes bindTools, tool choice strategies, parallel tool calling, and tool message handling
prime
by robzolkos
Prime yourself on a codebase by listing files and reading the README.
product-tryon-visualization
by tara-shopos
Generate realistic product try-on visualizations showing how garments, accessories, or products look when worn or used. Use for virtual try-on experiences, fit visualization, and helping customers see products in use before purchase.
interview
by robzolkos
Interview me about the plan
langchain-rag
by christian-bromann
Build Retrieval Augmented Generation (RAG) systems with LangChain - includes embeddings, vector stores, retrievers, document loaders, and text splitting
langchain-chat-models
by christian-bromann
Guide to using chat model integrations in LangChain including OpenAI, Anthropic, Google, Azure, and Bedrock
langchain-models
by christian-bromann
Initialize and use LangChain chat models - includes provider selection (OpenAI, Anthropic, Google), model configuration, and invocation patterns
solana-account-model
by SanctifiedOps
Expert guide to Solana's account model: ownership, signers, rent, PDAs, CPIs, and state layout decisions. Use when modeling accounts, auditing account flows, or debugging account-related errors.
eld-debug
by 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
kueue
by tylertitsworth
"Kueue — ClusterQueues, ResourceFlavors, fair sharing, preemption, TAS, MultiKueue. Use when managing batch workload queuing and GPU quotas on K8s. NOT for Volcano."
langchain-chat-models
by evanfang0054
使用 LangChain 中的聊天模型集成指南，包括 OpenAI、Anthropic、Google、Azure 和 Bedrock
llm-integration
by liauw-media
"Use when integrating LLM APIs into applications. Covers API patterns, prompt templates, streaming, error handling, cost optimization, and provider abstraction. Apply when building chat interfaces, completion endpoints, or AI-powered features."
catchup
by robzolkos
Catch up on codebase changes by reviewing the diff from master and reading relevant spec files.
keda
by tylertitsworth
"KEDA — ScaledObject/ScaledJob CRDs, 60+ triggers, scale-to-zero for GPU inference, TriggerAuthentication. Use when configuring event-driven pod autoscaling. NOT for HPA basics or Kueue."
langchain-structured-output
by evanfang0054
使用 Zod 模式、类型安全响应和自动验证从 LangChain 代理和模型获取结构化的验证输出
backend-ai-agent
by Workshop-Ventures
Create AI agents using Vercel AI SDK with tool use, tracing, and failover. Use when asked to "create an AI agent", "add AI", "create LLM integration", or "build an assistant".
subagent-generator
by squirrelsoft-dev
Generates custom Claude Code subagents with specialized expertise. Activates when user wants to create a subagent, specialized agent, or task-specific AI assistant. Creates properly formatted .md files with YAML frontmatter, suggests tool restrictions and model selection, generates effective system prompts. Use when user mentions "create subagent", "new agent", "specialized agent", "task-specific agent", or wants isolated context for domain-specific work.
deepagents-overview
by christian-bromann
Understanding Deep Agents framework - what they are, how to create them with create_deep_agent/createDeepAgent, and the agent harness architecture with built-in middleware for planning, filesystems, and subagents.
discovery
by robzolkos
Quick user-centric interview to capture requirements from a time-poor stakeholder.
langchain-multimodal
by christian-bromann
Work with multimodal inputs/outputs in LangChain - includes images, audio, video, content blocks, and vision capabilities
data-ai-skills
by pluginagentmarketplace
Master machine learning, data engineering, AI engineering, LLMs, prompt engineering, and MLOps. Build intelligent systems with Python.
langchain-embeddings
by christian-bromann
Guide to using embedding model integrations in LangChain including OpenAI, Azure, and local embeddings
call-cursor-agent
by dotneet
Call cursor-agent to perform a task.
euler-irm-oracles
by euler-xyz
Oracle and Interest Rate Model guide for Euler Finance V2. This skill should be used when deploying oracle adapters, configuring price resolution, querying prices, or understanding IRM types. Triggers on tasks involving Chainlink, Pyth, Chronicle, price feeds, Linear Kink IRM, Adaptive Curve IRM, or interest rate configuration.