MLOps
模型部署、评估与运维
product-strategy
pluginagentmarketplace
Master product strategy, market analysis, competitive positioning, and long-term product vision. Define business models and craft go-to-market strategies that drive success.
building-commands
C0ntr0lledCha0s
Expert at creating and modifying Claude Code slash commands. Auto-invokes when creating/updating commands, modifying command frontmatter (model, allowed-tools, argument-hint), designing workflows, or writing to /commands/.md files.
langchain-multimodal
christian-bromann
Work with multimodal inputs/outputs in LangChain - includes images, audio, video, content blocks, and vision capabilities
data-ai-ml-skill
pluginagentmarketplace
Master machine learning, data engineering, AI engineering, MLOps, and prompt engineering. Build intelligent systems from data pipelines to production AI applications with LLMs, agents, and modern frameworks.
pal-mcp-expert
mamba-mental
Expert guidance for using the Pal MCP Server (zen-pal-nas). This skill should be used when working with multi-model AI orchestration, tool workflows (chat, thinkdeep, planner, consensus, debug, codereview, precommit, clink), configuration troubleshooting, or optimizing model selection strategies. Activates automatically when user mentions Pal MCP, zen-pal-nas, or specific tool names.
rust-ml
peixotorms
Use when building machine learning or AI inference in Rust. Covers inference, model loading, tensor operations, GPU and CUDA acceleration, batch processing, feature extraction, embeddings, tokenizer, hugging face integration, deep learning, ONNX with tract, model singletons with OnceLock, candle, tch-rs, ndarray tensors, and data pipelines with polars.
buildkite
HJewkes
Buildkite CI/CD integration. Use when the user needs to check build status, trigger builds, read build logs, debug failures, manage pipelines, or any Buildkite workflow. Triggers include "buildkite", "build", "pipeline", "CI", "deploy", "build log", "build failed".
navi
mcxross
This skill should be used when the user asks about Navi Protocol, Navi lending, Navi borrowing, or wants to integrate with Navi on Sui. Covers lending markets, reserves, obligations, price feeds, and reward distribution.
langchain-structured-output
christian-bromann
Get structured, validated output from LangChain agents and models using Pydantic schemas, type-safe responses, and automatic validation
cost-planning-for-solana-apps
SanctifiedOps
Estimate and control costs for Solana apps: RPC, indexing, storage, bots, and on-chain fees. Use for budgeting and scaling.
evaluating-skills-with-models
taisukeoe
Evaluate skills by executing them across sonnet, opus, and haiku models using sub-agents. Use when testing if a skill works correctly, comparing model performance, or finding the cheapest compatible model. Returns numeric scores (0-100) to differentiate model capabilities.
hugging-face-space-deployer
GhostScientist
Create, configure, and deploy Hugging Face Spaces for showcasing ML models. Supports Gradio, Streamlit, and Docker SDKs with templates for common use cases like chat interfaces, image generation, and model comparisons.
langchain-tool-calling
christian-bromann
How chat models call tools - includes bindTools, tool choice strategies, parallel tool calling, and tool message handling
data-poisoning
pluginagentmarketplace
Test AI training pipelines for data poisoning vulnerabilities and backdoor injection
codex-cli
rafaelcalleja
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
prime
robzolkos
Prime yourself on a codebase by listing files and reading the README.
product-tryon-visualization
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
robzolkos
Interview me about the plan
langchain-rag
christian-bromann
Build Retrieval Augmented Generation (RAG) systems with LangChain - includes embeddings, vector stores, retrievers, document loaders, and text splitting
langchain-chat-models
christian-bromann
Guide to using chat model integrations in LangChain including OpenAI, Anthropic, Google, Azure, and Bedrock
benchmark-datasets
pluginagentmarketplace
Standard datasets and benchmarks for evaluating AI security, robustness, and safety
langchain-models
christian-bromann
Initialize and use LangChain chat models - includes provider selection (OpenAI, Anthropic, Google), model configuration, and invocation patterns
solana-account-model
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.
Google ADK Python Skill
mamba-mental
Remember: ADK treats agent development like traditional software engineering - use version control, write tests, and follow engineering best practices.