MLOps
模型部署、评估与运维
mcp-management
laurigates
Install and configure Model Context Protocol (MCP) servers for Claude Code projects. Use when you want to add or enable an MCP server, connect a tool or integration (database, API, file system), update MCP settings in .mcp.json, or troubleshoot MCP server connection issues.
agents-analyze
laurigates
Analyze all plugins for sub-agent opportunities. Identifies skills with verbose output, gaps in agent coverage, and model selection improvements.
mcp-code-execution
laurigates
Design and scaffold the code execution pattern for MCP-based agent systems. Use when building agents that interact with many MCP tools, when intermediate data is too large for model context, when you need loops/conditionals across tool calls, or when PII must stay out of the model context. Based on Anthropic's engineering guidance.
study
leodearden
Load a deep, discussion-ready understanding of a specific piece of code into context BEFORE reasoning about it. Use whenever the goal is comprehension and readiness rather than an immediate edit — triggers like "read the code for X in detail and get ready to discuss it", "study how X works", "get a deep understanding of X before we talk", or any time the user is about to explore a subtle aspect, do an authoritative analysis of some behaviour/logic, or design a tricky feature/change/refactor. Reach for this even when the user doesn't say "study": any request to get primed on a specific function, class, module, subsystem, or feature ahead of a hard conversation should pull this in.
who-are-you
Soul-Brews-Studio
Know ourselves - show identity, model info, session stats, and Oracle philosophy. Use when user asks "who are you", "who", "who we are", or wants to check current AI identity.
watch
Soul-Brews-Studio
Learn from YouTube videos via Gemini transcription. Use when user says "watch", "transcribe youtube", "learn from video", or shares a YouTube URL to study.
mineru-extract
blessonism
Use the official MinerU (mineru.net) parsing API to convert a URL (HTML pages like WeChat articles, or direct PDF/Office/image links) into clean Markdown + structured outputs. Use when web_fetch/browser can’t access or extracts messy content, and you want higher-fidelity parsing (layout/table/formula/OCR).
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
Google ADK Python Skill
einverne
Remember: ADK treats agent development like traditional software engineering - use version control, write tests, and follow engineering best practices.
creating-financial-models
ynulihao
This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions
mcp-tokenflux-images
vaayne
Generate images using AI models via TokenFlux API. Use when creating AI-generated images, artwork, or visual content. Triggers on "generate image", "create picture", "AI art", "image generation", "TokenFlux".
greptimedb-pipeline
GreptimeTeam
Guide for creating GreptimeDB Pipeline, by which user can add a process layer to GreptimeDB between ingestion and storage, to transform data.
ai-engineer
tao12345666333
Expert knowledge in AI/ML development, model deployment, and MLOps practices
Skill: tokenizer-diagnostics
strikersam
Pairs with training-stability-monitor — tokenizer bugs can cause loss spikes on specific token patterns
cats-mtl-typed-errors
alexandru
Scala typed errors with Cats MTL Raise/Handle and allow/rescue. Use for designing custom domain error types without EitherT, while keeping Cats Effect and ecosystem composition. Covers Scala 2/3 syntax and IO-only or F[_] usage.
deep-reading-analyst
YYH211
"Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems thinking, six thinking hats). Use when users want to: (1) deeply understand complex articles/content, (2) analyze arguments and identify logical flaws, (3) extract actionable insights from reading materials, (4) create study notes or learning summaries, (5) compare multiple sources, (6) transform knowledge into practical applications, or (7) apply specific thinking frameworks. Triggered by phrases like 'analyze this article,' 'help me understand,' 'deep dive into,' 'extract insights from,' 'use [framework name],' or when users provide URLs/long-form content for analysis."
model-first-reasoning
petekp
Apply Model-First Reasoning (MFR) to code generation tasks. Use when the user requests "model-first", "MFR", "formal modeling before coding", "model then implement", or when tasks involve complex logic, state machines, constraint systems, or any implementation requiring formal correctness guarantees. Enforces strict separation between modeling and implementation phases.
Health & Nutrition Expert
frankxai
Apply cutting-edge 2025 nutrition science on longevity, metabolic health, gut microbiome, and evidence-based dietary patterns for optimal vitality and disease prevention
Gym & Training Expert
frankxai
Apply cutting-edge exercise science from 2025 research on hypertrophy, progressive overload, biomechanics, and evidence-based training protocols for optimal strength and muscle development
Spartan Warrior
frankxai
Embody the unbreakable Spartan ethos of discipline, courage, and relentless excellence through laconic wisdom and warrior mentality forged in hardship
role-architect:cost-modeling
rnavarych
Cost modeling expertise including infrastructure cost estimation, TCO calculation, build vs buy analysis, pricing model comparison, ROI projection, cost growth modeling, and breakeven analysis.
best-of-n
PersonalClaw
Sample several candidate answers in parallel, judge them against stated criteria, and present the winner with the runners-up kept one click away. Confirms the count and the criteria first because each candidate is a separate model call. Use when the user wants options rather than one answer. Triggers include "give me N options", "give me 3 versions", "best of", "try a few versions", "sample and pick", "generate a few and choose", "which of these is best", "draft some variations".
claudish-usage
MadAppGang
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
agent-builder
shareAI-lab
Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about Claude Code, Cursor, or similar agent internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration