1 774 machine learning skills from 282 authors. They train and fine-tune models, build embeddings, run RAG and measure quality. Half of them fit into 2 253 tokens or less — that is what one costs your context window when the agent loads it. 422 ship runnable scripts rather than instructions alone. 10 of them cannot work without an MCP server, most often rube. We also found 363 copies of these same skills sitting in other people's repositories — counted once here, not 363 times.
1 774 unique 282 authors 905 updated this month 182 from vendors
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
作为代理工程师，采用评估优先执行、分解和成本感知模型路由进行操作。
团队中人工智能代理生成大部分实施输出的工程运营模型。
LLM API 使用成本优化模式 —— 基于任务复杂度的模型路由、预算跟踪、重试逻辑和提示缓存。
创建和更新宣传文稿、一页简介、投资者备忘录、加速器申请、财务模型和融资材料。当用户需要面向投资者的文件、预测、资金用途表、里程碑计划或必须在多个融资资产中保持内部一致性的材料时使用。
PyTorch深度学习模式与最佳实践，用于构建稳健、高效且可复现的训练流程、模型架构和数据加载。
选择在解析结构化文本时使用正则表达式还是大型语言模型的决策框架——从正则表达式开始，仅在低置信度的边缘情况下添加大型语言模型。
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
Analyze labor productivity from site data. Compare planned vs actual, identify trends, benchmark against industry standards.
Compare cost estimates across projects, versions, and scenarios. Identify variances, benchmark against standards, and generate comparison reports.
Analyze and compare subcontractor bids against CWICR benchmarks. Evaluate pricing, identify outliers, and support negotiation.
Semantic search in DDC CWICR construction database using vector embeddings. Find similar work items and resources for cost estimation.
Analyze 5000+ IFC and Revit projects at scale for patterns, benchmarks, and insights. Big data analysis for construction.
Integrate open construction datasets. Combine open data sources for enhanced analysis
Build RAG systems for construction knowledge bases. Create searchable AI-powered construction document systems
Analyze historical construction costs for benchmarking, trend analysis, and estimating calibration. Compare projects, track escalation, identify patterns.
Analyze large-scale construction datasets. Process thousands of projects for patterns, benchmarks, and predictive insights.
Implement semantic vector search for construction data. Build AI-powered search using embeddings and vector databases (Qdrant, ChromaDB) for intelligent querying of specifications, standards, and project documents.
Build ML models for construction predictions. Train and evaluate custom models for cost, duration, and risk prediction.
Predict construction project costs using Machine Learning. Use Linear Regression, K-Nearest Neighbors, and Random Forest models on historical project data. Train, evaluate, and deploy cost prediction models.
Build n8n pipeline for automated cost estimation from Revit/IFC using DDC CWICR database and LLM classification.
Security guidelines for LLM applications based on OWASP Top 10 for LLM 2025. Use when building LLM apps, reviewing AI security, implementing RAG systems, or asking about LLM vulnerabilities like 'prompt injection' or 'check LLM security'. IMPORTANT: Always consult this skill when building chatbots, AI agents, RAG pipelines, tool-using LLMs, agentic systems, or any application that calls an LLM API (OpenAI, Anthropic, Gemini, etc.) — even if the user doesn't explicitly mention security. Also use when users import 'openai', 'anthropic', 'langchain', 'llamaindex', or similar LLM libraries.
Create a personal athlete 81-cell MandalArt grid from an Ohtani Shohei-style 64+8+1 model. Use when the user asks for 大谷翔平 81 宮格, 個人運動員81宮格, sports skill maps, athlete training Mandala charts, badminton 81 grids, or editable JSON/SVG/PNG-ready athlete development templates with Ohtani-style colors.
Design experiment plans with progressive stages — initial implementation, baseline tuning, creative research, and ablation studies. Plan baselines, datasets, hyperparameter sweeps, and evaluation metrics. Use when planning experiments for a research paper.
Discover scientific equations from data using LLM-guided evolutionary search (LLM-SR). Multi-island algorithm with softmax-based cluster sampling, island reset, and LLM-proposed equation mutations. Use for symbolic regression and equation discovery.
LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments