Machine Learning Skills

OWASP LLM Top 10 (2025) audit checklist for AI applications, agent tools, RAG pipelines, and prompt construction. Load during any security review touching LLM client code, prompt templates, agent tools, or vector stores. (triggers: LLM security, prompt injection, agent security, RAG security, AI security, openai, anthropic, langchain, LLM review)

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。

Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.

Machine learning development patterns, model training, evaluation, and deployment. Use when building ML pipelines, training models, feature engineering, model evaluation, or deploying ML systems to production.

Details of the RAG Chatbot, including UI and backend logic.

Details on the Retrieval Augmented Generation pipeline, Ingestion, and Vector Search.

Write token-efficient documentation for LLM context. Use when creating CLAUDE.md, README, technical docs, agent instructions, or any documentation consumed by AI assistants.

Master SurrealDB 2.3.x with Python for multi-model database operations including CRUD, graph relationships, vector search, and real-time queries. Use when working with SurrealDB databases, implementing graph traversal, semantic search with embeddings, or building RAG applications.

Universal dataset import for FiftyOne supporting all media types (images, videos, point clouds, 3D scenes), all label formats (COCO, YOLO, VOC, CVAT, KITTI, etc.), and multimodal grouped datasets. Use when users want to import any dataset regardless of format, automatically detect folder structure, handle autonomous driving data with multiple cameras and LiDAR, or create grouped datasets from multimodal data. Requires FiftyOne MCP server.

Create a FiftyOne dataset from a directory of media files (images, videos, point clouds), optionally import labels in common formats (COCO, YOLO, VOC), run model inference, and store predictions. Use when users want to load local files into FiftyOne, apply ML models for detection, classification, or segmentation, or build end-to-end inference pipelines.

Visualize datasets in 2D using embeddings with UMAP or t-SNE dimensionality reduction. Use when users want to explore dataset structure, find clusters in images, identify outliers, color samples by class or metadata, or understand data distribution. Requires FiftyOne MCP server with @voxel51/brain plugin installed.

Find duplicate or near-duplicate images in FiftyOne datasets using brain similarity computation. Use when users want to deduplicate datasets, find similar images, cluster visually similar content, or remove redundant samples. Requires FiftyOne MCP server with @voxel51/brain plugin installed.

Synthèse co-fabriquée par un conseil de 3 LLMs (Claude, Gemini, Codex). Ce skill devrait être utilisé quand l'utilisateur demande une synthèse robuste, traçable et vérifiée. Il orchestre trois modèles avec des rôles experts distincts (Extracteur, Critique, Architecte) pour produire une synthèse fidèle au texte source, avec contrôle des glissements sémantiques et trail d'audit complet.

| (1) Working with ANY external library (React, Next.js, Supabase, etc.) (2) User asks about library APIs, patterns, or best practices (3) Implementing features that rely on third-party packages (4) Debugging library-specific issues (5) Need current documentation beyond training data cutoff (6) AND MOST IMPORTANTLY, when you are installing dependencies, libraries, or frameworks you should ALWAYS check the docs to see what the latest versions are. Do not rely on outdated knowledge. Always prefer this over guessing library APIs or using outdated knowledge.

Build AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows, and LLM integration. Master prompt engineering, function calling, streaming responses, and cost optimization for 2025+ AI development.

| Build production RAG systems with semantic chunking, incremental indexing, and filtered retrieval. Use when implementing document ingestion pipelines, vector search with Qdrant, or context-aware retrieval. Covers chunking strategies, change detection, payload indexing, and context expansion. NOT when doing simple similarity search without production requirements.

智谱AI的视觉语言模型，用于图像分析、内容识别和视觉问答

AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.

Automated compliance checking against CIS, PCI-DSS, HIPAA, and SOC 2 benchmarks

Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Generate output schemas (dataset_schema.json, output_schema.json, key_value_store_schema.json) for an Apify Actor by analyzing its source code. Use when creating or updating Actor output schemas.

UE Agent Benchmark 评测框架。定义通用评分体系、评测流程和质量层级，支持多场景 Benchmark。触发：用户提及 Benchmark/评测/基准测试/跑分 等关键词时激活。

> Research and compare how competing products implement a similar feature at the UX and interaction level. Provides structured comparison tables and strategic differentiation recommendations.

Use when defining or implementing Go interfaces, designing abstractions, creating mockable boundaries for testing, or composing types through embedding. Also use when deciding whether to accept an interface or return a concrete type, or using type assertions or type switches, even if the user doesn't explicitly mention interfaces. Does not cover generics-based polymorphism (see go-generics).

Use when optimizing Go code, investigating slow performance, or writing performance-critical sections. Also use when a user mentions slow Go code, string concatenation in loops, or asks about benchmarking, even if the user doesn't explicitly mention performance patterns. Does not cover concurrent performance patterns (see go-concurrency).

Finding and accessing AI/LLM model brand icons from lobe-icons library. Use when users need icon URLs, want to download brand logos for AI models/providers/applications (Claude, GPT, Gemini, etc.), or request icons in SVG/PNG/WEBP formats.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Create an llms.txt file from scratch based on repository structure following the llms.txt specification at https://llmstxt.org/

Add instrumentation, build golden datasets, write eval-based tests, run them, root-cause failures, and iterate — Ensure your Python LLM application works correctly. Make sure to use this skill whenever a user is developing, testing, QA-ing, evaluating, or benchmarking a Python project that calls an LLM. Use for making sure an LLM application works correctly, catching regressions after prompt changes, fixing unexpected behavior, or validating output quality before shipping.

Update the llms.txt file in the root folder to reflect changes in documentation or specifications following the llms.txt specification at https://llmstxt.org/

>- Multi-model LLM Council with live dashboard. Query multiple AI models simultaneously, see responses side-by-side in a swarm-style dashboard, synthesize consensus, and run anonymous model-to-model voting. Use when the user asks to start the LLM council, compare models, query multiple models, convene council, ask all models, do model comparison, run multi-model queries, or launch the council dashboard. Supports Claude Sonnet 4.5, Claude Opus 4.5, GPT-4o, GPT-5.1, Gemini 2.5 Flash, and Gemini 2.5 Pro via AI Gateway.

AWS Bedrock foundation models for generative AI. Use when invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns.

| Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques. it is triggered when the user requests assistance with fine-tuning a model, adapting a pre-trained model to a new dataset, or performing... Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.