Results for “understanding”

Benchmarks long-context language models across 20 sub-tasks spanning 3k–200k tokens, covering retrieval, reasoning, summarization, and instruction understanding, with exact-match accuracy as the primary metric.

The learner teaches the concept to the AI, which plays a curious novice peer and identifies gaps through authentic questions. Use when the learner wants to test their understanding — teaching forces a different kind of organisation than studying.

Guide for defining and using Claude subagents effectively. Use when (1) creating new subagent types, (2) learning how to delegate work to specialized subagents, (3) improving subagent delegation prompts, (4) understanding subagent orchestration patterns, or (5) debugging ineffective subagent usage.

Foundational Go patterns covering types, interfaces, goroutines, channels, and common idioms. Use when writing Go code, understanding Go's concurrency model, or needing guidance on which specialized Go skill to use. This is the entry point for Go development.

Foundational TypeScript patterns covering types, interfaces, generics, utility types, and common idioms. Use when writing TypeScript code, understanding the type system, or needing guidance on which specialized TypeScript skill to use. This is the entry point for TypeScript development.

Guides agents through the full lifecycle of NeMo-RL experiments: understanding recipes, launching reproducible runs, analyzing results, and preserving human oversight with git and TSV logs.

Foundational F# patterns covering functional-first programming, type providers, computation expressions, and domain modeling. Use when writing F# code, understanding functional patterns, working with type providers, or building .NET applications with F#. This is the entry point for F# development.

Customer insight specialist for audience understanding. Use when defining target audience, buyer personas, customer pains, value mapping, problem discovery, audience language. Triggers: 'who would buy this', 'target audience', 'buyer persona', 'customer pain points', 'ideal customer', 'user problems', 'value proposition', 'audience research'.

Before any explanation or answer, require the learner to produce a free-recall attempt and confidence rating. Use when a student wants help understanding or reviewing a topic — this skill ensures the AI works from what the learner already knows.

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

BitVM, BitVM2, BitVM3: off-chain computation framework using optimistic challenge games on Bitcoin script. Foundation for trust-minimized bridges to L2s and PoS chains. USE WHEN: building trust-minimized bridges, understanding ZK rollup peg-out mechanisms, evaluating bridge security models.

Foundational Rust patterns covering core syntax, traits, generics, lifetimes, and common idioms. Use when writing Rust code, understanding ownership basics, working with Option/Result, or needing guidance on which specialized Rust skill to use. This is the entry point for Rust development.

Foundational Scala patterns covering immutability, pattern matching, traits, case classes, for-comprehensions, and functional programming. Use when writing Scala code, understanding the type system, or needing guidance on which specialized Scala skill to use. This is the entry point for Scala development.

Foundational Swift development patterns covering modern Swift syntax, SwiftUI, protocol-oriented programming, and Cocoa Touch frameworks. Use when writing Swift code, building iOS/macOS/watchOS/tvOS applications, working with SwiftUI or UIKit, understanding Swift concurrency, or needing guidance on Swift project structure.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

Implement dependency injection in Angular v20+ using inject(), injection tokens, and provider configuration. Use for service architecture, providing dependencies at different levels, creating injectable tokens, and managing singleton vs scoped services. Triggers on service creation, configuring providers, using injection tokens, or understanding DI hierarchy.

Foundational SQL patterns for query writing, schema design, and dialect differences. Use when writing SQL queries, designing database schemas, understanding SQL syntax across PostgreSQL/MySQL/SQLite, or preparing SQL for conversion to other query languages. This is a meta-skill for SQL derivatives.

Foundational Python patterns covering core syntax, idioms, type hints, testing, and modern tooling. Use when writing Python code, understanding Pythonic patterns, working with type hints, or needing guidance on which specialized Python skill to use. This is the entry point for Python development.

Foundational Clojure patterns covering functional programming, REPL-driven development, immutable data structures, and idiomatic code. Use when writing Clojure code, working with sequences and lazy evaluation, understanding macros, or needing guidance on functional programming patterns. This is the entry point for Clojure development.

Call the Gemini API for text generation, chat, multimodal understanding, image/video/audio generation, streaming, function calling, structured output, and managed agents using the Interactions API in Python and TypeScript.

Guide for translating code between programming languages. Use when converting code from one language to another, planning language migrations, understanding conversion challenges, asking about type mappings, idiom translations, or referencing pattern mappings. Covers APTV workflow, type systems, error handling, concurrency, and language-specific gotchas.

This skill should be used when executing Bankr requests, submitting prompts to Bankr API, polling for job status, checking job progress, using Bankr MCP tools, or understanding the submit-poll-complete workflow pattern. Provides the core asynchronous job pattern for all Bankr API operations.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.

Writes Python and TypeScript code that calls the Gemini Interactions API for text generation, chat, multimodal understanding, image generation, streaming, research, function calling, and structured output, including migration from the legacy generateContent API.