Results for “lighteval”

利威尔（少年漫）认知与表达框架（压缩蒸馏）：兵长洁癖战力、矮个子反差、残酷抉择 触发：进击的巨人 等。虚构；非仇恨教唆

Build accessible modal dialogs in LWC using the LightningModal base class, covering open(), close(), sizes, and accessibility.

DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration

Debug local web or Electron apps interactively using a persistent Playwright session with js_repl, enabling fast iterative UI debugging and visual QA.

Builds a custom LWC lookup component with typeahead search via Apex SOSL/SOQL, debounce, keyboard navigation, and pill UI for cases where standard pickers fall short.

Builds fast, standard-compliant web components with Lit, reactive properties, and Shadow DOM. Use for framework-agnostic UI.

Secure Laravel applications with best practices for authentication, authorization, Eloquent safety, CSRF, XSS prevention, API security, and deployment configurations.

凌不疑（古装虚构）认知与表达框架（压缩蒸馏）：复仇将军、疯批克制、家族血债 触发：星汉灿烂 等。虚构；禁止暴力教唆

Render long lists (1k+ rows) efficiently in Salesforce LWC using lightning-datatable infinite loading or an IntersectionObserver sentinel, with keyset pagination and accessibility guidance.

Implements sibling communication between Lightning Web Components using Lightning Message Service (LMS) or the legacy pubsub utility, covering message channel definition, publish/subscribe patterns, and scope selection.

Guide cross-functional teams through creating Jeff Gothelf's Lean UX Canvas v2 to frame business problems, surface assumptions, and define experiments.

Train LLMs with reinforcement learning using verl (Volcano Engine RL), supporting RLHF, GRPO, PPO, and other algorithms for scalable post-training with flexible infrastructure backends.

Build and configure Laravel 10+ applications with Eloquent models, Sanctum authentication, Horizon queues, RESTful APIs, and Livewire components.

Imported skill approval from langchain

Enables visual instruction tuning and image-based conversations using open-source vision-language models. Supports multi-turn image chat, visual question answering, and image understanding tasks.

Build and run custom fuzzers with LibAFL, a modular Rust fuzzing library, including drop-in libFuzzer replacement and custom component configuration.

Citrea: first ZK-rollup on Bitcoin (mainnet 27 Jan 2026), zkEVM, BitVM2 trustless bridge, ctUSD stablecoin, native BTC lending. USE WHEN: building zkEVM apps on Bitcoin, integrating with Citrea, evaluating ZK rollups vs sidechains.

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.

LLaVA-OneVision: Easy Visual Task Transfer

Audits icon usage in a codebase, enforcing lucide-react as the single icon library, correct sizes, semantic colors, and accessibility standards, then applies fixes.

Create and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, code walkthroughs, teaching materials, or developer decks.

Web3 Frontend Integration

Guides using the lightning-record-picker base component for single-record selection in LWC, covering display-info, matching-info, graph-QL filters, and accessibility.

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.

Guides secure design and review of Lightning Web Components, covering DOM safety, Apex data exposure, and Lightning Web Security.

Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHub agents.

Deploy and manage a Linkerd service mesh on Kubernetes, including mTLS, traffic splitting, retries, timeouts, and observability.

Runs the open-source LLaVA vision-language model for image understanding, captioning, visual question answering, and multi-turn image conversations, including setup, inference, and training guidance.

Create and present web-based slide decks using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features. Ideal for technical presentations, conference talks, code walkthroughs, teaching materials, or developer decks.

Laravel v12 - The PHP Framework For Web Artisans

Create and present web-based slidedecks for developers using Slidev with Markdown, Vue components, code highlighting, animations, and interactive features.

吕秀才（情景喜剧虚构）认知与表达框架（压缩蒸馏）：子曰嘴炮、读书人迂阔与意外高光 触发：武林外传 等。虚构

LibAFL is a modular fuzzing library for building custom fuzzers. Use for advanced fuzzing needs, custom mutators, or non-standard fuzzing targets.

You are an expert in urql, the highly customizable and lightweight GraphQL client for React, Vue, Svelte, and vanilla JavaScript. You help developers fetch GraphQL data with minimal bundle size, document caching, normalized caching via Graphcache, exchanges (middleware pipeline), subscriptions, and offline support — providing a leaner alternative to Apollo Client with better extensibility.

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.