618 个 · 按相关度排序
Put one question to several models at once — you, OpenAI Codex, and a cheap third via OpenCode — and show all the answers side by side. No judging, no consensus: three opinions, the user picks. Use for "ask everyone", "what do the other models think", "second opinion", "multi ask", or any open question where one model's answer is not enough.
中文简介正在准备中。当前显示原文说明。
Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.
中文简介正在准备中。当前显示原文说明。
Use ENCODE functional genomics data for disease mechanism research. Use when the user wants to connect GWAS variants to regulatory elements, annotate disease-associated loci with functional data, identify therapeutic targets from epigenomic data, build disease regulatory models, cross-reference with clinical trials and drug databases, or conduct any disease-focused, pathology-driven, or clinical variant interpretation workflow. Covers the full pipeline from disease-tissue mapping through GWAS variant annotation, heritability enrichment, cancer epigenomics, drug target identification, and clinical trial cross-referencing. Integrates ENCODE with Open Targets, PubMed, ClinicalTrials.gov, and bioRxiv.
中文简介正在准备中。当前显示原文说明。
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.
中文简介正在准备中。当前显示原文说明。
Generates immutable Dart data classes, sealed union types, and deep copyWith using Freezed (v3.2.x) with optional json_serializable integration. Use when creating DTOs, API response models, app state classes, or any model requiring immutability, pattern matching, or JSON serialization. Activates on: @freezed annotation, freezed_annotation import, immutable data class request, copyWith deep nesting, union/sealed types for loading/data/error states, generic response wrappers, or build_runner code generation for models.
中文简介正在准备中。当前显示原文说明。
Xcode 26 and Apple platform update notes with a focus on Liquid Glass, Foundation Models Framework, and Apple Intelligence. Use when asked to explain, summarize, compare, or implement Xcode 26 era framework changes across SwiftUI, UIKit, AppKit, Foundation, App Intents, StoreKit, MapKit, WidgetKit, visionOS, or Swift language features.
中文简介正在准备中。当前显示原文说明。
Implement Swift Codable models for JSON and property-list encoding and decoding with JSONDecoder, JSONEncoder, CodingKeys, and custom init(from:) or encode(to:). Use when parsing API responses, remapping keys, flattening nested JSON, handling date or data decoding strategies, decoding heterogeneous arrays, or integrating Codable with URLSession, SwiftData, or UserDefaults.
中文简介正在准备中。当前显示原文说明。
FastAPI best practices and conventions. Use when working with FastAPI APIs and Pydantic models for them. Keeps FastAPI code clean and up to date with the latest features and patterns, updated with new versions. Write new code or refactor and update old code.
中文简介正在准备中。当前显示原文说明。
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
中文简介正在准备中。当前显示原文说明。
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.
中文简介正在准备中。当前显示原文说明。
Claude API (platform.claude.com) のモデル・SDK。 model ID・選択基準、Fable・Mythos 5.1 / Opus・Sonnet・Haiku 5.5 移行・破壊的変更、 コスト最適化 (effort / caching / batch / advisor)、pricing、deprecation、用語集。 公式 SDK 7 言語 (Python / TypeScript / Java / Go / Ruby / C# / PHP)、 Claude API 用 CLI `ant` (Claude Code CLI とは別。quickstart / authentication / scripting、`ant apply` resources as code、Managed Agents session 接続)、 middleware、OpenAI SDK 互換、Apple Foundation Models。
中文简介正在准备中。当前显示原文说明。
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library
中文简介正在准备中。当前显示原文说明。
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
中文简介正在准备中。当前显示原文说明。
Apple FoundationModelsフレームワークによるオンデバイスLLM — テキスト生成、@Generableによるガイド生成、ツール呼び出し、iOS 26+でのスナップショットストリーミング。
中文简介正在准备中。当前显示原文说明。
Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.
中文简介正在准备中。当前显示原文说明。
Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff.
中文简介正在准备中。当前显示原文说明。
通过日志和复现操作排查OpenClaw的模型通信、工具执行及响应流问题，并检查已保存的对话和附件，为修复原因与再次验证收集证据。
从测试开始实现 Laravel 功能，使用 PHPUnit 或 Pest 验证模型、API、身份认证和权限，模拟外部服务，并通过覆盖率了解测试执行了哪些代码。
帮助您使用Unsloth，以LoRA和QLoRA微调语言模型，探索减少GPU内存占用的训练方式，并依据官方文档整理的参考资料查询功能与API、实现代码和排查错误。
通过Flow Nexus在E2B隔离环境中训练和部署神经网络，执行预测、监控分布式训练，并进行性能评估和模型共享。
Organize PyTorch models and data pipelines with PyTorch Lightning, automate training, save checkpoints, and track experiments. Includes templates and guidance for configuring training across multiple GPUs or TPUs.
中文简介正在准备中。当前显示英语简介。
Plan how an AI application should use Hindsight memory. Identify useful information to retain, define user-scoping tags and memory bank settings, and specify how retrieved facts and synthesized knowledge should reach the model.
中文简介正在准备中。当前显示英语简介。
Build TypeScript code for Azure AI Foundry projects using its SDK, a library for accessing project services. Create and run agents, inspect connections and deployed models, and manage datasets and search indexes.
中文简介正在准备中。当前显示英语简介。
Generate client libraries for REST APIs, with authentication, retries, typed request and response models, error classes, and pagination helpers. Language-specific patterns and usage examples show how applications can call API resources.
中文简介正在准备中。当前显示英语简介。