41건 · 관련도순
Select and sequence reading comprehension strategies matched to a specific text's challenges and demands. Use when students struggle with a text or need targeted reading support.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Select and sequence reading comprehension strategies matched to a specific text's challenges and demands. Use when students struggle with a text or need targeted reading support.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when the user asks to "test our messaging before we scale it", "design a message-market-fit panel", or "run a 5-second comprehension test on our new tagline"; produces a message-test design spec — hypothesis, panel and recruit criteria, comprehension / 5-second / message-market-fit (Wynter-style) protocols, stimulus set drawn from the canon, success thresholds, and a stop/revise decision rule — for the TALE Evaluate phase so the message is validated before any paid scale. It designs the test; it never runs the experiment or adjudicates a claim. Not for running the panel or A/B experiment — use send-experiment-designer or ad-test-designer; not for analyzing the results — use performance-analyzer; not for authoring the message itself — use message-system-architect. 消息测试/理解度测试/面板设计/五秒测试/消息市场契合
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Script a teacher think-aloud demonstrating expert reasoning processes for a specific task. Use when modelling problem-solving, writing, reading comprehension, or analytical processes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Performs deep AI-powered analysis and understanding of long-form videos (up to 3 hours, 10GB) using Volcengine LAS large language models. Video analysis, video comprehension, and video summarization — generates comprehensive video summaries, video recaps, chapter breakdowns, event timelines, key moments, and structured content indexing. Supports behavior detection, action detection, video annotation, video tagging, and video content recognition. Enables intelligent video question answering — ask questions about video content and get AI answers. Handles long meeting recordings, lecture videos, webinars, surveillance and security footage, movies, tutorials, and any long video that needs detailed understanding. Async processing with submit-poll workflow. Use this skill when the user wants to analyze or understand long videos (up to 3h/10GB) with LLM-based deep comprehension, summarize video content or generate recaps, extract chapters/key moments/timelines from videos, do video Q&A (ask questions about video content), detect actions/behaviors in videos, review meeting recordings/lectures/webinars, or get structured video descriptions.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Script a teacher think-aloud demonstrating expert reasoning processes for a specific task. Use when modelling problem-solving, writing, reading comprehension, or analytical processes.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use when the user asks to "test our messaging before we scale it", "design a message-market-fit panel", or "run a 5-second comprehension test on our new tagline"; produces a message-test design spec — hypothesis, panel and recruit criteria, comprehension / 5-second / message-market-fit (Wynter-style) protocols, stimulus set drawn from the canon, success thresholds, and a stop/revise decision rule — for the TALE Evaluate phase so the message is validated before any paid scale. It designs the test; it never runs the experiment or adjudicates a claim. Not for running the panel or A/B experiment — use send-experiment-designer or ad-test-designer; not for analyzing the results — use performance-analyzer; not for authoring the message itself — use message-system-architect. 消息测试/理解度测试/面板设计/五秒测试/消息市场契合
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Read a supplied paper in depth and produce a structured Markdown explanation of its research logic, essential design choices, and evidence limits. Work through key equations with concrete numerical examples and identify missing controls or unreported information.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Write, review, and refactor Python code using concrete readability rules. Keep functions focused, reduce nested logic, clarify names and expressions, and apply Python features such as comprehensions, dataclasses, and pathlib while respecting existing codebase conventions.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Build text that reveals word by word as readers scroll. Preserve inline links, emphasis, and responsive wrapping, while keeping complete text accessible to screen readers and immediately readable when reduced motion is preferred.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Download, split, and deeply read academic PDFs. Use when asked to read, review, or summarize an academic paper. Splits PDFs into 4-page chunks, reads them in small batches, and produces structured reading notes — avoiding context window crashes and shallow comprehension.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Provides adversarial code comprehension for security research, mapping architecture, tracing data flows, and hunting vulnerability variants to build ground-truth understanding before or alongside static analysis.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Reference guide for translating Python syntax constructs to Scala equivalents. Use when converting Python code to Scala and need mappings for basic syntax elements like variable declarations, control flow, comprehensions, string formatting, and common operators.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Build a library of metacognitive prompts targeting planning, monitoring, or evaluation for a specific task. Use when developing students' thinking-about-thinking during independent work.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Generate elaborative interrogation prompts that deepen encoding through targeted why and how questions. Use when students memorise without understanding or need deeper processing of content.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Create self-explanation prompts that deepen understanding of worked examples, texts, or diagrams. Use when students read material passively without engaging with underlying principles.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design metacognitive checkpoints that prevent AI-assisted learning from bypassing genuine understanding. Use when students use AI tools and may overestimate their own comprehension.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design a checking-for-understanding protocol with specific techniques for each lesson stage. Use when planning systematic comprehension checks during explicit or direct instruction.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Inspect a Core UI or code surface for a small number of justified motion opportunities and explicitly identify what should remain static. Use when asked what should animate, where motion would improve feedback or comprehension, how to make an interface feel more alive without over-animating it, or whether a proposed animation is worth adding. Read-only; do not use to review or fix existing motion code or to implement animations.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Routes tasks for discovering NLP datasets in the CLUEDatasetSearch catalogue, including Chinese NLP classification, QA, matching, NER, generation, translation, corpus, and reading-comprehension resources.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Generate concise, structured summaries of requirements for quick team understanding. Use when analyzing requirements from text documents (MD, TXT, DOCX) or technical specifications to create bullet-point summaries that highlight core functionality and dependencies/constraints. Ideal for sprint planning, stakeholder updates, team onboarding, or any situation requiring rapid comprehension of requirement documents.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Interactive codebase orientation for a HUMAN who wants to learn the code. Runs the same tree-sitting + featuring pipeline as exploring-codebases but synthesizes it into guided exercises and an HTML teaching artifact rather than an analysis document. Use for "orient me to this repo", "teach me this codebase", "walk me through this code", "learning orientation", or when someone wants genuine comprehension rather than a task completed. The audience is the test: if nobody is being taught and the goal is to get work done, use exploring-codebases instead.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Design metacognitive checkpoints that prevent AI-assisted learning from bypassing genuine understanding. Use when students use AI tools and may overestimate their own comprehension.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Create self-explanation prompts that deepen understanding of worked examples, texts, or diagrams. Use when students read material passively without engaging with underlying principles.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.