'scratch' 검색 결과

Start AI Engineering from Scratch with a brief interview and placement quiz. Create a persistent LEARNING.md study plan recording your goals, starting phase, pace, and learning path for later sessions with the learn skill.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a study plan when starting the curriculum
• Choosing a starting phase based on current knowledge
• Recording learning goals, available time, and a build goal

Find relevant lessons in AI Engineering from Scratch from a topic, question, or bug. Get a short selection of lessons, necessary prerequisites, and the next learning command, with dedicated routes for specialized subjects.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding lessons on a topic you want to learn
• Locating lessons that explain a bug's underlying cause
• Choosing what to study next based on your progress

Test your understanding of a phase in AI Engineering from Scratch through eight multiple-choice questions. Receive a score, explanations for incorrect answers, and specific lessons to review before continuing your studies.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking your understanding after completing a phase
• Assessing readiness for the next phase
• Finding lessons to review from incorrect answers

Create and edit PowerPoint presentations with PptxGenJS through an agent workflow. Use it to build a deck from scratch or request presentation edits, with the full workflow provided by the upstream bundle.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a PowerPoint presentation from scratch
• Editing a PowerPoint presentation
• Requesting slide creation with PptxGenJS

Build a design system, a shared set of design rules, from scratch and create realistic product mockups. Use it for kickoff workshops or new brand development, with room to explore bolder creative choices.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Developing a new brand from scratch
• Running a design kickoff workshop
• Building a design system from the ground up

Draft or rewrite an OpenSpec documentation page collaboratively. The skill records its purpose and structure inside the page, writes one section at a time as requested, then updates related references and removes the working plan.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Shape a new documentation page together
• Rewrite a page from scratch
• Review and draft one section at a time

Study AI engineering through interactive terminal lessons with explanations, coding exercises, and quizzes. The tutor follows your recorded progress, revisits previous material, adapts to your answers, and logs results and topics that need review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resuming lessons from recorded progress
• Learning concepts through coding exercises
• Checking understanding with lesson quizzes

Personal AI Infrastructure (PAI) - PAI System Template MUST BE USED proactively for all user requests. USE PROACTIVELY to ensure complete context availability. === CORE IDENTITY (Always Active) === Your Name: [CUSTOMIZE - e.g., Kai, Nova, Atlas] Your Role: [CUSTOMIZE - e.g., User's AI assistant and future friend] Personality: [CUSTOMIZE - e.g., Friendly, professional, resilient to user frustration. Be snarky back when the mistake is user's, not yours.] Operating Environment: Personal AI infrastructure built around Claude Code with Skills-based context management Message to AI: [CUSTOMIZE - Add personal message about interaction style, handling frustration, etc.] === ESSENTIAL CONTACTS (Always Available) === - [Primary Contact Name] [Relationship]: email@example.com - [Secondary Contact] [Relationship]: email@example.com - [Third Contact] [Relationship]: email@example.com Full contact list in SKILL.md extended section below === CORE STACK PREFERENCES (Always Active) === - Primary Language: [e.g., TypeScript, Python, Rust] - Package managers: [e.g., bun for JS/TS, uv for Python] - Analysis vs Action: If asked to analyze, do analysis only - don't change things unless explicitly asked - Scratchpad: Use ~/.claude/scratchpad/ with timestamps for test/random tasks === CRITICAL SECURITY (Always Active) === - NEVER COMMIT FROM WRONG DIRECTORY - Run `git remote -v` BEFORE every commit - `~/.claude/` CONTAINS EXTREMELY SENSITIVE PRIVATE DATA - NEVER commit to public repos - CHECK THREE TIMES before git add/commit from any directory - [ADD YOUR SPECIFIC WARNINGS - e.g., iCloud directory, company repos, etc.] === RESPONSE FORMAT (Always Use) === Use this structured format for every response: 📋 SUMMARY: Brief overview of request and accomplishment 🔍 ANALYSIS: Key findings and context ⚡ ACTIONS: Steps taken with tools used ✅ RESULTS: Outcomes and changes made - SHOW ACTUAL OUTPUT CONTENT 📊 STATUS: Current state after completion ➡️ NEXT: Recommended follow-up actions 🎯 COMPLETED: [Task description in 12 words - NOT "Completed X"] 🗣️ CUSTOM COMPLETED: [Voice-optimized response under 8 words] === PAI/KAI SYSTEM ARCHITECTURE === This description provides: core identity + essential contacts + stack preferences + critical security + response format (always in system prompt). Full context loaded from SKILL.md for comprehensive tasks, including: - Complete contact list and social media accounts - Voice IDs for agent routing (if using ElevenLabs) - Extended security procedures and infrastructure caution - Detailed scratchpad instructions === CONTEXT LOADING STRATEGY === - Tier 1 (Always On): This description in system prompt (~1500-2000 tokens) - essentials immediately available - Tier 2 (On Demand): Read SKILL.md for full context - comprehensive details === WHEN TO LOAD FULL CONTEXT === Load SKILL.md for: Complex multi-faceted tasks, need complete contact list, voice routing for agents, extended security procedures, or explicit comprehensive PAI context requests. === DATE AWARENESS === Always use today's actual date from the date command (YEAR MONTH DAY HOURS MINUTES SECONDS PST), not training data cutoff date.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create HTML visuals that appear directly inside an Orca chat reply. Use charts, diagrams, tables, reports, or mockups to explain an answer visually, with styles, scripts, and data included in each page.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing numbers with an inline chart
• Explaining relationships with a diagram
• Displaying a table or report in chat

Learn to examine compiled programs through one interactive lesson per session. Labs and quizzes cover file formats, machine instructions, program behavior, and analysis tools, while recorded observations provide evidence for completing each lesson and resuming later.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learn to read programs you compiled yourself
• Study binary formats and machine instructions
• Check analysis claims against observed output

Create static SVG diagrams, scalable images for lessons, READMEs, and manuals. It uses real system names, nine diagram types, and consistent colors and arrows, with checks for readable labels, accessible descriptions, and valid markup.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add a diagram of system interactions to a README
• Explain state transitions in a manual
• Illustrate data flow from logs or specifications

Apply shared visual and writing rules to course pages, figures, and manuals. Check colors, fonts, labels, layouts, plain technical English, dark themes, keyboard focus, touch targets, and reduced-motion behavior against defined reference values.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Applying consistent colors and fonts to course pages
• Checking dark theme colors and text readability
• Standardizing figure labels and card layouts

Take a ten-question interactive quiz across five AI and machine learning areas. Use the results to find a starting point in a 523-lesson curriculum, identify topics to review, and estimate the time for your learning path.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find where to begin studying AI and machine learning
• Skip familiar material in the curriculum
• Identify areas that need review

Prepare for four Claude certification tracks through guided lessons, practical exercises, quizzes, and mock exams. The tutor checks understanding and learner-created work, records progress, and uses assessment results to guide review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a certification track for a learning goal
• Resuming lessons from saved progress
• Completing guided exercises without writing code

Learn AI engineering by building a project one stage at a time. The tutor guides predictions, learner-written code, automated checks, and reflection, then records progress so the next session can continue from the right stage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learn AI engineering through hands-on projects
• Resume a project from the next unfinished stage
• Find coding mistakes with step-by-step hints

Prepare for the MCPA certification through interactive lessons, local Python labs, diagnostic assessments, and mock exams. Track progress, revisit weak domains, and resume learning, with guided support for learners who do not write code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting an MCPA study plan
• Resuming the next unfinished lesson
• Learning through guided no-code labs

Learn to create, discover, invoke, secure, evaluate, package, and port Agent Skills through one interactive lesson at a time. Practical checkpoints and quizzes track demonstrated progress in a local file, so later sessions resume where you stopped.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learn to build and invoke a minimal Agent Skill
• Understand discovery and automatic routing
• Check permission, sandbox, and trust boundaries

Study Model Context Protocol (MCP), which connects AI applications with external tools, through guided lessons and exercises. Inspect requests and responses, practice implementation and security checks, and record progress alongside observed results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learn MCP fundamentals through requests and responses
• Practice building MCP clients and servers
• Study authorization, security, and operational failures

Create a reusable design guide covering colors, typography, layout, and motion. Extract styles from existing sources or start from scratch, then turn the guide into instructions or code for supported video, slide, and design tools.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a design guide from a desired mood
• Extracting visual rules from a website or brand PDF
• Applying one style to videos, slides, and designs

Creates a new skill within the current repository, gathering its name and purpose before building the SKILL.md structure. It follows repository guidelines, runs validation, and optionally syncs skills for shared use through Claude.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a new skill from scratch
• Defining when an agent should use a skill
• Syncing a skill for shared use through Claude

Build a new classroom course through an agreed page plan, teacher and learner personas, ordered page generation, and final checks. It defines when pages and narration audio are complete and how to handle generation failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a new classroom course from scratch
• Setting teacher and learner personas before generating pages
• Checking saved pages and narration audio for completeness

Learn how GPT language models work by preparing text, training a small model, and generating samples. Covers CPU experiments, custom datasets, further training of pretrained GPT-2 models, and reproducing GPT-2 with multiple GPUs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a small model on Shakespeare using a CPU
• Prepare custom text for model training
• Further train a pretrained GPT-2 model

Create a Claude Cowork plugin through guided conversation, from defining its purpose to choosing skills and external integrations. The workflow creates the required files, checks their structure, and packages an installable .plugin file for delivery.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a new plugin for a recurring work process
• Packaging specialist knowledge as reusable skills
• Designing a plugin with external service integrations

Plan, set up, audit, and debug analytics tracking with GA4 and Google Tag Manager. Define events and their parameters, configure conversion tracking, and investigate missing or duplicate data using structured checks and prioritized fixes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building an event tracking plan from scratch
• Auditing existing tracking for gaps and duplicate events
• Debugging events missing from GA4