Content Digest

This turns any content into a quiz-first learning session. Drop in a YouTube URL, tweet, article, or PDF and it spins up a task agent to extract and clean the text, then runs web research on key concepts before you see anything. You get three warmup questions first (pretesting effect), pick what sections you want to read, then nine more questions across three difficulty levels. The workflow is built to keep your main context clean while subagents chew through transcripts and scraping. After the quiz it offers elaborative interrogation on concepts you missed and expands into foundational research beyond the original content. Good for when you want to actually retain something instead of just skimming another article.

skills.sh installs: 1.3K
GitHub stars: 19
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ai-native-camp/camp-2 --skill content-digest --agent claude-code

Installs into .claude/skills of the current project.

Files

Content Digest

콘텐츠 → Quiz-First 학습 → 선택적 깊이 탐색 → 근본 개념 확장.

Task Agent 기반 설계: 긴 컨텍스트는 subagent가 처리하고, 메인 세션은 최종 결론만 소비

아키텍처 원칙

Context Separation: 긴 자막/본문은 Task agent가 처리, 메인 세션은 가벼운 md 파일만 Read
Clean Transcript: 자막에서 번호, 시간 제거 → 순수 영어 텍스트만 추출
Web Research Integration: 추출된 키워드로 자동 웹 리서치
Single Output: 모든 처리 결과는 단일 md 파일로 저장

지원 콘텐츠

타입	추출 방법	저장 경로
YouTube	Task agent (yt-dlp + 정제)	`research/digests/youtube/`
X/Twitter	fetch-tweet 스킬 (api.fxtwitter.com)	`research/digests/tweet/`
Webpage	Task agent (browser + 정제)	`research/digests/web/`
PDF	Task agent (Read + 정제)	`research/digests/pdf/`