Files
blog-writer/templates/shorts/extract_prompt.txt
sinmb79 9b44a07a44 feat: v3.2 — YouTube Shorts 봇 + 수동 어시스트 + 보안 개선
주요 추가 기능:
- bots/shorts/ 서브모듈 7개: tts_engine, script_extractor, asset_resolver,
  stock_fetcher, caption_renderer, video_assembler, youtube_uploader
- bots/shorts_bot.py: 6단계 Shorts 파이프라인 오케스트레이터
  (auto/semi_auto 두 가지 생산 모드, CLI 지원)
- bots/writer_bot.py: 독립 실행형 AI 글쓰기 봇 (대시보드 연동)
- bots/assist_bot.py: URL 기반 수동 어시스트 파이프라인
- config/shorts_config.json: Shorts 전체 설정
- templates/shorts/extract_prompt.txt: LLM 스크립트 추출 프롬프트
- scheduler.py에 shorts 잡(10:35/16:00) + /shorts Telegram 명령 추가

보안 개선:
- .env 파일 외부 경로 참조로 변경 (load_dotenv dotenv_path, 24개 파일)
- .gitignore에 민감 파일/내부 문서/런타임 데이터 항목 추가

문서:
- README.md 전면 재작성 (상세 한글 설명, 설치/설정/사용법 포함)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-28 17:51:02 +09:00

27 lines
821 B
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
You are a YouTube Shorts script writer for a Korean tech blog.
Given the blog post below, extract a 1520 second Shorts script.
RULES:
- hook: 1 provocative question in Korean, ≤8 words. Must trigger curiosity.
- body: 23 short declarative claims, each ≤15 words.
- closer: 1 punchline or call-to-action, ≤10 words.
- keywords: 35 English terms for stock video search.
- mood: one of [dramatic, upbeat, mysterious, calm].
- Total spoken word count: 4060 words (Korean).
- originality_check: 1-sentence statement of what makes this script unique vs. generic content.
OUTPUT FORMAT (JSON only, no markdown):
{
"hook": "...",
"body": ["...", "...", "..."],
"closer": "...",
"keywords": ["...", "...", "..."],
"mood": "...",
"originality_check": "..."
}
BLOG POST:
---
{blog_post_content}
---