Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Youtube Transcript

ASecurity

YouTube 영상 자막을 추출하고 요약합니다. yt-dlp 기반으로 MCP 없이 로컬에서 안정적으로 동작합니다. /youtube-transcript 또는 "이 영상 자막 가져와"로 실행.

6 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsbash

Works with

mcp

Security Analysis

A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned 9/29/2026

$npx -y skills add Dannykkh/skill-olympus --skill youtube-transcript --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Youtube Transcript?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Youtube Transcript
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/dannykkh-youtube-transcript/badge)](https://www.skillsdirectory.com/skills/dannykkh-youtube-transcript)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: youtube-transcript
description: YouTube 영상 자막을 추출하고 요약합니다. yt-dlp 기반으로 MCP 없이 로컬에서 안정적으로 동작합니다. /youtube-transcript 또는 "이 영상 자막 가져와"로 실행.
---

# YouTube Transcript

> YouTube 영상의 자막을 추출하고 분석합니다. yt-dlp 기반, MCP 불필요.

## Quick Start

```
/youtube-transcript https://www.youtube.com/watch?v=VIDEO_ID
"이 영상 자막 가져와: https://youtu.be/VIDEO_ID"
"이 영상 요약해줘: https://www.youtube.com/watch?v=VIDEO_ID"
```

## Prerequisites

- `yt-dlp` 설치 필요
  - Windows: `pip install yt-dlp` 또는 `winget install yt-dlp`
  - Mac: `brew install yt-dlp`
  - Linux: `pip install yt-dlp`

## Workflow

### 1. URL 추출

`$ARGUMENTS` 또는 사용자 메시지에서 YouTube URL을 추출합니다.

지원 형식:
- `https://www.youtube.com/watch?v=VIDEO_ID`
- `https://youtu.be/VIDEO_ID`
- `VIDEO_ID` (11자리 영숫자)

### 2. yt-dlp 설치 확인 + 자동 설치

```bash
yt-dlp --version
```

미설치 시 **자동 설치** (pip 사용 가능하면):

```bash
pip install yt-dlp
```

pip도 없으면 플랫폼별 안내:
- Windows: `winget install yt-dlp`
- Mac: `brew install yt-dlp`
- Linux: `sudo apt install yt-dlp` 또는 `pip install yt-dlp`

설치 후 다시 `yt-dlp --version`으로 확인하고 진행.

### 3. 자막 언어 확인

```bash
yt-dlp --list-subs "URL" 2>&1 | head -5
```

- 수동 자막(manual)이 있으면 우선 사용
- 없으면 자동 생성 자막(auto-generated) 사용
- 사용자가 언어를 지정하지 않으면 영어(en) → 한국어(ko) 순으로 시도

### 4. 자막 다운로드

```bash
# 임시 파일로 다운로드
yt-dlp --write-auto-sub --sub-lang {LANG} --sub-format srt --skip-download \
  -o "/tmp/yt-transcript-%(id)s" "URL"
```

Windows의 경우:
```bash
yt-dlp --write-auto-sub --sub-lang {LANG} --sub-format srt --skip-download \
  -o "$TEMP/yt-transcript-%(id)s" "URL"
```

### 5. 자막 읽기 + 정리

다운로드된 `.srt` 파일을 Read로 읽고, 타임스탬프를 제거하여 순수 텍스트로 정리합니다.

SRT 형식:
```
1
00:00:00,160 --> 00:00:04,799
This is the subtitle text

2
00:00:02,560 --> 00:00:07,040
Next subtitle line
```

정리 후:
```
This is the subtitle text. Next subtitle line...
```

### 6. 결과 제공

사용자 요청에 따라:

| 요청 | 응답 |
|------|------|
| "자막 가져와" | 정리된 전체 자막 텍스트 출력 |
| "요약해줘" | 자막 기반 핵심 내용 요약 (한국어) |
| "번역해줘" | 자막을 한국어로 번역 |
| 특정 질문 | 자막 내용에서 답변 추출 |

### 7. 임시 파일 정리

```bash
rm -f /tmp/yt-transcript-*.srt 2>/dev/null
# Windows
del "%TEMP%\yt-transcript-*.srt" 2>nul
```

## Options

| 옵션 | 설명 | 기본값 |
|------|------|--------|
| `--lang XX` | 자막 언어 코드 (en, ko, ja 등) | en |
| `--summary` | 자막 추출 후 자동 요약 | false |
| `--raw` | SRT 타임스탬프 포함 원본 출력 | false |

## Error Handling

| 에러 | 대응 |
|------|------|
| yt-dlp 미설치 | 설치 명령어 안내 |
| 영상 없음 / 비공개 | "영상을 찾을 수 없습니다" |
| 자막 없음 | "이 영상에는 자막이 없습니다" |
| 네트워크 오류 | 1회 재시도 후 실패 보고 |

Attribution

DannykkhDannykkh
View sourceSee grades on GitHubMore from Dannykkh →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →