Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AX-Surfers/vibecut --skill vibecut-youtube-descriptiongit clone --depth 1 https://github.com/AX-Surfers/vibecutWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ax-surfers/vibecut/vibecut-youtube-description)<a href="https://agentmods.dev/skills/ax-surfers/vibecut/vibecut-youtube-description"><img src="https://agentmods.dev/badge/skills/ax-surfers/vibecut/vibecut-youtube-description/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ax-surfers/vibecut/vibecut-youtube-description"><img src="https://agentmods.dev/badge/skills/ax-surfers/vibecut/vibecut-youtube-description.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00109 | $0.01927 |
| Opus 5 | $0.00055 | $0.00963 |
| Sonnet 5 | $0.00022 | $0.00385 |
| Haiku 4.5 | $0.00011 | $0.00193 |
Grade A, and why
vibecut-youtube-description scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
vibecut-youtube-description 스킬
CapCut 자막 → 영상 흐름 파악 → 유튜브 제목 + 설명 + 챕터 자동 생성 파이프라인.
핵심 처리 흐름
CapCut draft_info.json
├─ [1] 프로젝트·타임라인 결정 → 전체 자막 추출 (타임스탬프 + 텍스트)
├─ [2] 영상 정보 확인 (GitHub 링크, 커뮤니티 링크 등) — config 있으면 자동, 없으면 질문
├─ [3] 제목 3가지 생성
├─ [4] 설명 생성 (후크 → 요약 → 링크 → 📌 다루는 내용 → ⏱️ CHAPTERS)
└─ [5] youtube_description.txt 저장
실행 절차
1단계: 프로젝트 결정 + 자막 추출
경로는 하드코딩하지 않고 설정(~/.vibecut/config.json의 capcut_projects_dir, 또는
VIBECUT_CAPCUT_DIR)에서 읽습니다. 프로젝트 이름을 모르면 최근 프로젝트를 나열합니다.
SCRIPTS=$(python3 -c "import json,os; print(json.load(open(os.path.expanduser('~/.vibecut/config.json'))).get('scripts_dir',''))")
uv run "${SCRIPTS}/find_project.py" --recent 5 # <프로젝트 경로>\t<타임라인 이름들>
PROJECT="<CapCut 프로젝트 경로>"
TIMELINE="<타임라인 이름 또는 빈 문자열>" # 타임라인이 여러 개면 지정 필수
uv run python - "${PROJECT}" "${TIMELINE}" "${SCRIPTS}" <<'PYEOF'
import json, sys
from pathlib import Path
project, timeline, scripts = sys.argv[1:4]
sys.path.insert(0, scripts)
from capcut_editor import draft_path_for, resolve_timeline
proj = Path(project)
tl, _ = resolve_timeline(proj, timeline or None)
draft = json.loads(draft_path_for(proj, tl).read_text(encoding="utf-8"))
mat_map = {t["id"]: t for t in draft["materials"].get("texts", [])}
# 자막 트랙 = type이 text인 트랙 중 세그먼트가 가장 많은 것 (tracks[1] 고정 가정 금지)
text_tracks = [t for t in draft["tracks"] if t.get("type") == "text" and t.get("segments")]
if not text_tracks:
raise SystemExit("❌ 자막 트랙이 없습니다 — 먼저 vibecut-add-subtitles 를 실행하세요")
track = max(text_tracks, key=lambda t: len(t["segments"]))
subs = []
for seg in sorted(track["segments"], key=lambda s: s["target_timerange"]["start"]):
mat = mat_map.get(seg["material_id"])
if not mat:
continue
text = json.loads(mat["content"]).get("text", "").strip()
if text:
subs.append((seg["target_timerange"]["start"] / 1e6, text))
for st, text in subs:
m, s = divmod(int(st), 60)
print(f" {m:02d}:{s:02d} {text}")
print(f"\n자막 {len(subs)}줄, 영상 길이 {draft['duration']/1e6/60:.1f}분")
PYEOF
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago Changed · -5 lines 3104c9034f0c
- 11d ago First seen · 212 lines · 109 tokens per session scan A 6a887b677ef8
vibecut-youtube-description is a skill published in the GitHub repository AX-Surfers/vibecut (2 stars, last pushed 8d ago), licensed MIT. It adds 109 tokens to every session and 1,927 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.