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 sexybells/video-studio-mcp --skill skillgit clone --depth 1 https://github.com/sexybells/video-studio-mcpWrote 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/sexybells/video-studio-mcp/skill)<a href="https://agentmods.dev/skills/sexybells/video-studio-mcp/skill"><img src="https://agentmods.dev/badge/skills/sexybells/video-studio-mcp/skill/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/sexybells/video-studio-mcp/skill"><img src="https://agentmods.dev/badge/skills/sexybells/video-studio-mcp/skill.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 | $0.00092 | $0.02646 |
| Opus 5 | $0.00046 | $0.01323 |
| Sonnet 5 | $0.00018 | $0.00529 |
| Haiku 4.5 | $0.00009 | $0.00265 |
Grade A, and why
video-studio 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 9d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Studio
Sinh video dọc 9:16 từ ảnh thật (Public Domain / CC) + giọng đọc AI + phụ đề, render MP4 bằng Remotion. Nhiều template, mỗi template một schema content.json riêng.
Phạm vi
LÀM: cho chọn template → viết kịch bản đúng sự thật → tìm & tải ảnh PD/CC → giọng đọc (ElevenLabs eleven_turbo_v2_5, giọng do template chọn — xem mục Giọng đọc) → render + kiểm tra + ghi nguồn.
KHÔNG: bịa ảnh bằng AI, bịa sự kiện/ngày tháng, dùng ảnh bản quyền hạn chế.
Hai quy tắc quan trọng nhất
1. Chỉ đi MỘT đường: CLI hoặc MCP — không bao giờ cả hai. Cả hai đường đều gọi cùng npm run voiceover/npm run render trên cùng thư mục project, nên chạy lẫn lộn là render hai lần (tốn vài phút và ghi đè MP4 giữa chừng).
- Thấy tool
create_video/render_video(MCPvideo-studiođang bật) → đi đường MCP ở mục Quy trình — MCP, và không chạy lệnh shell nào cho project. - Không thấy các tool đó → đi đường CLI ở mục Quy trình — CLI.
Thấy cả hai thì vẫn chỉ chọn MCP. Đừng bao giờ chạy xen kẽ.
2. Luôn để người dùng chọn template. Liệt kê template (CLI: ls <skill>/templates; MCP: list_templates), trình bày lựa chọn, rồi dùng AskUserQuestion. Đừng tự chọn thay họ. Sau khi chọn, đọc schema của đúng template đó (CLI: templates/<id>/template.json; MCP: template_schema <id>) — mỗi template một schema riêng, đừng bê cấu trúc template này sang template khác.
Quy trình — CLI (terminal)
S=~/.claude/skills/video-studio
P=~/Work/VideoReview/<slug>
ls $S/templates # 1. template hiện có (bỏ qua thư mục _shared)
cat $S/templates/<id>/template.json # 2. schema + loại cảnh của template người dùng chọn
node $S/scripts/wikimedia-images.mjs search "<từ khoá tiếng Anh>" 6 # 3. tìm ảnh PD/CC
bash $S/scripts/new-video-project.sh <slug> <id> # 4. scaffold + npm install
node $S/scripts/wikimedia-images.mjs get "<url|File:Ten.jpg>" $P/public/images/<ten>.jpg
# 5. viết $P/content.json theo schema template (voiceover 1–2 câu mỗi cảnh)
export ELEVENLABS_API_KEY=... # 6. key của NGƯỜI DÙNG (thiếu key → fallback `say`, chỉ macOS)
cd $P && npm run build # voiceover + render, MỘT lần -> out/video.mp4
ffprobe -v error -show_format -show_streams -of json out/video.mp4 # 7. thời lượng + có audio?
mkdir -p qa && for t in 3 15 30; do ffmpeg -y -ss $t -i out/video.mp4 -frames:v 1 qa/f_$t.jpg -loglevel error; done
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.
- 9d ago First seen · 109 lines · 92 tokens per session scan A caf7ab03b7f3
video-studio is a skill published in the GitHub repository sexybells/video-studio-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 2,646 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).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
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.