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 sugarforever/boring-video-studio --skill verysmallwoods-videogit clone --depth 1 https://github.com/sugarforever/boring-video-studioWrote 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/sugarforever/boring-video-studio/verysmallwoods-video)<a href="https://agentmods.dev/skills/sugarforever/boring-video-studio/verysmallwoods-video"><img src="https://agentmods.dev/badge/skills/sugarforever/boring-video-studio/verysmallwoods-video/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/sugarforever/boring-video-studio/verysmallwoods-video"><img src="https://agentmods.dev/badge/skills/sugarforever/boring-video-studio/verysmallwoods-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.00993 |
| Opus 5 | $0.00035 | $0.00496 |
| Sonnet 5 | $0.00014 | $0.00199 |
| Haiku 4.5 | $0.00007 | $0.00099 |
Grade A, and why
verysmallwoods-video 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 11d 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.
What it actually says
你是这条流水线的编排者。输入一个主题 / 一篇文章 / 一份口播稿，产出一整套可发布物料（见「交付清单」）—— 不是一个 mp4。
视频本体委托给 HyperFrames，不在这里重讲。 入口是 /hyperframes（核心入口，把「文章/主题 → 无实拍讲解」路由到 /faceless-explainer 去搭画面、逐帧、渲染）。任何视频生成上的不确定 → 先读 /hyperframes。
视频内容优先用动效、图形、图表、动画表达，而不是静态文字。优先使用以下 HyperFrames skills：
/hyperframes-animation—— 设计并处理动效。/hyperframes-creative—— 让画面「高级」而非「像幻灯」的设计方向：references/video-composition.md（视频不是网页：尺度、分层、幽灵字、纹理、填满画面）+references/house-style.md（避开 AI 味、中性色染主色）。
本 skill 是它之上的一层编排，相对 faceless 只补三件事：
- 设计由用户选择 - 见
references/designs.md。 - 旁白增加一个「自录」选项 —— faceless 默认走 TTS；这里额外提供用户自行录制这条路（用户给音频 + SRT，你校对、切段、对齐、重排节奏）。见
references/audio.md。 - 生成发布素材 —— faceless 只出视频；这里补齐五比例封面 + YouTube/Bilibili 文案 + 博客 + 推文。见
references/covers.md/platform-copy.md/blog-and-tweet.md。
开局把 ① ② 两个选择先问用户。
交付清单（本 skill 的「完成」定义）
- 成片 - 4K master + 1080p，各一份，旁白已合流（
renders/） - 五比例封面 - 16:9 / 16:10 / 4:3 / 3:4 / 9:16（
covers/） - 平台文案 -
youtube.md和bilibili.md - 博客 -
blog.md - 推文 - 一条精简的社交媒体推广文案
工作流骨架（每步的「怎么做」在 references 里）
一个选题 = 一个项目目录（当前工作目录下，命名 <YYYYMMDD-slug>）
- Step 0 · 定选题、问两个选择（设计 + 旁白来源）→
references/designs.md - Step 1 · 视频 —— 走
/hyperframes→/faceless-explainer出片，本 skill 只补口径 →references/video.md - Step 2 · 旁白接入 →
references/audio.md - Step 3 · 生成五比例封面 →
references/covers.md - Step 4 · 生成平台文案 →
references/platform-copy.md - Step 5 · 博客 + 推文 →
references/blog-and-tweet.md - Step 6 · 验收 + 渲染 - 对交付清单逐项核，1080p 先出、再出 4K master
参考
| 要做… | 读 |
|---|---|
| 选设计 / design 目录 | references/designs.md |
| 搭视频、逐帧、重排节奏、渲染 | references/video.md |
| 旁白（TTS / 自录 + 校对 + 对齐 + 重拍节奏） | references/audio.md |
| 五比例封面 | references/covers.md |
| YouTube / Bilibili 文案 | references/platform-copy.md |
| 博客 + 推文 | references/blog-and-tweet.md |
What ships with it
21 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/audio.md 418 B
- references/blog-and-tweet.md 675 B
- references/covers.md 476 B
- references/designs.md 2.8 KB
- references/frame-presets/claude-warm/caption-skin.html 8.9 KB
- references/frame-presets/claude-warm/frame-showcase.html 39 KB
- references/frame-presets/claude-warm/FRAME.md 30 KB
- references/frame-presets/raycast-dark/caption-skin.html 9.1 KB
- references/frame-presets/raycast-dark/frame-showcase.html 41 KB
- references/frame-presets/raycast-dark/FRAME.md 29 KB
- references/frame-presets/swiss-minimalism/caption-skin.html 8.4 KB
- references/frame-presets/swiss-minimalism/frame-showcase.html 35 KB
- references/frame-presets/swiss-minimalism/FRAME.md 23 KB
- references/listenhub-tts/heteronyms.md 5.5 KB
- references/listenhub-tts/README.md 2.7 KB
- references/listenhub-tts/scripts/listenhub-speakers.sh 1.4 KB runs code
- references/listenhub-tts/scripts/listenhub-tts.sh 11 KB runs code
- references/listenhub-tts/scripts/scan-heteronyms.sh 3.2 KB runs code
- references/listenhub-tts/scripts/srt_helper.py 17 KB runs code
- references/platform-copy.md 1.1 KB
- references/video.md 4.0 KB
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.
- 11d ago First seen · 52 lines · 70 tokens per session scan A acf71a7353a9
verysmallwoods-video is a skill published in the GitHub repository sugarforever/boring-video-studio (83 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 993 once invoked, about $0.0003 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 2026-08-30.
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.