Borrowing it
Nothing to install: this file belongs to cacity/VideoHub. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cacity/VideoHub/main/.agents/skills/videohub-cover-designer/SKILL.mdgit clone --depth 1 https://github.com/cacity/VideoHubWrote 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/cacity/videohub/videohub-cover-designer)<a href="https://agentmods.dev/skills/cacity/videohub/videohub-cover-designer"><img src="https://agentmods.dev/badge/skills/cacity/videohub/videohub-cover-designer/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/cacity/videohub/videohub-cover-designer"><img src="https://agentmods.dev/badge/skills/cacity/videohub/videohub-cover-designer.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 | $0.00140 | $0.01036 |
| Opus 5 | $0.00070 | $0.00518 |
| Sonnet 5 | $0.00028 | $0.00207 |
| Haiku 4.5 | $0.00014 | $0.00104 |
Grade A, and why
videohub-cover-designer 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
VideoHub Cover Designer
用实际素材制作缩略图优先的系列化封面。不要只生成文件；必须打开成图检查。
工作流
- 确认剧名、集数、两行以内的封面看点及目标平台。
- 读取 cover-design-rules.md。连续剧先找到上一集封面或配置，继承底图、字体、颜色、人物焦点和版式。
- 从用户提供的剧照或原视频选择清晰、可辨识的实际画面。避开黑场、模糊帧、源字幕、水印和剧透画面。
- 使用
scripts/generate_series_covers.py生成目标画幅和清单。只生成用户需要的比例，不要把未要求的画幅塞进发布包。 - 使用
view_image打开实际请求的封面；人物被裁、文字过小、集数不醒目或文字覆盖脸部时，调整焦点或文案后重跑。 - 将封面放进当前项目的发布包，保留生成清单。影视解说项目同时核对标题和封面内容确实出现在成片中。
生成命令
python .agents/skills/videohub-cover-designer/scripts/generate_series_covers.py `
--source "<剧照或干净视频帧>" `
--output-dir "<项目目录>/outputs/cover_assets" `
--title "豺狼的日子" `
--episode "05" `
--episode-label "第5集" `
--hook "骨折靴藏枪" `
--hook "工厂生死围捕" `
--category "谍战悬疑 · 影视解说" `
--focus-x 0.63 `
--focus-y 0.48 `
--landscape-focus-x 0.63 `
--landscape-focus-y 0.20
--focus-x/y 用于竖版和默认画幅；当竖图生成16:9时人物被裁，可用
--landscape-focus-x/y 单独调整横版焦点，不影响已经确认的竖版封面。
横版需要独立构图时，用 --landscape-source 传入单独处理的人物右置或左置底图。
用 --formats cover_3x4.jpg cover_4x3.jpg 限制输出比例；不需要主页预览时增加
--no-thumbnail-preview。
输出：
cover_9x16.jpg：1080x1920cover_3x4.jpg：1080x1440cover_4x3.jpg：1440x1080cover_16x9.jpg：1920x1080thumbnail_preview.jpg：模拟个人主页小图cover_manifest.json：输入、参数、尺寸和 SHA-256
--episode 可省略，适用于电影或单条视频。--hook 最多传两次。人物偏左或偏右时调整 --focus-x；人物偏上或偏下时调整 --focus-y，取值范围均为 0 到 1。
完成标准
- 用户要求的全部图片尺寸正确，文件可解码；未要求的比例不进入发布包。
- 3:4 缩小到约 220 像素宽后，剧名和集数仍可直接辨认。
- 集数使用独立高对比徽标，不依赖小号副标题。
- 人脸、眼睛、武器或关键动作不被文字遮挡，也不被画幅边缘切坏。
- 同一系列各集只改变集数和本集看点，版式、色彩和字体保持一致。
- 不能使用成片未讲到的剧情作标题，也不能用与演员或场景不一致的 AI 剧照。
What ships with it
3 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.
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 · 62 lines · 140 tokens per session scan A af10983df3b9
videohub-cover-designer is a skill published in the GitHub repository cacity/VideoHub (147 stars, last pushed 3d ago), licensed MIT. It adds 140 tokens to every session and 1,036 once invoked, about $0.0007 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
qiaomu-cut
A workflow for turning a brief video idea into a planned, sourced, edited, rendered, and checked video project.
stage-compose
Authoring knowledge for Orkas/OVS HTML video compositions -- write an index.html, drive animation from a paused timeline, declare canvas + duration, then run the VideoStudio draft gate to render an mp4. Trigger for explainer / animation / motion-graphics / caption / lower-third / title-card work, or to build a compose…
frontend-design
Aesthetic direction for OrkasVideoStudio HTML and motion-graphics compositions. Use before stage-compose writes composition-manifest.json artdirection and index.html to choose a subject-specific visual point of view, type, palette, layout signature, restrained motion, and anti-template checks.
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.
stage-plan
The "ingest + plan" half of end-to-end video orchestration — ingest the user's material from evidence, then decompose intent into ONE cross-modal EDL (plan.json: edit/generate/compose/provided segments + narration/music/caption tracks + a delivery promise), validate it with ovs plan validate. Trigger when the…
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…