Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/video-intro-outroWrote 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/zju-real/easel/video-intro-outro)<a href="https://agentmods.dev/skills/zju-real/easel/video-intro-outro"><img src="https://agentmods.dev/badge/skills/zju-real/easel/video-intro-outro/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/zju-real/easel/video-intro-outro"><img src="https://agentmods.dev/badge/skills/zju-real/easel/video-intro-outro.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 | $0.00164 | $0.01389 |
| Opus 5 | $0.00082 | $0.00694 |
| Sonnet 5 | $0.00033 | $0.00278 |
| Haiku 4.5 | $0.00016 | $0.00139 |
Grade A, and why
video-intro-outro 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频片头 / 片尾
生成片头/片尾视频卡片（标题 + 副标题 + logo + 关注引导），并把 片头 + 主视频 + 片尾 归一化后拼接成一条成片。全部走
skills/shared/scripts/intro_outro.py，不要手拼 drawtext / xfade——脚本已处理字体路径、音画参数一致、转场时间偏移计算。
只做"片头/片尾卡片 + 拼接"。静态封面图见 poster-hero；通用剪辑见 video-editing； 完整"一句话→成片"流水线见 auto-short-video。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| 主视频 | 拼接时必填 | 要加片头/片尾的视频（没给就问） |
| 标题/副标题 | 推荐 | 片头主题、片尾致谢等文案 |
| 关注引导 CTA | 片尾常用 | 如"点赞 + 关注 不迷路" |
| logo | 可选 | 品牌 logo 图片，叠在标题上方 |
| 画幅 | 可选 | 默认竖版 1080x1920；拼接时默认对齐主视频 |
| 背景 | 可选 | 纯色 / 双色渐变 / 图片 |
输出（outputs/主题名/）
- 片头 / 片尾卡片片段（
intro.mp4/outro.mp4） - 拼接后的成片（
*-final.mp4） - 报告：卡片时长、画幅、转场方式
执行步骤
脚本路径（相对项目根）：skills/shared/scripts/intro_outro.py（各子命令支持 -h）。
1. 生成片头卡片
python skills/shared/scripts/intro_outro.py card \
--title "本期主题" --subtitle "3 分钟讲清楚" \
--gradient --color 0x1a2a6c --color2 0xb21f1f \
--size 1080x1920 --duration 2.5 -o outputs/主题名/intro.mp4
2. 生成片尾卡片（带关注引导）
python skills/shared/scripts/intro_outro.py card --preset outro \
--title "感谢观看" --cta "点赞 + 关注 不迷路" \
--color black --size 1080x1920 --duration 2.5 \
-o outputs/主题名/outro.mp4
背景三选一：--color <色>（纯色）/ --gradient（配 --color/--color2 双色渐变）/
--bg-image <图>（图片背景，自动裁切填满）。--logo <图> 叠加品牌 logo。
3. 拼接到主视频
# 硬切（默认，最稳）
python skills/shared/scripts/intro_outro.py attach --main <主视频> \
--intro outputs/主题名/intro.mp4 \
--outro outputs/主题名/outro.mp4 \
-o outputs/主题名/<名>-final.mp4
# 淡入淡出转场
python skills/shared/scripts/intro_outro.py attach --main <主视频> \
--intro outputs/主题名/intro.mp4 --transition fade --trans-duration 0.5 \
-o outputs/主题名/<名>-final.mp4
--intro / --outro 至少给一个，可只加其一。--transition 可选
none/fade/fadeblack/fadewhite/wipeleft/slideup/circleopen。画幅默认对齐主视频，
--size 可强制。
Profile 感知
- 有 Profile：标题/CTA 语气贴合
style.md人设；有品牌 logo/主色时用作--logo与--color；默认画幅按platforms.md主平台（抖音/小红书竖版 1080x1920，B站/横版 1920x1080）。 - 无 Profile：用中性文案与默认深色背景，竖版 1080x1920，末尾提示可提供品牌信息定制。
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 First seen · 90 lines · 164 tokens per session scan A 6253014abf50
video-intro-outro is a skill published in the GitHub repository ZJU-REAL/Easel (841 stars, last pushed today), licensed Apache-2.0. It adds 164 tokens to every session and 1,389 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
ppt-generation
Generate PPTX presentations from slide plan + content.
chart-visualization
Generate charts: select type, extract data, render image.
jacky-motion2-0-srt
A workflow for turning a Chinese spoken script and matching SRT subtitle file into a single 16:9 HTML information animation. SRT is a subtitle file that stores text with start and end times; the animation follows those times and adds recorded-screen placeholders when needed.
video-podcast-maker
Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video…
video-podcast-maker-lite
Minimal personal narrated-video pipeline — a topic becomes a talking-head-free explainer MP4 (1080p or 4K) via script → Azure TTS (SSML) → Remotion. Use when the user wants a quick narrated video from a topic without the full video-podcast-maker machinery (no extra skills, no thumbnails/shorts/publish matrix). Do NOT…
video-podcast-maker-nano
Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints…