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 ZJU-REAL/Easel --skill skill-carousel-plannergit clone --depth 1 https://github.com/ZJU-REAL/EaselWrote 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/skill-carousel-planner)<a href="https://agentmods.dev/skills/zju-real/easel/skill-carousel-planner"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-carousel-planner/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/skill-carousel-planner"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-carousel-planner.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 | $0.00116 | $0.01810 |
| Opus 5 | $0.00058 | $0.00905 |
| Sonnet 5 | $0.00023 | $0.00362 |
| Haiku 4.5 | $0.00012 | $0.00181 |
Grade A, and why
skill-carousel-planner 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
轮播图规划
规划多图笔记/轮播图的分页结构：封面 Hook、内容节奏、每页文案和视觉方向、CTA 设计，附互动潜力评分。
加载后立即开始规划流程，不做摘要或等待确认。
关键参考文件：
references/format-specs.md-- 尺寸规范、页数限制、文字大小references/hook-library.md-- 经过验证的封面 Hook 公式及互动数据references/scoring-system.md-- 互动评分维度与阈值
输入
用户 prompt 中提供的主题和目标。可以是关键词、一句话描述，或详细 brief。
输出
结构化轮播图规划文档，包含：封面文案、逐页分解、配文、评分卡、制作备注。
保存到 outputs/主题名/carousel-brief.md。
执行步骤
第一步：确认上下文
- 从用户 prompt 中提取主题和目标（教育、转化、建立权威、娱乐）。
- 识别目标受众。
- 加载所有关键参考文件。
- 查阅
references/hook-library.md，找到与主题最匹配的高互动 Hook 类型。
第二步：封面页 Hook
封面页遵循与短视频开头相同的规则：必须在 1 秒内打断滑动。
封面 Hook 规则
- 封面文字不超过 12 个字
- 必须制造好奇缺口或情绪触发
- 使用
references/hook-library.md中经过验证的 6 个公式：- 反常识： "别再XX了"
- 数字清单： "5 个毁掉XX的错误"
- 对比冲击： 前后对比的视觉悬念
- 直击痛点： "为什么你XX总是失败"（陈述式，不加问号）
- 颠覆声明： "这会改变你的一切"
- 身份认同： "XX 人必看"（收藏率 + 分享率高）
- 字体必须大、加粗，在缩略图尺寸下也清晰可读
- 封面不放 logo 或品牌标识（会削弱好奇心）
记录选定的 Hook 公式和封面文案。
第三步：分页结构
按 Hook > 内容铺垫 > 揭晓 > 行动号召 弧线编排：
| 页码 | 角色 | 规则 |
|---|---|---|
| 1 | Hook / 封面 | 不超过 12 字，好奇缺口，见第二步 |
| 2-3 | 问题 / 铺垫 | 建立痛点或抛出问题 |
| 4-7 | 内容 / 价值 | 每页一个要点，页面文字不超过 20 字 |
| 8-9 | 揭晓 / 收获 | 交付核心洞察或转变 |
| 末页 | 行动号召 | 收藏/分享/关注引导 |
每页内容规则
- 每页只讲一个点。 需要逗号就拆页。
- 每页文字不超过 20 字（文字叠层）。越少越好。
- 视觉统一： 全篇使用相同的背景风格、字体和配色。
- 阅读动线： 从上到下，从左到右。不散乱排布。
- 翻页动力： 每页必须制造让读者翻到下一页的理由。
逐页输出：
- 页码
- 页面文案（文字叠层，不超过 20 字）
- 视觉描述
- 翻页动力说明（读者为什么会翻到下一页）
第四步：末页行动号召
末页决定帖子能否被收藏和转发。根据内容类型选择：
| CTA 类型 | 适用场景 | 示例 |
|---|---|---|
| 收藏引导 | 干货教程类 | "收藏备用" / "先码住" |
| 分享引导 | 共鸣实用类 | "@你身边的XX" / "转给需要的人" |
| 关注引导 | 系列内容 | "关注看更多" / "下期更新XX" |
| 评论引导 | 观点讨论类 | "你是哪种？评论区告诉我" |
| 私信引导 | 引流转化类 | "评论区回复'方案'领取完整版" |
CTA 必须具体。禁止使用空泛的"点击主页"作为主要 CTA。
第五步：配文
撰写与轮播图互补（不重复）的配文：
- 第一句：独立于轮播图也能打的 Hook
- 正文：展开轮播图中的某一点，加入个人视角
- 结尾：与末页 CTA 呼应
- 话题标签：3-5 个垂直标签，禁用泛标签（#生活 #日常 这类无效）
- 配文长度：300-800 字（小红书最佳区间）
第六步：互动评分
使用 references/scoring-system.md 中的标准评分：
| 维度 | 权重 | 评分 (1-10) |
|---|---|---|
| Hook 强度 | 25% | |
| 翻页节奏 / 翻页动力 | 20% | |
| 价值密度 | 20% | |
| CTA 有效性 | 15% | |
| 视觉统一性 | 10% | |
| 配文质量 | 10% |
What ships with it
4 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.
- 9d ago First seen · 175 lines · 116 tokens per session scan A f4069cf74add
skill-carousel-planner is a skill published in the GitHub repository ZJU-REAL/Easel (494 stars, last pushed 2d ago), licensed Apache-2.0. It adds 116 tokens to every session and 1,810 once invoked, about $0.0006 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
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…