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/01coder-agent-skills --skill slides-videogit clone --depth 1 https://github.com/sugarforever/01coder-agent-skillsWrote 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/01coder-agent-skills/slides-video)<a href="https://agentmods.dev/skills/sugarforever/01coder-agent-skills/slides-video"><img src="https://agentmods.dev/badge/skills/sugarforever/01coder-agent-skills/slides-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/01coder-agent-skills/slides-video"><img src="https://agentmods.dev/badge/skills/sugarforever/01coder-agent-skills/slides-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 | $0.00140 | $0.03133 |
| Opus 5 | $0.00070 | $0.01566 |
| Sonnet 5 | $0.00028 | $0.00627 |
| Haiku 4.5 | $0.00014 | $0.00313 |
Grade A, and why
slides-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 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slides-Video · 幻灯片驱动的口播视频
制作"一张 PPT 对应一段口播"的结构化视频。本 skill 沉淀的是制作方法和校对流程,不是某一次的视觉风格 —— 风格由用户决定、由下游 skill 实现。
Pre-flight · 依赖检查与 slides skill 选择
本 skill 是编排 + 方法层,自己不生成幻灯片 —— 它调用一个幻灯片生成 skill + video-planner。
| 依赖 | 作用 |
|---|---|
| 一个幻灯片生成 skill | 生成单文件 HTML 横向翻页 deck · 负责所有视觉风格 |
video-planner |
生成 script.md / youtube.md / bilibili.md / x.md 等脚本与发布素材 |
不固定某一个 slides skill —— 从当前可用的里选
开工前先确定用哪个幻灯片 skill:
-
识别候选 —— 会话里能产出单文件 HTML 横向翻页 deck 的 skill 就是候选。常见的有
magazine-web-ppt、guizang-ppt-skill、frontend-slides—— 但以本次会话实际列出的为准,不要假设某个一定在、也不要硬编码某一个。 -
0 个可用 → 不要自己手写 deck 逻辑。告知用户当前没有可用的幻灯片生成 skill,并推荐安装一个再继续,例如:
frontend-slides—— https://github.com/zarazhangrui/frontend-slides- 也可让用户用
find-skills搜索安装
装好后回到第 1 步重新识别。
-
正好 1 个 → 直接用它,并在开工时告诉用户用的是哪个。
-
多个可用 → 必须用
AskUserQuestion跟用户确认选哪个(列出候选 + 各自风格特点),不要替用户拍板。
选定后,后文所有「调用 slides skill」都指这个选中的;video-planner 固定用于脚本与发布素材。任一必需依赖不可用就停下告知用户 —— 不要自己重写 deck / 脚本生成逻辑(那样会失去与生态的一致性)。
建议并行调用 personal-chinese-writing-style 确保语言风格跟作者一致。
适用场景
适合 —— 任何需要用 slides 搭配口播讲解的视频:
- 发布解读(新模型、新产品、新版本)
- 产品评测 / 技术讲解
- 论文 / 报告 / 行业数据拆解
- 多主体横向对比
- 趋势观察 / 现象评论
不适合 —— 纯教程(用通用 video-planner 够了)· 纯屏幕演示(slides 不是主体)· 短视频 / Shorts。
核心原则 · 本 skill 的方法学
这 4 条是贯穿整个工作流的方法原则。不涉及具体风格,只规定做事的方式。
1. PPT-脚本 1:1 同步
每张 PPT 页 = 一段脚本。录视频时翻页 = 切段。
- 脚本每段开头有切页标记:
【PPT 切到 Slide N · 页名】 - 视频总时长 ≈ 页数 × 平均每页 30-50 秒
- 页数预算参考:
- 5-6 分钟 → 约 9 页
- 7-8 分钟 → 约 13-15 页
- 3-4 分钟 → 约 6-7 页
这个 1:1 约束是本 skill 相对通用 video-planner 的核心增量,不可妥协。
2. 语言面向目标受众,而非内部专家
无论受众是 AI 爱好者、开发者还是普通用户:
- 首次出现的术语必须用人话解释一句,不能裸用 jargon
- 用 类比 / 比喻 替代抽象名词(让观众能在头脑里形成图像)
- 每段结尾点出"对受众意味着什么" —— 把技术点翻译成受众能感受到的场景 / 价值
- 数字要带参照系 —— 不要堆"30%"、"1.6T"这类裸数,给参照("相当于 X"、"比上代 Y 倍")
谁是受众在 Step 1 跟用户对齐。不同受众,解释深度和比喻选择不同。
3. 叙事框架二选一
开工前必须决定:
- 单主角 —— 深度拆一个话题/产品 · 页面呈线性展开
- 多主角 —— 多个话题/产品同框对比 · 页面按"每主角独立幕"组织
这决定页面结构。不要含糊开写,中途很难改。
What ships with it
5 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 · 244 lines · 140 tokens per session scan A 939aa5a4db05
slides-video is a skill published in the GitHub repository sugarforever/01coder-agent-skills (134 stars, last pushed 2mo ago), licensed MIT. It adds 140 tokens to every session and 3,133 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
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.