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 ChenShuo2004/cs-skills --skill cs-code-videogit clone --depth 1 https://github.com/ChenShuo2004/cs-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/chenshuo2004/cs-skills/cs-code-video)<a href="https://agentmods.dev/skills/chenshuo2004/cs-skills/cs-code-video"><img src="https://agentmods.dev/badge/skills/chenshuo2004/cs-skills/cs-code-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/chenshuo2004/cs-skills/cs-code-video"><img src="https://agentmods.dev/badge/skills/chenshuo2004/cs-skills/cs-code-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00191 | $0.04524 |
| Opus 5.5 | $0.00076 | $0.01810 |
| Sonnet 5.5 | $0.00038 | $0.00905 |
| Haiku 4.5 | $0.00019 | $0.00452 |
Grade A, and why
cs-code-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 18d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CS 代码视频
模型不直接生成视频。它写一个网页，网页暴露 window.render(t) 画出第 t 秒，脚本逐帧截图，再用 FFmpeg 合成 mp4。配乐和音效用 numpy 合成，配音用 edge-tts。
一句话提示词做视频是抽卡，效果不可控，也复现不了。本 skill 的做法：先把规划摆到用户面前，确认了再动手。5 项输入 → 导演层 → 三张风格卡 → 分镜表（等确认） → 3 张关键帧（等确认） → brief.md → 逐镜头制作 → 自评 ≥8 分 → 交付。
用户明确要 Vibe 知识大赏或来源可核查的代码科普片时，按 references/vibe-knowledge.md 的六步模式执行。它在研究、真实素材、输入默认值、KAI 角色和 10 秒样片上的规则优先于下文通用模式；渲染和 QA 仍用本 skill 的工具。
管线固定，画面不固定。 渲染、配音、混音、QA 每次一样；画面语言每次从选题里长出来，再套上陈硕的签名层。不要先拿模板再塞内容。
交付边界
- 默认值（只在用户明确说「你定」或无人值守时才用，并写进风格卡让用户改）：单个 HTML 工程 + 一支 mp4，1920×1080、30fps、30 秒、代码合成配乐、不配音。
- 通用模式的画面由代码生成，或由 GPT 按资产清单出图后代码做动画（见 hybrid.md）；不从网上下载图片或视频素材。Vibe 知识模式可使用来源和许可可追溯的真实证据图，按对应参考文件记录。
- GPT 出图要花钱：真正出图前先
gen_image.py --dry-run把张数和模型给用户看，确认后再出。 - 通用模式的事实来自用户给的原材料，不确定的不写；Vibe 知识模式必须主动联网核对，建立逐条来源表。
- 参考视频只学结构、节奏和手法，不照搬别人的素材、外观和文案；学到的手法记进
signature.md的吸收清单。 - 不上传、不发布。
- 路由：真实网页演示片 →
$cs-web-promo-film；电商对标复刻、Seedance/Flow 生成包 →$cs-auto-videl；剪辑已有素材、ChatCut 策划 →$cs-chatcut。教程类视频默认做成 KAI 教程片（见 tutorial.md）。像素解说（cs-pixel-explainer）和暗夜知识片（cs-knowledge-film）是系列皮肤，只在用户确认是该系列续集时使用，见 director.md ⑥。
导演铁律（每支片都适用，写进 brief 的 <direction>）
- 整片一套风格、一套配色；同一个角色或元素在每个镜头里长得一样。
- 每个镜头只讲一件事；画面上的字少而大，每段文字至少停 2.5 秒。
- 动画用缓动或弹簧，不用匀速。
- 转场从画面内容里长出来（一条线变成下一个场景的地平线、一个点放大成下一场的月亮），不用默认淡入淡出。
- 镜头跟着内容动：推近、拉远、跟随，主体在画面里足够大（至少三分之一）。
- 禁止：居中大字 + 渐变背景的默认风格、所有元素同时淡入、满屏小字、任何看起来像模板的东西；每支片再按情况补充。
先读什么
按阶段读最少的资料：
- 想画面、配风格、出风格卡：references/director.md，开工前同时看 style-log.md
- Vibe 知识大赏、来源可核查的代码科普片：references/vibe-knowledge.md
- 陈硕的个人风格（不变层）：references/signature.md
- 选代码路线、绿幕人物：references/code-stack.md
- 教程类视频 → KAI 教程片：references/tutorial.md（系列皮肤，结构和画风已锁定，跳过风格卡）
- GPT 出图 × 代码动画（镜头类型、分工、角色一致性、提示词）：references/hybrid.md
- 写 brief：references/brief-template.md
- 制作规则（render(t)、弹簧、字体、WebGL、像素纯度、声音、渲染速度）：references/craft-rules.md
- 自评和验收：references/qa.md
What ships with it
25 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.
- agents/openai.yaml 450 B
- assets/crt.js 3.5 KB runs code
- assets/kai-boy-3d.js 15 KB runs code
- assets/kai-cat-3d.js 14 KB runs code
- assets/kai-cat.js 12 KB runs code
- assets/layers.js 9.7 KB runs code
- assets/reference-wizard.html 23 KB
- assets/template.html 5.5 KB
- assets/voice/tts.py 1.8 KB runs code
- assets/voice/配音.bat 176 B runs code
- references/brief-template.md 3.6 KB
- references/code-stack.md 4.1 KB
- references/craft-rules.md 6.1 KB
- references/director.md 8.4 KB
- references/hybrid.md 6.8 KB
- references/qa.md 2.2 KB
- references/signature.md 10 KB
- references/tutorial.md 5.2 KB
- references/vibe-knowledge.md 6.7 KB
- scripts/audio.py 9.5 KB runs code
- scripts/gen_image.py 7.7 KB runs code
- scripts/qa.py 4.1 KB runs code
- scripts/render.mjs 5.2 KB runs code
- scripts/verify_video.py 2.4 KB runs code
- style-log.md 1.3 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.
- 18d ago Changed · -6 lines 99cd5c31aba5
- 20d ago Changed · +3 lines · -123 tokens per session 48d8f22b0d3d
- 22d ago First seen · 173 lines · 314 tokens per session scan A 18909b62eaed
cs-code-video is a skill published in the GitHub repository ChenShuo2004/cs-skills (204 stars, last pushed 17d ago), licensed MIT. It adds 191 tokens to every session and 4,524 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.