Individual skill

cs-code-video

用代码做动画视频：页面暴露 render(t)，Playwright 逐帧截图 + FFmpeg 合成 mp4，可接合成配乐、出图和配音。通用模式先明确主题、规格、风格和声音，出风格卡、分镜与关键帧后逐镜制作；Vibe知识大赏模式额外查证来源、记录真实素材许可、先渲 10 秒样片。触发词包括 $cs-code-video、用代码做视频、知识解说动画、Vibe知识大赏、来源可核查的代码科普片、KAI 教程片、像素动画、片头。固定暗夜星空系列用 cs-knowledge-film，固定像素解说系列用 cs-pixel-explainer；真实网页演示、电商视频和 ChatCut 策划各用对应 skill。

cs-code-video/SKILL.md

Read pinned source

Source commit e63cb26e58e2b307e3ff9a0ad834d3c1b1b65a90

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: No
Repository scan complete: No
Skill scan complete: No
Observed behavior: Not checked yet
Last checked: Nov 8, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 208
Repository last updated: Nov 7, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

testing Derived category
testing-browser Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

SKILL.mdcore · 15,091 bytes
SKILL.mdcore · 15,091 bytes
SKILL.mdcore · 15,091 bytes
SKILL.mdcore · 15,091 bytes
SKILL.mdcore · 15,091 bytes
agents/openai.yamlasset · 450 bytes
assets/crt.jsruns · 3,617 bytes
assets/kai-boy-3d.jsruns · 14,917 bytes
assets/kai-cat-3d.jsruns · 13,965 bytes
assets/kai-cat.jsruns · 12,350 bytes
assets/layers.jsruns · 9,897 bytes
assets/reference-wizard.htmlasset · 23,540 bytes
assets/template.htmlasset · 5,655 bytes
assets/voice/tts.pyruns · 1,817 bytes
assets/voice/配音.batruns · 176 bytes
references/brief-template.mddoc · 3,681 bytes
references/code-stack.mddoc · 4,159 bytes
references/craft-rules.mddoc · 6,257 bytes
references/director.mddoc · 8,594 bytes
references/hybrid.mddoc · 6,919 bytes
references/qa.mddoc · 2,274 bytes
references/signature.mddoc · 10,356 bytes
references/tutorial.mddoc · 5,286 bytes
references/vibe-knowledge.mddoc · 6,826 bytes
scripts/audio.pyruns · 9,685 bytes
scripts/gen_image.pyruns · 7,859 bytes
scripts/qa.pyruns · 4,165 bytes
scripts/render.mjsruns · 5,347 bytes
scripts/verify_video.pyruns · 2,502 bytes
style-log.mddoc · 1,323 bytes

Read excerpt


<!-- CS Skills · 陈硕 | portable skill entry | https://github.com/ChenShuo2004/cs-skills -->

# 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](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