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-story-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-story-video)<a href="https://agentmods.dev/skills/chenshuo2004/cs-skills/cs-code-story-video"><img src="https://agentmods.dev/badge/skills/chenshuo2004/cs-skills/cs-code-story-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-story-video"><img src="https://agentmods.dev/badge/skills/chenshuo2004/cs-skills/cs-code-story-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 | $0.00103 | $0.01353 |
| Opus 5.5 | $0.00041 | $0.00541 |
| Sonnet 5.5 | $0.00021 | $0.00271 |
| Haiku 4.5 | $0.00010 | $0.00135 |
Grade A, and why
cs-code-story-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.
What it actually says
CS 代码叙事视频
把一条故事做成可重复渲染的画面。角色在 A-roll 讲述；B-roll 用独立的全屏场景演出事件，而不是把信息面板放大或换字。默认 KAI 像素角色、1920×1080、30fps、无 BGM、无烧录口播字幕。角色、配色和场景可随项目替换；不能把《人生意义》的七章、台词和镜头当成通用模板。
何时使用
- 用户要把自己的主题、口播或录音做成代码渲染的叙事短片，并希望交付视频、字幕时间文件和封面。
- 只要写真实项目的个人 IP 口播，优先
$cs-personal-ip-script；只要最终音频的短语时码，使用$cs-narration-phrase-timeline；要 ChatCut 策划或产品数字人视频，使用各自专用 Skill。当前 Skill 在完整制作过程中按实际需要使用这些能力，不强迫所有项目经过它们。
输入与工作目录
从用户给出的主题、稿件、原声、人物和参考资料中提取信息；不把参考画面、录音或未经核实的数据复制到新片中。已有工程就继续原工程；新工程默认建在当前工作区 video/<项目名>/。原素材保持只读，复制工作副本并记录 SHA-256。Skill 仓库只存可复用的代码、KAI 默认像素角色与测试，不收录用户项目的原声、稿件或导出视频。
先读 项目与镜头合同。可用 scripts/scaffold.mjs 从 assets/starter/ 建工程；只在新目录运行它，不覆盖已有工程。
从内容到成片
- 内容与证据。 明确受众、核心问题、故事推进与可展示的事件。参考素材只分析节奏、动效和构图。用户只有主题时，完成可朗读口播、章节逻辑和场景方案，然后等待其最终录音；不编造时码或替用户生成声音。真实项目经历适用时可调用
$cs-personal-ip-script。 - 锁定音频。 拿到最终音频后，用 FFprobe 测时长、SHA-256 锁来源。需要短语级字幕时，必须有与录音一致的逐字稿，再调用
$cs-narration-phrase-timeline。只有自动转写稿时先标为待校对；不得把 ASR 猜测、按字数估时或超出音频长度的时间戳当成准确对齐。有效时间表可用scripts/phrases-to-srt.mjs转为后期 SRT。 - 编排镜头。 以帧为整数写
story.json：章节卡约 21 帧，章首必须有主题 B-roll，章内关键句按内容切换 A-roll 与 B-roll。A-roll 可左、右或中站位；B-roll 必须是独立全屏场景。人物轻微呼吸或眨眼，组件分段进退场；每个场景物件承担具体叙事任务。给后期字幕留清晰区域，文字只保留必要的章节词与物件关键词。 - 代码制作。 用 starter 的时间轴、场景注册、角色层、像素动效原语和封面组件作为工程起点。每条片子的事件场景在
src/scenes.tsx中重新设计；色彩或风格可更换，不通过重命名旧场景假装创作。用scripts/validate-story.mjs检查素材、哈希、章节、镜头和音频实际时长，再渲染。 - 样片与完整版。 先导出覆盖开头两章的样片，查看章节卡、A/B-roll 差异、角色身份、文字和组件进退场。修正明显问题后继续完整渲染；只有用户明确设了审批点才暂停。样片与全片使用同一音频和镜头数据，不能为凑时长拉伸原声。
- 封面与验收。 同一视频制作 1200×1600 和 1600×1200 两张旧纸、黑白主体、红色大字的杂志风封面；文字由代码排版，标题与主体在缩略图下仍需可读。按 成片验收 检查视频、音频、镜头、封面和尾句。没有实际人耳听审时明确记录，不能写成已听审。
交付
在项目目录保留 story.json、原稿及来源记录、镜头表、有效的 phrase-timeline.json/SRT（若满足真实对齐条件）、开头样片、完整版 MP4、两张封面和 QA 报告。若因缺最终录音或准确朗读稿而不能进入后续阶段，交付已完成的脚本与场景方案，准确说明待补输入。
默认不发布、不上传素材、不推送仓库。用户指定新的画幅、封面风格、字幕或音乐时，以该项目要求为准，并在验收中检查这些新条件。
What ships with it
17 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 376 B
- assets/starter/package.json 1.0 KB
- assets/starter/public/kai-pixel.png 394 KB
- assets/starter/src/covers.tsx 5.8 KB
- assets/starter/src/index.ts 89 B runs code
- assets/starter/src/model.ts 1.1 KB runs code
- assets/starter/src/root.tsx 895 B
- assets/starter/src/scenes.tsx 2.2 KB
- assets/starter/src/video.tsx 3.6 KB
- assets/starter/story.json 567 B
- assets/starter/tsconfig.json 310 B
- references/qa.md 1.4 KB
- references/story-contract.md 3.0 KB
- scripts/phrases-to-srt.mjs 3.5 KB runs code
- scripts/scaffold.mjs 2.0 KB runs code
- scripts/validate-story.mjs 6.9 KB runs code
- tests/pipeline.test.mjs 5.7 KB runs code
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 First seen · 35 lines · 103 tokens per session scan A e220bfc34948
cs-code-story-video is a skill published in the GitHub repository ChenShuo2004/cs-skills (204 stars, last pushed 18d ago), licensed MIT. It adds 103 tokens to every session and 1,353 once invoked, about $0.0004 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 2026-10-07.
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.