Agent skill

Cs Knowledge Film

by ChenShuo2004 in ChenShuo2004/cs-skills

制作明确要求暗夜星空、衬线双语字幕与金色光点风格的知识解说片,或用户显式调用 $cs-knowledge-film:从概念与画面隐喻设计,到口播、场景 spec、配音和 1080p 渲染。普通科普视频不默认套用这一视觉模板;网页产品演示、ChatCut 策划和电商视频复刻各用对应 skill。

MITAuto-check passedMedia & Creative

Install Cs Knowledge Film

skills CLI
$ npx skills add ChenShuo2004/cs-skills --skill cs-knowledge-film -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ChenShuo2004/cs-skills cs-knowledge-film --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cs-knowledge-film .claude/skills/cs-knowledge-film && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cs-knowledge-film
GitHub stars
197
Token cost
~806 tokens
SKILL.md length
156 words
Files
14 (incl. scripts, references, assets)
Skills in repo
26
Repo updated
First seen
Licence
MIT

At a glance

制作明确要求暗夜星空、衬线双语字幕与金色光点风格的知识解说片,或用户显式调用 $cs-knowledge-film:从概念与画面隐喻设计,到口播、场景 spec、配音和 1080p 渲染。普通科普视频不默认套用这一视觉模板;网页产品演示、ChatCut 策划和电商视频复刻各用对应 skill。

  • Works in 5 steps: 先定三件事 → 写口播稿(见 references/script.md) → 拆场景写 spec.json(见 references/spec.md) → …
  • Media & Creative work in your project
  • SKILL.md covers 交付, 风格速查(细节见 references/style.md), 工作流 and 边界
  • Runs JavaScript and Python scripts from its folder; calls node and python

What it does

Cs Knowledge Film is an agent skill from ChenShuo2004/cs-skills. 制作明确要求暗夜星空、衬线双语字幕与金色光点风格的知识解说片,或用户显式调用 $cs-knowledge-film:从概念与画面隐喻设计,到口播、场景 spec、配音和 1080p 渲染。普通科普视频不默认套用这一视觉模板;网页产品演示、ChatCut 策划和电商视频复刻各用对应 skill。

Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/example-spec.json` and `assets/examples/ai-hallucination.json`).

It sits in Media & Creative. It works with Playwright. The repository describes itself as: 陈硕的 Codex Skills 与 AI 工作流手册:把产品、内容、调研与交付沉淀为可复用的智能工作流。 The licence is MIT.

When your agent uses it

  • Media & Creative work in your project

Example prompts

  • “/cs-knowledge-film”

Requirements

  • Python 3
  • Node.js

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. 先定三件事
  2. 写口播稿(见 references/script.md)
  3. 拆场景写 spec.json(见 references/spec.md)
  4. 配音 → 时间轴 → 预览 → 渲染
  5. 验收(见 references/qa.md)

What it can do on your machine

Read from SKILL.md and the folder at commit 6f5009d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 5 files in scripts/ (JavaScript and Python), which the agent can run.

    Shell commands in SKILL.md call:

    • node
    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cs Knowledge Film loads about 806 tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 41 tokens; SKILL.md has 156 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~806
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ChenShuo2004/cs-skills at commit 6f5009d, republished under its MIT licence (© ChenShuo2004). 156 words, ~806 tokens.

Download SKILL.mdSave it as .claude/skills/cs-knowledge-film/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.
name
cs-knowledge-film
description
制作明确要求暗夜星空、衬线双语字幕与金色光点风格的知识解说片,或用户显式调用 $cs-knowledge-film:从概念与画面隐喻设计,到口播、场景 spec、配音和 1080p 渲染。普通科普视频不默认套用这一视觉模板;网页产品演示、ChatCut 策划和电商视频复刻各用对应 skill。
<!-- CS Skills · 陈硕 | portable skill entry | https://github.com/ChenShuo2004/cs-skills -->

CS 暗夜知识片

把一个抽象概念讲成一部安静、克制、有电影感的知识短片。本 skill 的暗夜星空视觉是用户选择这一风格时使用的实现,不是所有知识视频的默认视觉。先找到选题的核心问题与可见的动作,再决定使用现有场景、扩展场景,或为该题材另做画面。

交付

  • 一个项目目录:spec.json(唯一需要手写的文件)、audio/、timeline.json、subtitles.srt、preview.jpg、video.mp4。
  • 视频默认 1920×1080、30fps、H.264 + AAC;可选中文配音(edge-tts)+ score.py 生成的配乐与音效(参照原片:A 小调低音长音、温暖和弦铺底、玻璃钟琴、与画面事件逐一对齐的打字/转轮/呼啸/撞击声,-16 LUFS);画面内置中英双语字幕,同时导出 subtitles.srt。
  • 不上传、不发布。BGM 只用用户提供的文件(spec.bgm)。

风格速查(细节见 references/style.md)

  • 底色近黑带一点藏蓝,慢速闪烁的星空,暗角 + 轻微颗粒。
  • 字体:中文宋体/衬线(Noto Serif SC),英文 Lora 斜体;不用黑体。
  • 颜色只有三种语义:金=重点/惊奇/答案,冰蓝=结构/线条/已知,绯红=噪声/错误/被排除。
  • 左上角章节标签 01 猜 THE GUESS;底部中文字幕 + 英文斜体小字。
  • 动效慢:淡入 0.6–1s、缓出曲线;光点有辉光和呼吸感;不要弹跳、不要转场特效。

工作流

1. 先定三件事

缺了才问,能自己判断就不问:

  1. 主题与一句话结论(这支片子最后让观众记住哪一句)
  2. 时长(默认 2–3 分钟;每分钟约 220–250 字口播)
  3. 是否需要英文字幕(默认要,和参考片一致)
2. 写口播稿(见 references/script.md)

先提炼一句话结论、主要误解和适合这个题目的画面隐喻,再设计钩子与章节。可参考“体验式钩子 → 标题 → 3–5 章 → 回到开头收束”,但故事结构由内容决定,不必重复参考片的章节或结尾。

每句 8–25 字,一句一个意思,适合被逐句打在字幕上。数字和史实要核对,不编造。

3. 拆场景写 spec.json(见 references/spec.md)

把 assets/example-spec.json 当作格式示例,不复制其中的场景顺序或视觉隐喻。先列出每章要让观众看见的变化,再选现有场景类型;现有类型表达不了时,按 references/spec.md 的扩展说明新增场景。

概念形态场景类型
预期 / 猜下一个字 / 填空typewriter
候选词概率、采样、温度probs
片名title
二分、度量、量化numberline
罕见事件、时间、希望、灯火landscape(烽火、时间条、弧线、灯)
日常 vs 罕见新闻city(夜景、下雪、头条)
公式、定义formula
语言、冗余、噪声、压缩textplay
传输、编码、信道signal / probe
同样数据不同意义compare
信息茧房、同质化cards
名人原话quote
真实图片(星图、照片)image
停顿、提问orb / blank

事件时间用 "L2"(本场第 2 句开始)、"L2e"(第 2 句结束)、"L2+0.5" 锚定到口播,配音变长变短都不会错位。

4. 配音 → 时间轴 → 预览 → 渲染

把 scripts/ 下 4 个文件放在任意位置,项目目录里只放 spec.json:

bash
python scripts/tts.py  <项目目录>          # 逐句配音 audio/line_XXX.mp3(需联网,免费)
node   scripts/timeline.mjs <项目目录>     # 按真实音频长度排时间轴,拼 narration.wav + subtitles.srt
python scripts/score.py <项目目录>         # 按场景和事件生成配乐 + 音效 score.wav(改了 spec 就重跑)
node   scripts/render.mjs <项目目录> --preview   # 每场 2 帧拼成 preview.jpg —— 必须先看
node   scripts/render.mjs <项目目录> --still 42  # 单帧排查
node   scripts/render.mjs <项目目录>              # 全量渲染 video.mp4
node   scripts/render.mjs <项目目录> --remux      # 只换声音:复用已渲染画面重新混音

依赖:Node 18+、playwright(含 Chromium)、ffmpeg、Python 3;配音需安装 edge-tts,程序配乐需安装 numpy scipy。已有 Chrome 的环境可用 CHROME_EXECUTABLE 指向其可执行文件,PLAYWRIGHT_MODULE 可指向现有的 Playwright 模块目录。在目标环境中显式安装依赖,脚本不会自动修改 Python 环境。没有配音时 timeline 按字数估算,可以先出无声版确认画面;修改文案或音色后重跑 tts.py,它会只更新变化的句子。

5. 验收(见 references/qa.md)

必须实际看 preview.jpg,再抽查关键事件帧(数字揭晓、灯亮、遮罩出现)。常见问题:字幕压住画面元素、事件早于对应口播、文字超出画面、辉光过曝成灰屏。

边界

  • 本 skill 负责“讲清一个知识点”的解说片;真人口播、直播切片、产品演示不在范围。
  • 不把别人的原片文案照搬进新片;参考的是结构和视觉语言,文案自己写。
  • 图片素材只用用户提供或可合法使用的(公共领域 / CC),在 spec 里记录来源。

© ChenShuo2004, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 13 other files (scripts, references, assets) in cs-knowledge-film of ChenShuo2004/cs-skills.

  • SKILL.md
  • agents/openai.yaml
  • assets/example-spec.json
  • assets/examples/ai-hallucination.json
  • assets/examples/ai-next-word.json
  • references/qa.md
  • references/script.md
  • references/spec.md
  • references/style.md
  • scripts/engine.html
  • scripts/render.mjs
  • scripts/score.py
  • scripts/timeline.mjs
  • scripts/tts.py

Open the folder on GitHubat commit 6f5009d

Compare with similar skills

Cs Knowledge Film next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cs Knowledge Film compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cs Knowledge Film this skillChenShuo2004/cs-skills197—~806Automated safety check: PassMIT
Video Wrapperop7418/Video-Wrapper-Skills339—~1.2kAutomated safety check: NotesNone
Storyreceptron/mulmocast-cli475—~3.5kAutomated safety check: NotesNone
Render Value Propgooseworks-ai/goose-skills1.2k—~1.1kAutomated safety check: PassMIT
Guizang Social Cardsop7418/guizang-social-card-skill7.4k1 repos~7.8kAutomated safety check: PassAGPL-3.0
PosterlyChenruishuo/posterly416—~4.6kAutomated safety check: NotesAGPL-3.0

Similar skills

  • Video Wrapper

    op7418/Video-Wrapper-Skills

    为访谈视频添加综艺特效(花字、卡片、人物条、章节标题等)。支持 4 种视觉主题,先分析字幕内容生成建议供用户审批,再渲染视频。

    339 GitHub stars~1.2k tokensUpdated 8 mo ago
    Media & CreativeAuto-check: notes
  • Story

    receptron/mulmocast-cli

    Create high-quality MulmoScript through structured multi-phase creative process

    475 GitHub stars~3.5k tokensUpdated yesterday
    Media & CreativeAuto-check: notes
  • Render Value Prop

    gooseworks-ai/goose-skills

    Render a designed 'value prop' video from a config — 3-5 noun-phrase benefit claims (<=4 words each) revealed sequentially over per-SKU product visuals, one crisp editorial frame per claim (hook…

    1.2k GitHub stars~1.1k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Guizang Social Cards

    op7418/guizang-social-card-skill

    Produces social card sets for Xiaohongshu and WeChat: carousels, Live Photo motion cards and puzzle layouts, and WeChat cover pairs, rendered from single-file HTML.

    7.4k GitHub starsUsed in 1 repo~7.8k tokens
    Media & CreativeAuto-check passed
  • Posterly

    Chenruishuo/posterly

    Create or revise academic conference posters in HTML/CSS and export print-ready PDFs.

    416 GitHub stars~4.6k tokensUpdated 5 days ago
    Media & CreativeAuto-check: notes
  • Explain Video

    limin112/min-skill

    Build a narrated explainer video from a concept — discussion → structure → HTML slide deck → narration script → TTS voice → subtitles → background music → Playwright screen recording → ffmpeg…

    454 GitHub stars~2.4k tokensUpdated yesterday
    Media & CreativeAuto-check passed

More from ChenShuo2004/cs-skills

All 26 skills in this repo
  • Cs Checkpoint Version

    ChenShuo2004/cs-skills

    A skill your agent uses when the user asks to save the current repository version, create a rollback point, checkpoint dirty worktree changes, preserve staged/unstaged/untracked files before risky…

    197 GitHub stars~1.1k tokensUpdated 3 days ago
    Auto-check passed
  • Cs Code Video

    ChenShuo2004/cs-skills

    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…

    197 GitHub stars~2.1k tokensUpdated 3 days ago
    Auto-check passed
  • Cs Auto Videl

    ChenShuo2004/cs-skills

    A skill your agent uses when the user types $cs-auto-videl or asks for Douyin/TikTok ecommerce video workflows, including competitor replication, strong-Hook nine-grid promptimage.md to image2…

    197 GitHub stars~2.1k tokensUpdated 3 days ago
    Auto-check passed
  • 当用户要把产品事实、口播、数字人、产品界面和 CTA 制作成可验收的数字人产品介绍视频时使用:统一预检 ChatCut、FFmpeg、ComfyUI、Fish/TTS 与 Remotion,按 plan、sample、batch 三种模式编排,先完成可审批样片再批量或出成片。用于有明确产品包的横版/竖版产品视频流水线;不要用于通用自动剪辑、电商短视频复刻、纯视频选题策划或未经确认的批量生成与发布。

    197 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed
  • Cs Code Story Video

    ChenShuo2004/cs-skills

    把中文口播、角色和参考素材制作成可验收的 16:9 代码叙事视频:A-roll 角色讲述、全屏场景 B-roll、真实音频时码、Remotion 样片与成片、3:4/4:3 杂志风封面。仅用于代码驱动的叙事视频,不替代 ChatCut 剪辑、数字人产品片或电商复刻。

    197 GitHub stars~541 tokensUpdated 3 days ago
    Auto-check passed
  • Cs Codex Image

    ChenShuo2004/cs-skills

    通过 Codex 内置生图生成或编辑图片,并将该能力接入 Claude Code、Claude 桌面版或其他本地 MCP Agent。用于 cs-codex-image、内置生图、不用 API Key 出图、Claude 调用 Codex 生图。固定 KAI 封面和小黄角色仍由对应品牌 Skill 决定视觉规范。

    197 GitHub stars~415 tokensUpdated 3 days ago
    Auto-check passed

Works with

Questions about Cs Knowledge Film

What does Cs Knowledge Film do?

制作明确要求暗夜星空、衬线双语字幕与金色光点风格的知识解说片,或用户显式调用 $cs-knowledge-film:从概念与画面隐喻设计,到口播、场景 spec、配音和 1080p 渲染。普通科普视频不默认套用这一视觉模板;网页产品演示、ChatCut 策划和电商视频复刻各用对应 skill。. Cs Knowledge Film is an agent skill from ChenShuo2004/cs-skills.

When should I use Cs Knowledge Film?

Cs Knowledge Film fits situations like: media & Creative work in your project.

How do I install Cs Knowledge Film in Claude Code?

Run `npx skills add ChenShuo2004/cs-skills --skill cs-knowledge-film -a claude-code`. Or copy the skill folder (cs-knowledge-film in ChenShuo2004/cs-skills) into .claude/skills/cs-knowledge-film in your project. Claude Code loads it when a task matches its description.

How do I install Cs Knowledge Film in Codex?

Run `npx skills add ChenShuo2004/cs-skills --skill cs-knowledge-film -a codex`. Or copy the skill folder (cs-knowledge-film in ChenShuo2004/cs-skills) into .agents/skills/cs-knowledge-film in your project. Codex loads it when a task matches its description.

Can I use Cs Knowledge Film in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ChenShuo2004/cs-skills --skill cs-knowledge-film -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cs-knowledge-film, .gemini/skills/cs-knowledge-film, .github/skills/cs-knowledge-film and .opencode/skills/cs-knowledge-film in your project.

What does Cs Knowledge Film need to run?

Going by SKILL.md and its folder, Cs Knowledge Film needs JavaScript and Python for the scripts in its folder and the command-line tools its instructions call (node and python). Our summary lists: Python 3; Node.js.

Does Cs Knowledge Film access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cs Knowledge Film safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Cs Knowledge Film use?

Cs Knowledge Film is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cs Knowledge Film use?

About 806 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.2k tokens, read only when the agent opens those files.

What are the alternatives to Cs Knowledge Film?

Skills that share tags, products or a category with Cs Knowledge Film: Video Wrapper (op7418/Video-Wrapper-Skills, 339 stars), Story (receptron/mulmocast-cli, 475 stars), Render Value Prop (gooseworks-ai/goose-skills, 1.2k stars) and Guizang Social Cards (op7418/guizang-social-card-skill, 7.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cs Knowledge Film?

ChenShuo2004 (a GitHub user) maintains it in ChenShuo2004/cs-skills, which has 197 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 8, 2026.

Source: ChenShuo2004/cs-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.