Render Chatgpt Chat
gooseworks-ai/goose-skills
Assemble a ChatGPT chat-reveal video ad from a thread + timeline JSON — one continuous Playwright recording of a ChatGPT mobile chat (user types with the iOS keyboard up → taps send → keyboard…
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…
$ npx skills add ChenShuo2004/cs-skills --skill cs-code-video -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ChenShuo2004/cs-skills cs-code-video --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cs-code-video .claude/skills/cs-code-video && rm -rf skills-srcUse ~/.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/
Install the "cs-code-video" agent skill from https://github.com/ChenShuo2004/cs-skills/tree/main/cs-code-video into .claude/skills/cs-code-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cs-code-video", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ChenShuo2004/cs-skills/tree/main/cs-code-videoType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ChenShuo2004/cs-skills --skill cs-code-video -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ChenShuo2004/cs-skills cs-code-video --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cs-code-video .agents/skills/cs-code-video && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cs-code-video" agent skill from https://github.com/ChenShuo2004/cs-skills/tree/main/cs-code-video into .agents/skills/cs-code-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cs-code-video", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ChenShuo2004/cs-skills --skill cs-code-video -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ChenShuo2004/cs-skills cs-code-video --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cs-code-video .cursor/skills/cs-code-video && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cs-code-video" agent skill from https://github.com/ChenShuo2004/cs-skills/tree/main/cs-code-video into .cursor/skills/cs-code-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cs-code-video", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ChenShuo2004/cs-skills.git --path cs-code-video--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ChenShuo2004/cs-skills --skill cs-code-video -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ChenShuo2004/cs-skills cs-code-video --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cs-code-video .gemini/skills/cs-code-video && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cs-code-video" agent skill from https://github.com/ChenShuo2004/cs-skills/tree/main/cs-code-video into .gemini/skills/cs-code-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cs-code-video", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ChenShuo2004/cs-skills cs-code-videoInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ChenShuo2004/cs-skills --skill cs-code-video -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/cs-code-video .github/skills/cs-code-video && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cs-code-video" agent skill from https://github.com/ChenShuo2004/cs-skills/tree/main/cs-code-video into .github/skills/cs-code-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cs-code-video", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ChenShuo2004/cs-skills --skill cs-code-video -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ChenShuo2004/cs-skills cs-code-video --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ChenShuo2004/cs-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cs-code-video .opencode/skills/cs-code-video && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cs-code-video" agent skill from https://github.com/ChenShuo2004/cs-skills/tree/main/cs-code-video into .opencode/skills/cs-code-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cs-code-video", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
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 is an agent skill from 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 $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。
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 30 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/crt.js` and `assets/kai-boy-3d.js`).
It sits in Media & Creative, covering Video production and Browser testing. It works with FFmpeg and 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.
9 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 6f5009d. It shows what the files ask for, not the result of running them.
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.
Ships 1 file in scripts/ (JavaScript, Python and Batch, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3nodepipffmpegpythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
OPENAI_API_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Cs Code Video loads about 2.1k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 80 tokens; SKILL.md has 447 words of instructions outside code blocks.
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.
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.
The full file from ChenShuo2004/cs-skills at commit 6f5009d, republished under its MIT licence (© ChenShuo2004). 447 words, ~2,074 tokens.
.claude/skills/cs-code-video/SKILL.md (or your agent's skills folder). This skill also uses 26 other files; get the full folder from GitHub.<!-- CS Skills · 陈硕 | portable skill entry | https://github.com/ChenShuo2004/cs-skills -->
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。
gen_image.py --dry-run 把张数和模型给用户看,确认后再出。signature.md 的吸收清单。$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。<direction>)按阶段读最少的资料:
把 scripts/ 和 assets/ 拷到工程目录。assets/template.html 只提供骨架(render(t)、弹簧、时间表、字幕函数),顶部的 STYLE 和全部镜头都按风格卡重写,不要沿用模板自带的配色和示例镜头。
node scripts/render.mjs index.html out/final.mp4 --size 1920x1080 --fps 30 [--duration 30] [--start 0] [--audio audio/mix.wav] [--subframes 4] [--workers 2] [--draft]
node scripts/render.mjs index.html qa/s1.png --still 2.0 # 单帧
python3 scripts/audio.py sfx cues.json audio/sfx.wav # [{"t":1.2,"type":"click|pop|whoosh|thud|ding|riser|glitch|type","gain":1}]
python3 scripts/audio.py music audio/music.wav --bpm 120 --bars 16
python3 scripts/audio.py beats music.mp3 > source/beats.json # bpm / beats / downbeats / hits
python3 scripts/audio.py vo spec.json # 逐句配音 → audio/vo.wav + timeline.js
python3 scripts/audio.py mix audio/mix0.wav audio/vo.wav audio/music.wav:0.25 audio/sfx.wav:0.8 --len 30 # --len = 成片时长
python3 scripts/audio.py normalize audio/mix0.wav audio/mix.wav # -14 LUFS ±0.5,真峰值 ≤ -1 dBTP
python3 scripts/qa.py out/final.mp4 qa # 抽帧、手机抽帧、切镜连续帧、波形、打分表
python3 scripts/gen_image.py assets.json --dry-run | --draft | --final | --pick id=2 | --export-md # GPT 出图(在有 OPENAI_API_KEY 的电脑上跑)assets/template.html:render(t) 骨架,自带缓动、闭式弹簧 spring/springTo、带种子随机、版式缩放 S、STYLE 风格变量、可关闭的打字机字幕;有 timeline.js 时按配音时长自动排镜头。assets/layers.js:把 GPT 图变成动画:illustration(运镜)、parallax(分层视差)、grid / card / promptBox / bigStep(讲解界面)、avatar(头像对口型)、subtitle(box / plain 两种字幕)。用法见 hybrid.md 第三节。assets/kai-boy-3d.js:主角 KAI 男孩 3D 版,KaiBoy3D(w,h).render({t, yaw, mode, pose, expr, bg})。每支片的主角,和 KAI 猫同框时都用透明底叠加。assets/kai-cat-3d.js:宠物 KAI 猫 3D 版(WebGL2 光线步进,零依赖),KaiCat3D(w,h).render({t, yaw, mode, pose, expr, bg}),白模 / 上色两种模式,透明底可叠进任何画面。assets/kai-cat.js:KAI 猫代码版角色组件,drawKaiCat(g, {x, y, size, t, pose, expr, style}),4 种姿势、5 种表情、4 种画风。每支片都要出场,规则见 signature.md 第五节。assets/crt.js:WebGL2 老电视后期层,template.html 里 USE_CRT = true 即开。只在风格卡选了复古质感时用。assets/voice/:tts.py + 配音.bat(Windows 双击即可),读同目录 spec.json 逐句生成 audio/line_XXX.mp3。assets/reference-wizard.html(调色板索引缓冲、整数倍放大、10 张/秒姿势量化、固定步长重放的 render(t)),像素复古风格从它起步。依赖:node + playwright、ffmpeg、python3 + numpy、中文字体(Noto Sans CJK 等);出图另需 pip install openai pillow 和 OPENAI_API_KEY。
接受三种原材料,可以混着给:想法、原内容(文章、口播稿、产品网址、代码库)、参考视频。先用一条消息问清下面 5 项,用户没给的不要自己编;原材料里已经能确定的项直接写出来请用户确认,不重复问:
audio.py beats 测节拍;给了参考视频:抽帧拼图 ffmpeg -i ref.mp4 -vf "fps=1,scale=320:-1,tile=6x5" -frames:v 1 source/ref-sheet.png,或直接 qa.py ref.mp4 source/ref 拿抽帧和切镜点。写下它的手法(镜头结构、节奏、转场、隐喻方式),不是外观。值得长期用的手法补进 signature.md 吸收清单。按 references/director.md 走:核心冲突 → A 稳妥 / B 跨界 / C 疯狂三个隐喻 → 各配一种风格 → 套 KAI 签名层 → 三张风格卡。
style-log.md 里最近 3 支用同一种风格(用户指定风格时除外)。选定风格卡后先写分镜表,不写代码。每个镜头一块,格式固定:
镜头 [N]|[开始–结束秒]
画面:构图、元素、文字(文字 ≤ 一句,停留 ≥ 2.5 秒)
动作:进场、主要动作、出场(缓动或弹簧,写明哪一档)
镜头:推 / 拉 / 跟随 / 固定
声音:这一段的音乐和音效(音效写到具体动作)
转场:怎么从画面内容里长到下一个镜头分镜表确认后,预览页从 template.html 骨架起步,按风格卡重写 STYLE,只做 3 个最能代表全片的瞬间(通常:开场第一眼、签名动作那一刻、收尾定版):
render.mjs previews/plan.html previews/k1.png --still <t> × 3,拼成一张给用户看风格。--duration 3 --draft。按 references/brief-template.md 把 7 块全部填实(<structure> 直接放确认过的分镜表)。之后的制作严格按它来;用户只要提示词时,交 brief.md 即结束。
按 references/hybrid.md:从 brief 的分镜表整理 assets.json(每镜要哪张图、参考哪个角色)→ --dry-run 给用户确认张数 → --draft 每张 2 个候选 → 用户挑图(--pick)或 --final 出定稿。没有 Key 就 --export-md 导出提示词,用户在 ChatGPT 手动出图后放进 images/。图片到齐再进入下一步。
KAILayers.load({...}),字体和资源加载完再设 window.ready = true,之后才截图。spec.json(scenes[{id, lines}],id 对应 template 里 SHOTS 的 id),在能访问语音服务的电脑上跑 assets/voice/配音.bat 或 python tts.py,拿回 audio/ 后 audio.py vo spec.json 整段合成,画面对旁白,不要一句一句拼。cues.json 的时间点直接从镜头关键帧抄。--draft --size 960x540 看节奏,对了再精修。mix --len <成片秒数> → normalize(先裁到成片时长再调响度,否则裁掉安静尾巴后会偏响)。audio.py check 把波形画成图自己看,确认没有削顶爆音、意外静音、低频一直轰。render.mjs … --audio audio/mix.wav。qa.py out/final.mp4 qa,按 references/qa.md 8 项打分,列最严重的 3 个问题和时间点,只重渲出问题的那几秒,重复到每项 ≥8。报告:成片路径、brief.md、qa/review_log.md、关键创作决定、已知不足、渲染用时、需要用户核对的事实。
收尾三件事:在 style-log.md 最上面追加一行;效果好的风格卡存成模板;踩到的新坑补进 craft-rules.md。
qa.py 打分表每项 ≥8,验收清单全部勾上。style-log.md 已追加。© ChenShuo2004, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 26 other files (scripts, references, assets) in cs-code-video of ChenShuo2004/cs-skills.
Open the folder on GitHubat commit 6f5009d
Cs Code Video 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cs Code Video this skillChenShuo2004/cs-skills | 193 | — | ~2.1k | Automated safety check: Pass | MIT | |
| Render Chatgpt Chatgooseworks-ai/goose-skills | 1.2k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Character Animation QAcalesthio/OpenMontage | 65k | — | ~389 | Automated safety check: Pass | MIT | |
| Browser Video Recordingnirholas/three.ws | 227 | 1 repos | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Render Apple Notes Chatgooseworks-ai/goose-skills | 1.2k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Demo Videoalinaqi/maggy | 707 | — | ~1.4k | Automated safety check: Pass | MIT |
gooseworks-ai/goose-skills
Assemble a ChatGPT chat-reveal video ad from a thread + timeline JSON — one continuous Playwright recording of a ChatGPT mobile chat (user types with the iOS keyboard up → taps send → keyboard…
calesthio/OpenMontage
Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.
nirholas/three.ws
Create polished 60 fps 4:3 4K browser screen-recording style videos from Codex in-app browser captures, with browser-only crop, natural macOS cursor styling, deliberate click choreography…
gooseworks-ai/goose-skills
Assemble an Apple Notes list video ad from a note + end-card JSON — a frame-accurate fake iPhone screen recording of a short list being typed into Apple Notes (character by character, key pops…
alinaqi/maggy
Record captioned product walkthrough videos of any web app with Playwright + ffmpeg — proof videos for stakeholders, feature demos, bug-fix evidence
gooseworks-ai/goose-skills
Assemble a silent, music-led 3-world product-tour ad — trim and hard-cut-concat the per-world WIDE-arrival + top-down-macro clips, composite the HTML/Playwright brand end card (approved headline +…
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…
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。
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…
ChenShuo2004/cs-skills
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。
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。
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。
Works with
Categories
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 is an agent skill from ChenShuo2004/cs-skills.
Cs Code Video fits situations like: tasks that involve Video production; tasks that involve Browser testing.
Run `npx skills add ChenShuo2004/cs-skills --skill cs-code-video -a claude-code`. Or copy the skill folder (cs-code-video in ChenShuo2004/cs-skills) into .claude/skills/cs-code-video in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ChenShuo2004/cs-skills --skill cs-code-video -a codex`. Or copy the skill folder (cs-code-video in ChenShuo2004/cs-skills) into .agents/skills/cs-code-video in your project. Codex loads it when a task matches its description.
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-code-video -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-code-video, .gemini/skills/cs-code-video, .github/skills/cs-code-video and .opencode/skills/cs-code-video in your project.
Going by SKILL.md and its folder, Cs Code Video needs JavaScript, Python and Windows cmd for the scripts in its folder, the command-line tools its instructions call (python3, node, pip, ffmpeg and python) and credentials named OPENAI_API_KEY. Our summary lists: Python 3; Node.js; A credential in OPENAI_API_KEY.
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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.
Cs Code Video is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.3k 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 14k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Cs Code Video: Render Chatgpt Chat (gooseworks-ai/goose-skills, 1.2k stars), Character Animation QA (calesthio/OpenMontage, 65k stars), Browser Video Recording (nirholas/three.ws, 227 stars) and Render Apple Notes Chat (gooseworks-ai/goose-skills, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ChenShuo2004 (a GitHub user) maintains it in ChenShuo2004/cs-skills, which has 193 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.