Video Translation
NoizAI/skills
Translate and dub videos from one language to another, replacing the original audio with TTS while keeping the video intact.
A skill your agent uses when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a physics problem (物理题: mechanics/力学 受力分析 牛顿定律 斜面 传送带 板块 平抛 圆周 能量 动量, optics/光学 折射…
Install Edu Physics Video
$ npx skills add wy51ai/edulab --skill edu-physics-video -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install wy51ai/edulab edu-physics-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/wy51ai/edulab.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/edu-physics-video .claude/skills/edu-physics-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 "edu-physics-video" agent skill from https://github.com/wy51ai/edulab/tree/master/skills/edu-physics-video into .claude/skills/edu-physics-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "edu-physics-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/wy51ai/edulab/tree/master/skills/edu-physics-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 wy51ai/edulab --skill edu-physics-video -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install wy51ai/edulab edu-physics-video --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/wy51ai/edulab.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/edu-physics-video .agents/skills/edu-physics-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 "edu-physics-video" agent skill from https://github.com/wy51ai/edulab/tree/master/skills/edu-physics-video into .agents/skills/edu-physics-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "edu-physics-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 wy51ai/edulab --skill edu-physics-video -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install wy51ai/edulab edu-physics-video --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/wy51ai/edulab.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/edu-physics-video .cursor/skills/edu-physics-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 "edu-physics-video" agent skill from https://github.com/wy51ai/edulab/tree/master/skills/edu-physics-video into .cursor/skills/edu-physics-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "edu-physics-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/wy51ai/edulab.git --path skills/edu-physics-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 wy51ai/edulab --skill edu-physics-video -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install wy51ai/edulab edu-physics-video --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/wy51ai/edulab.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/edu-physics-video .gemini/skills/edu-physics-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 "edu-physics-video" agent skill from https://github.com/wy51ai/edulab/tree/master/skills/edu-physics-video into .gemini/skills/edu-physics-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "edu-physics-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 wy51ai/edulab edu-physics-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 wy51ai/edulab --skill edu-physics-video -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/wy51ai/edulab.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/edu-physics-video .github/skills/edu-physics-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 "edu-physics-video" agent skill from https://github.com/wy51ai/edulab/tree/master/skills/edu-physics-video into .github/skills/edu-physics-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "edu-physics-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 wy51ai/edulab --skill edu-physics-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 wy51ai/edulab edu-physics-video --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/wy51ai/edulab.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/edu-physics-video .opencode/skills/edu-physics-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 "edu-physics-video" agent skill from https://github.com/wy51ai/edulab/tree/master/skills/edu-physics-video into .opencode/skills/edu-physics-video/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "edu-physics-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.
Facts
- Skill name
edu-physics-video- GitHub stars
- 1.4k
- Token cost
- ~2.3k tokens
- SKILL.md length
- 552 words
- Files
- 36 (incl. scripts)
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a physics problem (物理题: mechanics/力学 受力分析 牛顿定律 斜面 传送带 板块 平抛 圆周 能量 动量, optics/光学 折射…
- Works in 11 steps: 严格按下面 11 步顺序做，每步的"通过标准"满足了才能进入下一步。 → 先按物理方法解对题。 第 1… → 先讲清楚题目。 第一幕展示原题图片，旁白逐条读条件，每读一条就在图上框出那一条。 → …
- Asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a physics problem (物理题: mechanics/力学 受力分析 牛顿定律 斜面 传送带 板块 平抛 圆周 能量 动量
- SKILL.md covers 必须遵守的规则, 11 个步骤, 常见错误 and 参考文件
- Runs Python, JavaScript and Shell scripts from its folder; calls node, bash and npm; needs GLM_API_KEY
What it does
Edu Physics Video is an agent skill from wy51ai/edulab. Use when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a physics problem (物理题: mechanics/力学 受力分析 牛顿定律 斜面 传送带 板块 平抛 圆周 能量 动量, optics/光学 折射, electromagnetism/电磁 带电粒子), from a problem screenshot or text, with Chinese voice-over (GLM-TTS / 智谱 TTS), bilingual zh+en subtitles and blueprint-style canvas animation where the motion follows the real solution, rendered to MP4.
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 39 other files, including scripts (for example `examples/laser-curvature/anim.js`, `examples/laser-curvature/episode.json` and `examples/laser-curvature/script.json`).
It sits in Media & Creative, covering Text to speech and voice, Transcription and Translation. The licence is Apache-2.0.
When your agent uses it
- Asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a physics problem (物理题: mechanics/力学 受力分析 牛顿定律 斜面 传送带 板块 平抛 圆周 能量 动量
- Electromagnetism/电磁 带电粒子)
- From a problem screenshot
- With Chinese voice-over (GLM-TTS / 智谱 TTS)
Example prompts
- “/edu-physics-video”
Requirements
- Python 3
- Node.js
- A Bash shell
- A credential in GLM_API_KEY
Workflow steps
11 steps, taken from the first numbered list in SKILL.md.
- 严格按下面 11 步顺序做，每步的"通过标准"满足了才能进入下一步。
- 先按物理方法解对题。 第 1 步必须写出解题卡（研究对象、过程分段、每段受力、所用规律、答案、验算），见 reference/physics-solving.md。多段过程、符号答案用 sympy 验算。
- 先讲清楚题目。 第一幕展示原题图片，旁白逐条读条件，每读一条就在图上框出那一条。
- tts 字段只能是能念出来的中文。 不能有阿拉伯数字、= + − × ÷ / ^ √ ° ( ) 等符号，单位要读出来：v₀ = 10 m/s 写成 v零等于十米每秒，2 m/s² 写成 二米每二次方秒；sin/cos 写成 正弦/余弦；希腊字母按…
- 读音必须固定。 调 TTS 之前 --check 必须显示 未固定读音的生僻字/多音字: 0 且 script errors: 0。多音字的标注写在该字后面：长[cháng]、调[tiáo]节。
- API Key 只能由用户提供。 缺 GLM_API_KEY 时先问用户：配置 key（音质最好，推荐），还是用兜底引擎（edge-tts / macOS say，见 reference/glm-tts-setup.md）。不要编造 key、模型名或接口地址，不要把 key…
- 物理画面必须正确。 力的方向（摩擦力与相对运动相反、弹力垂直接触面）、力箭头按同一比例 FS、物体位置来自解析解、特殊角用课本近似值（sin37° = 0.6）与答案一致；小角度放大画时注明 notToScale()。
- 所有画面内容在 y ≤ 860 以内（y≈914~1044 是字幕框）。图形放左半边 x 60~900，推导写在右边 board() 上，用 bm()（支持 v_0^2 上下标）。
- 先写分镜，再写动画。 storyboard.md 顶部写解题卡 + 图形清单，再给每句旁白规划"指/动/留"，按 reference/visual-design.md 的物理动作表选动作；node render.mjs motion 必须通过。
- 先预览再花钱（--preview + stills auto），看图验证（每次都打开 build/sheet*.png，汇报你实际看到了什么）。
- 不要修改 engine.js；通用物理道具加在 phys.js，只属于这道题的图形写在 anim.js。不要把 node_modules、package*.json 复制进视频文件夹。
What it can do on your machine
Read from SKILL.md and the folder at commit 6a9c876. 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 4 files in scripts/ (Python, JavaScript and Shell, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
nodebashnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
GLM_API_KEY
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Edu Physics Video loads about 2.3k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 552 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.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:25
p4/srt 也输出到这里。**不要因为别的目录（包括本技能所在的项目）已经有 `.env`、`node_modules`、`pron.json` 就把 WS 换过去**，缺什么由 `new_video.sh` 和第 2 步补齐。`PROJ - NoteMentions a .env fileSKILL.md:57
) 引导用户**配置（`~/.config/math-problem-video/.env`，与数学视频技能共用）。用户没有 key：`TTS_ENGINE=auto` 自动改用兜底引擎；装 edge-tts 前先征得用户同意。 - NoteMentions a .env fileSKILL.md:146
glm-tts-setup.md)：智谱 GLM-TTS 注册、API Key、`.env`、音色、兜底引擎。
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 wy51ai/edulab at commit 6a9c876, republished under its Apache-2.0 licence (© wy51ai). 552 words, ~2,266 tokens.
Download SKILL.mdSave it as
.claude/skills/edu-physics-video/SKILL.md (or your agent's skills folder). This skill also uses 35 other files; get the full folder from GitHub.- name
- edu-physics-video
- description
- Use when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a physics problem (物理题: mechanics/力学 受力分析 牛顿定律 斜面 传送带 板块 平抛 圆周 能量 动量, optics/光学 折射, electromagnetism/电磁 带电粒子), from a problem screenshot or text, with Chinese voice-over (GLM-TTS / 智谱 TTS), bilingual zh+en subtitles and blueprint-style canvas animation where the motion follows the real solution, rendered to MP4.
物理题讲解视频 (edu-physics-video)
把一道物理题做成 16:9、1920×1080、带中文配音 + 中英双语字幕 + 蓝图风格动画的 MP4。流水线与 edu-math-video 相同，区别在解题方法和画面：先按物理解题流程（建模 → 分段 → 受力 → 选规律 → 求解 → 验算）解对，再让画面把物理过程真实地演出来——力箭头按比例从作用点长出、物体按解析解运动、v-t 图同步生长、摩擦力随运动反向而转向。
script.json ──build_audio.py──► build/timeline.json + build/mix.wav + ../<name>.srt
(旁白) (GLM-TTS + 合成音乐) │
anim.js + phys.js + engine.js ◄───────────────┘ (按旁白时间点驱动动画)
└──node render.mjs video──► ../<name>.mp4核心原则：画面跟着旁白走，物理过程在图上真的发生。 每句旁白都有一个动作把这句物理演出来；每个动画用"第 k 句旁白开始的时刻"S.at(k, f) 定时，绝不写死秒数；物体的位置只来自解析解 x(t)，用 simT() 线性映射时间（可以慢放，不能缓动）。
本技能自带全部代码，不要从别的项目复制文件：
template/：可直接运行的完整示例项目（斜面往返：受力分析 + 牛顿第二定律 + 两段运动 + v-t 图）。engine.js是通用引擎（蓝图主题，不改），phys.js是物理道具库（力、斜面、物块、弹簧、光线、图像、场），anim.js/script.json/episode.json/storyboard.md/problem.png是每道题都要重写的。examples/laser-curvature/：几何光学竞赛题完整示例（anim.js + script.json + storyboard.md + problem.png）：光线传播、平行玻璃砖侧移、折射定律小角近似、屏幕正视图分解位移、切线/圆心角。光学、几何味重、或题目截图带装置图时先读它。shared/pron.py+shared/pron.json：读音控制（GLM-TTS 没有 SSML/拼音输入），已收录物理常见多音词。scripts/：new_video.sh（建项目）、setup_check.sh（查环境）、make_problem_png.py（文字题→图片+高亮框，公式/单位不会被折行拆开）、problem_boxes.py（截图→高亮框坐标）、contact_sheet.py（截图拼图审查）。
下文 SKILL = 本文件所在目录，WS = 用户当前所在的目录（你的工作目录，$PWD）：视频文件夹建在这里，mp4/srt 也输出到这里。不要因为别的目录（包括本技能所在的项目）已经有 .env、node_modules、pron.json 就把 WS 换过去，缺什么由 new_video.sh 和第 2 步补齐。PROJ = 本视频文件夹，PY = setup_check.sh 报告的 python（macOS 上一般是 /usr/bin/python3）。
必须遵守的规则
退出码不是 0 就是没完成。 --check 退出码 1（哪怕只剩一个 ⚠ 多音字）、motion 退出码 1、截图里有问题，都不能写"只是警告、不影响"然后继续。修好再往下走。
- 严格按下面 11 步顺序做，每步的"通过标准"满足了才能进入下一步。
- 先按物理方法解对题。 第 1 步必须写出解题卡（研究对象、过程分段、每段受力、所用规律、答案、验算），见 reference/physics-solving.md。多段过程、符号答案用 sympy 验算。
- 先讲清楚题目。 第一幕展示原题图片，旁白逐条读条件，每读一条就在图上框出那一条。
tts字段只能是能念出来的中文。 不能有阿拉伯数字、= + − × ÷ / ^ √ ° ( )等符号，单位要读出来：v₀ = 10 m/s写成v零等于十米每秒，2 m/s²写成二米每二次方秒；sin/cos 写成 正弦/余弦；希腊字母按 pronunciation.md 的表写（θ 西塔、φ 菲）。字幕zh保留正常物理写法（v_0、d_A、m/s^2）。- 读音必须固定。 调 TTS 之前
--check必须显示未固定读音的生僻字/多音字: 0且script errors: 0。多音字的标注写在该字后面：长[cháng]、调[tiáo]节。 - API Key 只能由用户提供。 缺
GLM_API_KEY时先问用户：配置 key（音质最好，推荐），还是用兜底引擎（edge-tts / macOSsay，见 reference/glm-tts-setup.md）。不要编造 key、模型名或接口地址，不要把 key 打印出来或写进项目文件夹。 - 物理画面必须正确。 力的方向（摩擦力与相对运动相反、弹力垂直接触面）、力箭头按同一比例
FS、物体位置来自解析解、特殊角用课本近似值（sin37° = 0.6）与答案一致；小角度放大画时注明notToScale()。 - 所有画面内容在 y ≤ 860 以内（y≈914
1044 是字幕框）。图形放左半边 x 60900，推导写在右边board()上，用bm()（支持v_0^2上下标）。 - 先写分镜，再写动画。
storyboard.md顶部写解题卡 + 图形清单，再给每句旁白规划"指/动/留"，按 reference/visual-design.md 的物理动作表选动作；node render.mjs motion必须通过。 - 先预览再花钱（
--preview+stills auto），看图验证（每次都打开build/sheet*.png，汇报你实际看到了什么）。 - 不要修改
engine.js；通用物理道具加在phys.js，只属于这道题的图形写在anim.js。不要把node_modules、package*.json复制进视频文件夹。
11 个步骤
第 1 步：按物理方法解题，写解题卡
读 reference/physics-solving.md。拿到题目（有截图先读图），写下：
- 研究对象与模型；过程分段（每段的起止条件与分段判据：速度为零、共速、能否滑回、是否脱离……）；每段受力（大小、方向）；每段所用规律及理由；符号解 → 数值答案（带单位）；验算（量纲、极限、能量/动量另算一遍）。
- 多段过程或符号答案：用 sympy 写脚本算一遍。答案不确定或题目看不清时问用户，不要猜。
- 通过标准： 解题卡完整；能用 4~7 个"幕"讲完（一般一段过程一幕）；答案已验算。
第 2 步：建项目、查环境
bash SKILL/scripts/new_video.sh "$PWD" <ascii_folder_name> # WS 就是当前目录
bash SKILL/scripts/setup_check.sh WS/<ascii_folder_name>new_video.sh会把pron.py/pron.json链接到技能自带的共享词表，并在找得到时把node_modules链接到已有安装；找不到才需要在WS下npm install。python 包用PY -m pip install --user numpy requests pypinyin pillow。- 缺
GLM_API_KEY：停下，按 reference/glm-tts-setup.md 引导用户配置（~/.config/math-problem-video/.env，与数学视频技能共用）。用户没有 key：TTS_ENGINE=auto自动改用兜底引擎；装 edge-tts 前先征得用户同意。 - 通过标准：
setup_check.sh输出ALL OK。
第 3 步：测试 TTS
cd PROJ && PY build_audio.py --say "你好，我们来看一道物理题。"- 成功打印
WROTE build/say_xxxx.wav。401/403 = key 错或没余额，告诉用户，不要反复重试。第一次给这个用户做视频时，把 wav 路径给用户试听确认音色。 - 通过标准： 生成了 wav。
第 4 步：准备题目图片 problem.png 和高亮框
二选一（细节见 reference/animation.md）：
- 只有文字：
PY SKILL/scripts/make_problem_png.py --text "完整题目" --mark "条件1" ... --out PROJ/problem.png。问题 (1)(2)(3) 前用换行\n分行。 - 有截图（物理题常带装置图）：复制到
PROJ/，必要时problem_boxes.py crop；problem_boxes.py grid读坐标；problem_boxes.py check确认。截图很高时在 anim.js 里Object.assign(FRAME, { y0: 110, y1: 880 })放大卡片。 - 把尺寸和框填进
anim.js顶部的PROBLEM。 - 通过标准： 打开了
*.preview.png或*.check.png，文字完整（没有 ☒/□），每个框恰好罩住对应文字。
第 5 步：写 episode.json 和 script.json
按 reference/script-writing.md 写（含物理式子、单位、希腊字母的口语对照表）。
- 幕的顺序照解题流程：
intro读题 → 受力/建模 → 每段过程 → 分段判断/临界 → （验算）→outro回顾 + 报答案。 - 每句 ≤ 36 个汉字宽，一句只讲一件事；数值与解题卡完全一致，带单位。
- 通过标准： JSON 合法；每一幕的 id 都有计划好的画面。
第 6 步：写分镜 storyboard.md
先读 reference/visual-design.md，按 template/storyboard.md 的格式：顶部写解题卡和图形清单（所有物体、接触面、力、已知量、所求量、图像），再每句一行 | 幕id 句号 | 旁白要点 | 指 | 动 | 留 | 板书 |。
- "动"从物理动作表选：力从作用点长出、分解、复制品叠放比较大小、摩擦力转向、物体按解真实运动、v-t 曲线生长、面积着色、光线传播……不能只写"出现/显示/高亮"。每幕至少一个连续运动。
- 通过标准： 每句都有一行；图形清单完整；你能说出每一幕里"最能让人看懂物理"的那个动作。
Show full SKILL.md (218 more words)Show less
第 7 步：读音与脚本检查，修到 0
cd PROJ && PY build_audio.py --check ; cat build/pron_report.txtERROR行按提示改；⚠ 多音/生僻按 reference/pronunciation.md 处理（物理常见多音字、希腊字母表都在里面）。- 通过标准：
未固定读音的生僻字/多音字: 0且script errors: 0，退出码 0。
第 8 步：写 anim.js
先通读 template/anim.js，API 见 reference/animation.md（engine.js + phys.js 速查）。结构保持一致：
PROBLEM、TAGS；物理解常量区（课本近似值、分段解析解sPos(t)、vel(t)）；几何（incline/block等用p: 0只算几何）；比例常量FS（px/N）、VS（px per m/s）；SC.<id>每幕一个。- 每句：
glow(..., bump(lt, at(k)))指 → 动作 → 留下标记；右侧board()+bm(...)逐行写推导（与图同色），答案用bbox+stamp。 - 通过标准：
PY build_audio.py --check无 ERROR。
第 9 步：免费预览：动作检查 + 版面检查
cd PROJ && PY build_audio.py --preview && node render.mjs motion && node render.mjs stills auto && PY SKILL/scripts/contact_sheet.py .motion：STATIC必须修，每幕至少一句MOVE。- 打开
build/sheet_*.png逐张检查（审查清单）：不重叠、不出界、不压字幕、同步；物理正确：力的方向与比例、物体停下/反向的位置与时刻、图像与运动一致。需要中间帧：node render.mjs stills 12.5,13。 - 通过标准：
motion check passed；截图检查通过（在回复里逐幕说明你看到了什么）。
第 10 步：生成配音，自动听写核对，再检查一次画面
cd PROJ && PY build_audio.py && PY build_audio.py --asr && node render.mjs stills auto && PY SKILL/scripts/contact_sheet.py .--asr字母序列对不上的句子标 ✗（退出码 1）：按 pronunciation.md 的"字母"一节修改后重跑。- 真实时长与预览不同，重新看一遍 sheet（慢放倍率也会变）。
- 通过标准：
mix + srt written；字母读错的句子: 0（无 GLM key 时ASR SKIPPED，交付时列出含字母的句子请用户重点听）；截图检查通过。
第 11 步：渲染视频并交付
cd PROJ && node render.mjs video 6 # 6 = 并行浏览器页数（不是帧率！帧率固定 30）- 输出
WS/<output_name>.mp4和.srt。交付时告诉用户：路径、时长、各幕内容、答案；说明你无法听音频，请用户试听读音，列出你标注过读音的字和希腊字母。
常见错误
| 错误做法 | 正确做法 |
|---|---|
| 直接列公式算答案，不讲研究对象和过程分段 | 解题卡先行；幕结构 = 解题流程，分段判据单独一幕讲 |
| 摩擦力按"速度方向的反方向"画，物体反向后忘了改 | 按相对运动（趋势）方向；运动反向时让 f 箭头绕作用点转 180° |
物体位置用 lerp(a, b, eio(...)) 滑过去 | sPos(simT(lt, t0, dur, T))：解析解 + 线性时间，屏幕注明"慢放 ×k" |
| 力箭头长度随手画，8 N 比 12 N 还长 | 一幕一个比例 FS，长度 = 大小 × FS |
Math.sin(37 * PI / 180) | 课本近似 SIN = 0.6, COS = 0.8，与答案一致 |
tts 写 mg sinθ、sin i、μ = 0.5 | 重力沿斜面的分力 / m g乘正弦西塔、正弦i、动摩擦因数零点五 |
tts 里的单位省略或写 m/s | 十米每秒、二米每二次方秒，单位一定要读 |
希腊字母写 斐、伽马 | 菲、嘎马（见 pronunciation.md 希腊字母表） |
板书用 bl('v0^2 ...') | bm('v_0^2 / 2a_1 ...') 渲染上下标 |
| 装置图画到右边板子上 | 缩小比例，或该幕 ctx.translate 左移（board/bm 在 translate 外） |
| 从别的视频文件夹复制代码 | 用 new_video.sh 从本技能 template/ 建项目 |
编造 GLM_MODEL、接口地址 | 模型只有 glm-tts，地址已写在 build_audio.py；只需用户提供 GLM_API_KEY |
node render.mjs video 24 以为是 24fps | 参数是并行数；预览版面用 stills auto |
--check 还有 ⚠ 就调 TTS | 修到 0 |
| 渲染完不看画面就交付 | 每次都看 build/sheet*.png |
参考文件
- reference/physics-solving.md：物理解题方法：六步流程、分段判据、sympy 验算、把解变成动画的要求、常见题型的幕结构。第 1 步必读。
- reference/visual-design.md：讲解动画设计：指→动→留→连、物理配色、物理→动画动作表、真实运动写法。写分镜前必读。
- reference/animation.md：engine.js + phys.js API、场景写法、版面坐标、题目图片与高亮框、审查清单。
- reference/script-writing.md：
script.json格式、幕的设计、物理式子/单位的口语写法对照表。 - reference/pronunciation.md：读音控制、物理常见多音字、希腊字母读法。
- reference/glm-tts-setup.md：智谱 GLM-TTS 注册、API Key、
.env、音色、兜底引擎。 - reference/troubleshooting.md：报错与处理。
© wy51ai, Apache-2.0. 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 35 other files (scripts) in skills/edu-physics-video of wy51ai/edulab.
- SKILL.md
- examples/laser-curvature/anim.js
- examples/laser-curvature/episode.json
- examples/laser-curvature/problem.png
- examples/laser-curvature/script.json
- examples/laser-curvature/storyboard.md
- reference/animation.md
- reference/glm-tts-setup.md
- reference/physics-solving.md
- reference/pronunciation.md
- reference/script-writing.md
- reference/troubleshooting.md
- reference/visual-design.md
- scripts/contact_sheet.py
- scripts/make_problem_png.py
- scripts/new_video.sh
- scripts/problem_boxes.py
- … and 19 more
Open the folder on GitHubat commit 6a9c876
Compare with similar skills
Edu Physics 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 |
|---|---|---|---|---|---|---|
| Edu Physics Video this skillwy51ai/edulab | 1.4k | — | ~2.3k | Automated safety check: Notes | Apache-2.0 | |
| Video TranslationNoizAI/skills | 526 | — | ~1.3k | Automated safety check: Notes | None | |
| Proofreadsonilo-ai/skills | 115 | — | ~4.4k | Automated safety check: Notes | MIT | |
| Wjs Localizing Videojianshuo/claude-skills | 131 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Groq Core Workflow Bjeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Video Translatorshang-zhu/violin | 1.1k | — | ~1k | Automated safety check: Notes | MIT |
Similar skills
Proofread
sonilo-ai/skills
Transcribe a video with Sonilo and translate the transcript into editable .srt files — one per target language, plus the detected source language — so the wording can be read and corrected before…
Wjs Localizing Video
jianshuo/claude-skills
Thin orchestrator for the end-to-end video localization pipeline.
Groq Core Workflow B
jeremylongshore/tons-of-skills-marketplace
A skill your agent uses when you need Groq's non-chat endpoints — transcribing or translating audio with Whisper, understanding images with Llama 4 vision, generating speech (TTS), or benchmarking…
Video Translator
shang-zhu/violin
Dub a video into another language and generate subtitles using the default Together + Cartesia stack.
HyperFrames Media Use
heygen-com/hyperframes
Finds, generates and edits media for HyperFrames video projects: music, sound effects, images, icons, logos, voiceovers, captions and color grades.
More from wy51ai/edulab
Edu Chem Video
wy51ai/edulab
A skill your agent uses when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a chemistry problem (化学题: 氧化还原配平 双线桥 电子守恒, 物质的量计算, 化学平衡 三段式 平衡常数 转化率 反应速率, 离子反应, 电化学, 溶液 滴定…
Edu Analytic Geometry
wy51ai/edulab
把一道解析几何题解成一个自包含的交互教学网页：左栏题面 + 动态控制台（一个 可变参数滑块驱动实时重算的几何量 + 理论范围/定值指示），中栏 KaTeX 分步解析，右栏 2D Canvas 动态几何画板（椭圆/双曲线/抛物线/圆 + 动直线/动点 + 向量 + 标注 + 画笔涂鸦）。
Edu Math Video
wy51ai/edulab
A skill your agent uses when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a math problem (数学题, geometry, algebra, functions, motion/行程 problems), from a problem screenshot…
Edu Solid Geometry
wy51ai/edulab
把一道立体几何题解成一个自包含的交互教学网页：左侧 MathJax 分步解析， 右侧 Three.js 可交互 3D 模型（分步高亮 + 镜头切换）。支持三种入口——给定文字题目、 随机出题、上传题目图片识别后解题。覆盖正方体/长方体、棱锥/棱柱、圆柱/圆锥上的线面角、 二面角、异面直线夹角、点到平面距离、体积等题型，统一用"建系+向量法"，并由 sympy 精确 计算驱动（答案、3D…
Edu Chem Reaction
wy51ai/edulab
把一个化学反应做成自包含的微观 3D 交互演示网页：左/上为 Three.js 可交互分子动画 （拖滑块看断键·成键·原子重组，分步高亮），右为 KaTeX 反应方程 + 分步讲解 + 原子守恒计数 + 可选能量-反应进程曲线。支持三入口——给定文字反应/方程、随机出题、上传图片识别后演示。
Related
Categories
Questions about Edu Physics Video
What does Edu Physics Video do?
A skill your agent uses when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a physics problem (物理题: mechanics/力学 受力分析 牛顿定律 斜面 传送带 板块 平抛 圆周 能量 动量, optics/光学 折射…. Edu Physics Video is an agent skill from wy51ai/edulab. Use when asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a physics problem (物理题: mechanics/力学 受力分析 牛顿定律 斜面 传送带 板块 平抛 圆周 能量 动量, optics/光学 折射, electromagnetism/电磁 带电粒子), from a problem screenshot or text, with Chinese voice-over (GLM-TTS / 智谱 TTS), bilingual zh+en subtitles and blueprint-style canvas animation where the motion follows the real solution, rendered to MP4.
When should I use Edu Physics Video?
Edu Physics Video fits situations like: asked to make an explainer / walkthrough video (讲解视频、解题视频、例题精讲、微课) for a physics problem (物理题: mechanics/力学 受力分析 牛顿定律 斜面 传送带 板块 平抛 圆周 能量 动量; electromagnetism/电磁 带电粒子); from a problem screenshot; with Chinese voice-over (GLM-TTS / 智谱 TTS).
How do I install Edu Physics Video in Claude Code?
Run `npx skills add wy51ai/edulab --skill edu-physics-video -a claude-code`. Or copy the skill folder (skills/edu-physics-video in wy51ai/edulab) into .claude/skills/edu-physics-video in your project. Claude Code loads it when a task matches its description.
How do I install Edu Physics Video in Codex?
Run `npx skills add wy51ai/edulab --skill edu-physics-video -a codex`. Or copy the skill folder (skills/edu-physics-video in wy51ai/edulab) into .agents/skills/edu-physics-video in your project. Codex loads it when a task matches its description.
Can I use Edu Physics Video 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 wy51ai/edulab --skill edu-physics-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/edu-physics-video, .gemini/skills/edu-physics-video, .github/skills/edu-physics-video and .opencode/skills/edu-physics-video in your project.
What does Edu Physics Video need to run?
Going by SKILL.md and its folder, Edu Physics Video needs Python, JavaScript and a shell for the scripts in its folder, the command-line tools its instructions call (node, bash and npm) and credentials named GLM_API_KEY. Our summary lists: Python 3; Node.js; A Bash shell; A credential in GLM_API_KEY.
Does Edu Physics Video access the network?
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Edu Physics Video safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. 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 Edu Physics Video use?
Edu Physics Video is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Edu Physics Video use?
About 2.3k tokens (SKILL.md is roughly 9.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Edu Physics Video?
Skills that share tags, products or a category with Edu Physics Video: Video Translation (NoizAI/skills, 526 stars), Proofread (sonilo-ai/skills, 115 stars), Wjs Localizing Video (jianshuo/claude-skills, 131 stars) and Groq Core Workflow B (jeremylongshore/tons-of-skills-marketplace, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Edu Physics Video?
wy51ai (a GitHub user) maintains it in wy51ai/edulab, which has 1,406 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 10, 2026.
Source: wy51ai/edulab on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.