{
  "markdown": "# edulab\n\n[简体中文](README.zh-CN.md) · **English**\n\nA collection of education skills that turn academic problems into **interactive lesson web pages** and **narrated explainer videos**.\n\n## Install\n\n**Recommended** — install with [skills](https://github.com/vercel-labs/skills) in one command:\n\n```bash\nnpx skills add wy51ai/edulab\n```\n\nTo update to the latest version later:\n\n```bash\nnpx skills update\n```\n\n> **Note:** `npx skills update` only refreshes skills you've **already** installed — it does **not** pull in skills newly added to the repo. When this repo gains a new skill (e.g. a new `edu-*`), run `npx skills add wy51ai/edulab` again to install it.\n\nOr use it as a Claude Code plugin marketplace:\n\n```\n/plugin marketplace add wy51ai/edulab\n/plugin install edulab\n```\n\nOnce installed, the skills activate on their trigger words, and can also be invoked manually.\n\n## Skill: edu-solid-geometry\n\n![edu-solid-geometry demo](edu-solid-geometry.gif)\n\nSolves one solid geometry problem into a self-contained interactive lesson page. Three entry points:\n\n| Entry point | What it does |\n|---|---|\n| Text problem | Extracts the statement and solves directly |\n| Image upload | Reads the problem from the image via vision, echoes it back for confirmation, then solves |\n| Random problem | Solves with random parameters; re-rolls if the answer isn't clean |\n\n**Problem types covered**: line-plane angle, dihedral angle, angle between skew lines, point-to-plane distance, volume, and more — on cubes / cuboids, pyramids / prisms, cylinders / cones. All solved uniformly via the \"coordinate system + vector method.\"\n\n**Trigger words**: solid geometry, line-plane angle, dihedral angle, angle between skew lines, distance to plane, interactive geometry solution page; 立体几何、线面角、二面角、异面直线、点到平面距离、正四棱锥、解这道几何题、随机出一道立体几何题、这张图里的立体几何题, etc.\n\n### Dependency\n\nThe compute core `lib/geometry_kernel.py` depends on **sympy**. Use any `python3` that can import sympy:\n\n```bash\npython3 -m pip install sympy   # if sympy is missing\n```\n\n### Generate from the command line (without Claude)\n\n```bash\ncd skills/edu-solid-geometry\npython3 scripts/generate.py cube   ./cube.html     # cube · line-plane angle\npython3 scripts/generate.py box    ./box.html      # cuboid · volume\npython3 scripts/generate.py random 7 ./random.html # random problem (seed=7)\npython3 lib/geometry_kernel.py                     # kernel built-in self-check\n```\n\n> If you don't pass an output path, it writes to the **current working directory (cwd)**.\n\n## Skill: edu-analytic-geometry\n\n![edu-analytic-geometry demo](edu-analytic-geometry.gif)\n\nSolves one analytic geometry (conic sections) problem into a self-contained interactive lesson page. Same three entry points as above (text / image / random). Built on a **2D Canvas board + KaTeX** with a generic, data-driven interactive engine: a parameter slider drives derived constructions (line∩conic, point-on-conic, central reflection, tangent…) and live readouts, with a theoretical-range bar or a fixed-value indicator.\n\n**Problem types covered**: standard equation, chord length, dot-product range / fixed value, triangle-area extremum, fixed point, fixed value (slope product), locus, tangent, eccentricity — on ellipses / hyperbolas / parabolas / circles. All solved uniformly via \"parametrized line `x = my + c` + system + Vieta's formulas + substitution.\"\n\n> A correctness note baked into the kernel: open/closed interval endpoints are decided by whether a *real* line attains them, so the boxed answer always matches what the interactive tool shows (e.g. the ellipse `MA·MB` range is the **closed** `[-3, 7/4]` — slide θ to 0° and you read exactly −3).\n\n**Trigger words**: analytic geometry, conic sections, ellipse, hyperbola, parabola, chord length, dot product range, fixed point, fixed value, locus, eccentricity, interactive analytic geometry solution page; 解析几何、圆锥曲线、椭圆、双曲线、抛物线、焦点弦、向量数量积取值范围、定点问题、定值问题、斜率之积、三角形面积最值、轨迹方程、离心率, etc.\n\n### Dependency\n\nThe compute core `lib/analytic_kernel.py` depends on **sympy** (same as above).\n\n### Generate from the command line (without Claude)\n\n```bash\ncd skills/edu-analytic-geometry\npython3 scripts/generate.py list                          # list registered problem types\npython3 scripts/generate.py ellipse_dot_range ./sol.html  # ellipse · MA·MB range [-3, 7/4]\npython3 scripts/generate.py parabola_dot_const ./sol.html # parabola focal chord · OA·OB ≡ -3\npython3 scripts/generate.py all ./out_dir                 # all registered types\npython3 lib/analytic_kernel.py                            # kernel built-in self-check\n```\n\n> Like above, no output path → writes to the **current working directory (cwd)**.\n\n## Skill: edu-chem-reaction\n\n![edu-chem-reaction demo](edu-chem-reaction.gif)\n\nTurns one chemical reaction into a self-contained **microscopic 3D demonstration** page: an interactive Three.js molecular animation (drag the slider to watch bonds break / form and atoms recombine, with step highlighting) next to the KaTeX equation, step-by-step narration, an atom-conservation counter, and an optional energy–reaction-coordinate curve. Same three entry points (text / image / random).\n\n**Two engines, auto-selected** — one renderer with two per-frame position resolvers, sharing the bond-diff drawing, labels, overlays and UI:\n\n| Engine | For | Emphasizes |\n|---|---|---|\n| morph | combustion, combination / decomposition / displacement, redox | atoms fly to new partners — atom conservation & recombination |\n| mechanism | organic mechanisms (esterification…) with catalyst · transition state · leaving groups | rigid fragments move through keyframes — the mechanism |\n\n**sympy-driven correctness**: auto-balances the equation (integer coefficients from the matrix null space), validates the atom map (a bijection between reactant and product atoms) and conservation, and derives which bonds break / form from the before↔after difference — equation, geometry and counters all share one source.\n\n**Hybrid geometry**: a built-in VSEPR molecule library by default; if RDKit is installed it can build conformers from SMILES (never installs it automatically).\n\n**Reactions covered**: methane / hydrogen combustion, water electrolysis, Na + Cl₂ redox (with an electron-transfer overlay), glucose aerobic oxidation, and the esterification mechanism — spanning junior-high basics, senior inorganic redox, and organic mechanisms.\n\n**Trigger words**: chemistry reaction, microscopic / molecular animation, combustion, electrolysis, redox electron transfer, esterification mechanism, bond breaking and forming, atom conservation, balance equation, interactive chemistry reaction page; 化学反应、微观演示、分子动画、燃烧、电解水、氧化还原、电子转移、酯化反应、断键成键、原子守恒、化学方程式配平 etc.\n\n### Dependency\n\nThe compute core `lib/reaction_kernel.py` depends on **sympy** (same as above). **RDKit is optional** — used only if already installed, never installed automatically.\n\n### Generate from the command line (without Claude)\n\n```bash\ncd skills/edu-chem-reaction\npython3 scripts/generate.py list                            # list registered reactions\npython3 scripts/generate.py combustion_ch4 ./reaction.html  # methane combustion (morph · flame)\npython3 scripts/generate.py esterification ./reaction.html  # esterification (mechanism · catalyst)\npython3 scripts/generate.py random 7 ./random.html          # random reaction (seed=7)\npython3 lib/reaction_kernel.py                              # kernel built-in self-check\n```\n\n> Like above, no output path → writes to the **current working directory (cwd)**.\n\n## Skill: edu-math-video\n\n![edu-math-video demo](edu-math-video.png)\n\nTurns one math problem (geometry, algebra, functions, motion problems…) into a **16:9 1920×1080 explainer MP4**: Chinese voice-over (Zhipu **GLM-TTS**), bilingual zh + en subtitles (`.srt` too), and hand-drawn notebook-style canvas animation driven by the narration timeline. Input is a problem screenshot or plain text.\n\n**The picture explains the step**: every narration line gets a \"point → move → keep\" action on the figure (equal segments slide onto each other, congruent triangles overlay, the 3D camera tweens to a top view, a cone unrolls into a sector…) — timed by `S.at(k, f)` (a fraction into line *k*), never by hard-coded seconds. A `motion` check rejects static lines.\n\n**Pipeline** (one folder per video, created in the user's current directory):\n\n```\nscript.json ──build_audio.py──► timeline.json + mix.wav + <name>.srt   (GLM-TTS + synthesized music)\nanim.js + engine.js ──node render.mjs video──► <name>.mp4              (Playwright + ffmpeg, 30 fps)\n```\n\n**Guard rails**: the first scene shows the original problem with each condition boxed as it is read; `tts` text must be speakable Chinese (no digits / math symbols); polyphones are pinned (`长[cháng]`, shared `pron.json` lexicon) and `--check` must report 0 before any paid TTS call; a free `--preview` + contact-sheet review comes before real audio; `--asr` transcribes the audio back to catch misread letters.\n\n**Trigger words**: math explainer video, walkthrough video, problem-solving video, micro-lesson; 讲解视频、解题视频、例题精讲、微课 etc.\n\n### Dependency\n\n- Python 3 with `numpy requests pypinyin pillow`; Node.js 18+ with `playwright` + `ffmpeg-static` (installed once in the workspace — `scripts/new_video.sh` writes the `package.json`); Google Chrome or Playwright Chromium.\n- A Zhipu **`GLM_API_KEY`** provided by you, in `~/.config/math-problem-video/.env` (see `reference/glm-tts-setup.md`).\n- **No key?** It falls back automatically (`TTS_ENGINE=auto`): [edge-tts](https://github.com/rany2/edge-tts) if installed (free neural voices, needs internet), else macOS `say` (offline, robotic). Force one with `TTS_ENGINE=glm|edge|say`.\n\n### Run the pipeline by hand (without Claude)\n\n```bash\nbash skills/edu-math-video/scripts/new_video.sh \"$PWD\" my_problem   # scaffold from template/\nbash skills/edu-math-video/scripts/setup_check.sh my_problem        # must print ALL OK\ncd my_problem\npython3 build_audio.py --check                                      # script + pronunciation lint (free)\npython3 build_audio.py --preview && node render.mjs motion && node render.mjs stills auto\npython3 build_audio.py && node render.mjs video 6                   # real TTS, then render (6 = parallel pages)\n```\n\n## How it works\n\n1. **Get a problem spec** — normalize all three entry points into a structured description (body type and dimensions, given conditions, the quantity asked, language).\n2. **Exact kernel computation** — sympy computes exact coordinates, key vectors, normals, the final answer, and every intermediate value (as LaTeX strings). Never by hand.\n3. **Assemble and inject the template** — feed the `lesson` / `steps` / `model` data into the data-driven template `template/lesson.html`; 3D vertex coordinates come from `kernel.to_three(...)`, sharing the same source as the solution.\n4. **Self-check** — kernel answer == answer card == final value shown in the last step; a local static server + preview check confirms no console errors and correct formula/highlight rendering.\n5. **Deliver** — the finished page is written to the user's current working directory, named like `solution-<short-description>.html`.\n\n## Project structure\n\n```\nedulab/\n├── .claude-plugin/\n│   ├── plugin.json              # plugin metadata\n│   └── marketplace.json         # marketplace manifest\n├── index.html                   # finished sample (quad pyramid · line-plane angle)\n└── skills/\n    ├── edu-solid-geometry/      # solid geometry — 3D (Three.js) + MathJax\n    │   ├── SKILL.md\n    │   ├── template/lesson.html # data-driven template (generic 3D renderer + data island)\n    │   ├── lib/\n    │   │   ├── geometry_kernel.py  # sympy exact-computation core\n    │   │   └── bodies.py           # edge-topology library for solids\n    │   ├── scripts/generate.py\n    │   ├── output/\n    │   └── references/          # problem-schema.md · conventions.md\n    ├── edu-analytic-geometry/   # analytic geometry / conics — 2D (Canvas) + KaTeX\n    │   ├── SKILL.md\n    │   ├── template/board.html  # data-driven template (generic 2D renderer + param engine)\n    │   ├── lib/\n    │   │   ├── analytic_kernel.py  # sympy exact-solver core (system · Vieta · range · fixed value)\n    │   │   └── conics.py           # conic-section definition library\n    │   ├── scripts/generate.py\n    │   ├── output/\n    │   └── references/          # problem-schema.md · conventions.md\n    ├── edu-chem-reaction/       # chemistry reactions — 3D (Three.js) + KaTeX\n    │   ├── SKILL.md\n    │   ├── template/reaction.html # data-driven template (unified renderer + dual engine + data island)\n    │   ├── lib/\n    │   │   ├── reaction_kernel.py  # sympy balancing + conservation/atom-map check + bond-diff + assembly\n    │   │   └── molecules.py        # VSEPR molecule-geometry library\n    │   ├── scripts/generate.py\n    │   ├── output/\n    │   └── references/          # problem-schema.md · conventions.md\n    └── edu-math-video/          # math explainer videos — GLM-TTS + canvas animation → MP4\n        ├── SKILL.md\n        ├── template/            # runnable sample project (engine.js · anim.js · build_audio.py · render.mjs)\n        ├── shared/              # pron.py + pron.json — shared pronunciation lexicon\n        ├── scripts/             # new_video.sh · setup_check.sh · problem image & contact-sheet tools\n        ├── examples/cone-parallel/  # solid-geometry example (camera tween · cone unrolling)\n        └── reference/           # TTS setup · script writing · pronunciation · visual design · animation API\n```\n\n## Extending\n\n**edu-solid-geometry**\n- **Add a problem type**: add a solver function in `geometry_kernel.py` (see the recipe table in `references/conventions.md`), then add a `build_*` in `generate.py`.\n- **Add a solid**: add a coordinate-construction function in `geometry_kernel.py`, then add its edge topology in `bodies.py`.\n\n**edu-analytic-geometry**\n- **Add a problem type**: add a target-quantity function in `analytic_kernel.py` and reuse `range_over_m` / `is_constant_in_m`, then add a `build_*` in `generate.py` (pick an interaction: range bar / fixed value / fixed point / locus trace).\n- **Add a curve**: ellipse / hyperbola / parabola / circle are built in; new curves go in `conics.py` and the `board.html` engine.\n\n**edu-chem-reaction**\n- **Add a reaction**: add a `build_*` in `generate.py` (high-level `species + atom_map`, or low-level `atoms + fragments` for mechanisms) and register it in `REGISTRY`.\n- **Add a molecule / ion**: add an entry in `lib/molecules.py` (VSEPR geometry + display metadata + internal bonds).\n\n**edu-math-video**\n- **New problem**: never edit `engine.js`; write the per-problem `script.json` / `storyboard.md` / `anim.js`, and add new figure helpers inside `anim.js`.\n- **Fix a reading**: add the word to `shared/pron.json` (`words` / `ok`) — one lexicon shared by every video.\n\n## License\n\n[Apache-2.0](LICENSE)\n\n## Author\n\nWY · [@akokoi1](https://x.com/akokoi1)\n\n## Star History\n\n<a href=\"https://www.star-history.com/?repos=wy51ai%2Fedulab&type=date&legend=top-left\">\n <picture>\n   <source media=\"(prefers-color-scheme: dark)\" srcset=\"https://api.star-history.com/chart?repos=wy51ai/edulab&type=date&theme=dark&legend=top-left\" />\n   <source media=\"(prefers-color-scheme: light)\" srcset=\"https://api.star-history.com/chart?repos=wy51ai/edulab&type=date&legend=top-left\" />\n   <img alt=\"Star History Chart\" src=\"https://api.star-history.com/chart?repos=wy51ai/edulab&type=date&legend=top-left\" />\n </picture>\n</a>\n",
  "bytes": 15523,
  "sha": "72e4e53f402e9afacc8c2af6ddc408e2f05e512dfb129a6a80e7297569665286",
  "repo_slug": "wy51ai/edulab",
  "fonte": "repo",
  "truncated": false,
  "api": "https://api.agentalog.com/api/listings/skl_wy51ai_edulab_edu_math_video_0ed5c814/readme"
}