andyhuo520/vibe-knowledge / skills/ai-teardown
ai-teardown
Unverified「AI 拆机课」系列课工作室:输入一个主题(AI 产品、开源项目/书、人物历史、软件教程),产出由浅入深、每句话有出处的中文讲解视频系列 + 每节互动版 + 课程总页。流水线:收集资料 → 确认对象与课时 → 大纲 → 逐节旁白(MiMo 克隆音色 + 逐字对齐)→ scenes.json 画面编排(Notion 极简手绘引擎 / 马卡龙模板引擎,IconPark 图标与插画、Noto 动态 emoji、AntV X6 流程图、像素讲解小人、截图圈注、终端录屏)或 film.js 代码成片(cine 引擎:Three.js、粒子、着色器、真片段叠加、曲库配乐)→ Hyperframes / 无头 GPU 逐帧 1080p 渲染 → Artifact 发布 → 课程总页 + 导学视频。触发:做系列课 / 做课程视频 / 把某本书或某个开源项目做成课 / 科普讲解视频 / 教学视频 / 课程地图 / 导学视频 / 互动课件 / 「拆机课」「上手课」「实战课」「编排课」/ 王炸讲解片 / 用真实会话和成片教人做视频。不用于:单支宣传片(用 promo-video)、单张信息图、纯文章写作。
engine/scripts/sketch_publish_files.py
View on GitHub#!/usr/bin/env python3
"""手绘引擎的一节课:算出互动版真正用到的图片,输出 Artifact 发布用的 files 映射(JSON)。
用法:python3 scripts/sketch_publish_files.py <课目录> (在仓库根目录运行)
"""
import json, re, sys
from pathlib import Path
L = Path(sys.argv[1]); sd = L.parent.parent; nn = L.name
spec = json.loads((L / "scenes.json").read_text()); txt = json.dumps(spec, ensure_ascii=False)
led = {i["id"]: i for i in json.loads((sd / "assets/img/images.json").read_text())["images"]}
lot = {f.stem for f in (L / "lottie").glob("*.json")} if (L / "lottie").exists() else set()
names = set(re.findall(r'"(?:emoji|name|icon)": "([a-z0-9-]+)"', txt))
for s in spec["scenes"]:
names |= set(s.get("stickers", []))
for side in ("left", "right"):
if isinstance(s.get(side), dict) and s[side].get("emoji"): names.add(s[side]["emoji"])
names |= {"thinking-face"}
pre = "noto" if spec.get("skin") == "notion" else "emoji"
ids = {f"{pre}-{n}" for n in names - lot if ":" not in n}
ids |= set(re.findall(r'"(?:img|iconImg)": "([a-z0-9-]+)"', txt))
for s in spec["scenes"]:
if s.get("clip"):
fl = json.loads((L / f"data/flip-{s['clip']}.json").read_text()); ids |= set(fl["frames"])
if spec.get("presenter") == "hp":
ids |= {i for i in led if i.startswith("hp-")}
elif spec.get("presenter"):
ids |= {f"{spec['presenter']}-{k}" for k in ("0", "blink", "talk", "talk-blink")}
pub = sd / f"publish/lesson{nn}"
files = {"app.js": str(pub / "app.js"), "audio.mp3": str(pub / "audio.mp3")}
for v in sorted([*(pub / "video").glob("*.mp4"), *(pub / "video").glob("*.jpg")]) if (pub / "video").exists() else []: # 视频贴纸 + 封面
files[f"video/{v.name}"] = str(v)
for i in sorted(ids):
if i in led and (pub / "img" / led[i]["file"]).exists():
files[f"img/{led[i]['file']}"] = str(pub / "img" / led[i]["file"])
missing = sorted(i for i in ids if i not in led or not (pub / "img" / led[i]["file"]).exists())
if missing: print("缺:", missing, file=sys.stderr)
print(json.dumps(files, ensure_ascii=False))
print(f"{len(files)} 个文件", file=sys.stderr)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |