@autoaiai/aicut 0.1.11 → 0.1.13

package/skills/knowledge-explainer-skill/SKILL.md

@@ -1,149 +0,0 @@
----
-name: knowledge-explainer-skill
-description: "把 markdown / 笔记类文档自动生成讲解动画视频，AICUT 渲染、本地跑、不依赖云 API。by nyx研究所 (GitHub @znyupup · B站/小红书 @nyx研究所) Runs in AICUT: the film is film.html, a page per shot, drawn by `aicut look` and `aicut render`."
-license: MIT
-source: "znyupup/knowledge-explainer-skill"
----
-
-# knowledge-explainer-skill
-
-## Running it in AICUT
-
-AICUT's film is `film.html`: it cuts pages, footage, pictures and sound together on tracks. A page is a web page that
-sets `window.film = { frame(t) }` and draws that moment — no framework, no build step, no composition object, no
-`registerRoot`. Five shots are five pages cut together, not one page that changes scene, so each shot stays trimmable
-and replaceable in Studio.
-
-```sh
-npx -y @autoaiai/aicut@latest          # the manual: the format and the commands, always current
-npx -y @autoaiai/aicut@latest open .   # make this folder a film and print Studio's address
-npx -y @autoaiai/aicut@latest look     # a contact sheet of the whole film, its sound, and a determinism check
-npx -y @autoaiai/aicut@latest look 4.5 # one frame, full size — look at the PNG, not at the code
-npx -y @autoaiai/aicut@latest render   # the MP4, beside film.html
-```
-
-Run the manual before the first film: it is authoritative for the format, and this skill is about the method above it.
-
-Where the words below name another program's part, it becomes this:
-
-| elsewhere | in AICUT |
-|---|---|
-| composition, timeline, project file | `film.html`; tracks and clips inside it |
-| a scene, a sequence, a slide | a page (`pages/<name>.html`) cut onto a track |
-| `useCurrentFrame()`, `interpolate()` | `frame(t)` — the picture depends only on `t`, never on state or `Date.now()` |
-| a still, a screengrab | `aicut look <t>` |
-| `render` / `build` / `export` | `aicut render` (the person can also export from Studio) |
-| a dev server, a preview window | `aicut open` and the Studio address it prints |
-
-Hard rules that hold whatever the method says: the picture depends only on `t`; every value in the person's prompt is
-binding; look at the frames `look` writes before saying a film is done.
-
-
-**Author:** nyx研究所 · [GitHub](https://github.com/znyupup) · [B站 @nyx研究所](https://space.bilibili.com/4330525) · 小红书 @nyx研究所 · [X @znyupup_music](https://x.com/znyupup_music)
-
-> Skill 元信息文件 — 给 AI agent 读取使用
-
-## 触发场景
-
-当用户:
-- 想把一份文档变成视频
-- 提到"讲解动画"、"知识科普视频"、"科普讲解"
-- 给你一份 markdown / Word / 笔记类内容,问能不能做成视频
-- 提到"用 Remotion 做视频"
-
-## 工作流程
-
-1. **读取用户文档**
-   - 路径通常在 `~/Downloads/`,文件可能是 `.md` / `.txt` / 复制黏贴的内容
-   - 如果不是 markdown,先转换成 markdown
-
-2. **生成 script.md**
-   - 参考 [examples/script.md](examples/script.md) 的格式
-   - 每个章节 `## 模板名`,选择合适的内置模板
-   - 每页给一个 `duration`(秒)
-   - 复杂可视化(几何图、电路图等)用 `## CustomXxx` 段名
-
-3. **检查模板**
-   - 内置: Title / ContentCard / TwoColumn / Triangle / BeforeAfter / Outro(都是排版类)
-   - **真正的能力在 custom/** — 任何内置模板做不出来的(物理仿真、数据可视化、特效转场)主动写 jsx
-     - 文件名 = script.md 里的段名(`## CustomFunFact` → `custom/CustomFunFact.jsx`)
-     - 参考 [custom/_TEMPLATE.jsx.example`_TEMPLATE.jsx.example`
-     - 已有的 showcase 优先抄(范式覆盖广):
-       - [`custom/DoublePendulum.jsx``DoublePendulum.jsx` — 物理仿真(微分方程数值积分)
-       - [`custom/PaperFold.jsx``PaperFold.jsx` — 指数 / log scale 数据可视化
-       - [`custom/AlgorithmBubble.jsx``AlgorithmBubble.jsx` — 离散状态机 + 时间轴脚本编排
-     - 用 Remotion API: useCurrentFrame / useVideoConfig / interpolate / spring / useMemo
-
-4. **跑渲染**
-   ```
-node cli.js script.md out/video.mp4
-```
-```
-5. **检查输出**
-   - 看时长是否符合预期
-   - 看渲染日志有无错误
-   - 用 `open out/video.mp4` 让用户自己看
-```
-
-## 内置模板速查
-
-| 模板 | 关键参数 | 适用场景 |
-|---|---|---|
-| `Title` | `title, subtitle` | 章节开头 |
-| `ContentCard` | `title, items[], color` | 知识点列表 / 步骤拆解 |
-| `TwoColumn` | `title, left[], right[], callout` | 输入→输出对比 |
-| `Triangle` | `base, height, formula, result` | 三角形几何题 |
-| `BeforeAfter` | `title, before, after, unit, viz` | **数值/时长前后对比**(波形条 / 时间轴削减,动画) |
-| `Outro` | `title, cta` | 收尾 / CTA |
-
-`BeforeAfter` 的 `viz`:
-- `bars` — 两组波形条柱对比(适合数值类:音量、得分、占比)
-- `duration` — 横条对比 + 削掉的碎片飞出(适合时长类:剪辑前后、加载耗时)
-
-## Custom 模板生成原则
-
-- 每个 custom 文件 export 一个跟文件同名的 React component
-- 用 Remotion API 写动画(**不要**用 setTimeout / setInterval / requestAnimationFrame — Remotion 是逐帧渲染,所有状态都从 frame 推导)
-- 字号:标签 14, 正文 22, 标题 28-44, 大字 60+
-- 颜色:bg #0a0a0f, 主色 #6c5ce7 / #00cec9, 文字 #fff,辅助色 #fdcb6e #fd79a8 #e17055 #74b9ff
-- 出现节奏:先静(0-22f)再入场,避免一次全出
-- 复杂仿真用 `useMemo(() => simulate(...), [deps])` 一次预计算所有帧,逐帧索引 — 见 DoublePendulum.jsx
-- 离散状态机用"时间轴脚本"模式 — 在组件外预生成"每帧的 state 数组",逐帧索引 — 见 AlgorithmBubble.jsx
-- 数据可视化优先 SVG(轻、清晰、好控制),CSS 用于动效层
-
-## 选择策略 — 排版 vs 自定义
-
-**用内置排版(快、不卡):**
-- 知识点列表 / 步骤拆解 → ContentCard
-- 输入对输出 → TwoColumn
-- 数值/时长前后对比 → BeforeAfter
-- 几何题 → Triangle
-
-**写 custom(真生动):**
-- 物理过程(运动、振动、碰撞)→ 抄 DoublePendulum 范式
-- 时间线 / 量级对比(指数、对数)→ 抄 PaperFold 范式
-- 算法流程 / 状态变化 / 信息流→ 抄 AlgorithmBubble 范式
-- 化学反应、生物过程、电路、流程图、地图… → 必写 custom
-
-**关键判断**:如果你的内容会让观众想看"它怎么动的",就要 custom,内置排版做不出"动"的感觉。
-
-## 推荐用户动作
-
-# 1. 装 skill
-git clone https://github.com/znyupup/knowledge-explainer-skill
-cd knowledge-explainer-skill
-npm install
-
-# 2. 写文稿(或让 agent 写)
-vim examples/my_topic.md
-
-# 3. 跑 skill
-node cli.js examples/my_topic.md out/my_topic.mp4
-
-# 4. 看
-open out/my_topic.mp4
-
-## Source
-
-Rewritten for AICUT from [`znyupup/knowledge-explainer-skill`](https://github.com/znyupup/knowledge-explainer-skill)
-(MIT), SKILL.md. The method is that skill's own; the way it runs is AICUT's.

package/skills/knowledge-explainer-skill/examples/ai_video_3steps.md

@@ -1,61 +0,0 @@
----
-title: AI 自动剪 vlog · 3 个核心步骤
-fps: 30
-width: 1280
-height: 720
----
-
-## Title
-title: AI 怎么自动剪 vlog?
-subtitle: 3 个核心步骤,5 分钟讲明白
-duration: 4
-
-## ContentCard
-title: 自媒体的痛
-color: "#ff7675"
-items:
-  - 🎬 一条 vlog,剪 4 小时
-  - 🔍 时间轴密密麻麻找不到话头
-  - 🎵 配乐字幕来回试,没尽头
-  - 💡 能不能让 AI 全干?
-duration: 6
-
-## ContentCard
-title: 第一步 · 让 AI 看懂素材
-color: "#6c5ce7"
-items:
-  - 🎙 语音识别 — 每句话精确到秒
-  - 👁 视觉理解 — 画面拍的什么场景
-  - 🔊 音量检测 — 人声还是环境音
-  - 📝 输出一份文本报告,不用看视频
-duration: 7
-
-## TwoColumn
-title: 第二步 · LLM 编排叙事
-leftLabel: 素材报告
-rightLabel: 剪辑方案
-left:
-  - 23 条手机随手拍
-  - ASR + 视觉 + 音量
-  - 没有指定主题
-right:
-  - 自动推断「上海一天」
-  - 三幕式结构
-  - 修复 14 处语音截断
-callout: 不告诉它主题,它自己推断
-duration: 8
-
-## ContentCard
-title: 第三步 · 渲染 + 自然语言迭代
-color: "#00cec9"
-items:
-  - ⚙️ ffmpeg 自动裁剪 / 拼接 / 混 BGM
-  - 💬 "音乐大一点" → 秒改
-  - 💬 "做饭那段短一些" → 秒改
-  - 🚀 不用拖时间轴,不用重导
-duration: 7
-
-## Outro
-title: 一份 skill,把这 3 步全自动化
-cta: GitHub 搜 ai-video-editing-skill
-duration: 4

package/skills/knowledge-explainer-skill/examples/algorithm_bubble.md

@@ -1,20 +0,0 @@
----
-title: 抖音算法 1 分钟 · 信息茧房可视化
-fps: 30
-width: 1280
-height: 720
----
-
-## Title
-title: 信息茧房怎么炼成的
-subtitle: 你点的每一下,都在喂算法
-duration: 4
-
-## AlgorithmBubble
-caption: 算法在悄悄收敛你的世界
-duration: 18
-
-## Outro
-title: 看到的世界,是算法选给你的
-cta: 想破茧?偶尔点点不喜欢的
-duration: 4

package/skills/knowledge-explainer-skill/examples/before_after_demo.md

@@ -1,38 +0,0 @@
----
-title: BeforeAfter 模板演示
-fps: 30
-width: 1280
-height: 720
----
-
-## Title
-title: BeforeAfter · 对比可视化
-subtitle: 不止文字,直接画
-duration: 4
-
-## BeforeAfter
-title: 音乐声音大一点
-viz: bars
-before: 12
-after: 30
-unit: "%"
-beforeLabel: 调整前
-afterLabel: 调整后
-callout: 自然语言一句话,BGM 自动从 12% 抬到 30%
-duration: 6
-
-## BeforeAfter
-title: 做饭那段短一些
-viz: duration
-before: 15
-after: 8
-unit: s
-beforeLabel: 原长
-afterLabel: 现长
-callout: 自动削掉冗余,保留口令完整段
-duration: 6
-
-## Outro
-title: 文字 → 可视化
-cta: 这才是讲解动画该有的样子
-duration: 3

package/skills/knowledge-explainer-skill/examples/cta_outro.md

@@ -1,11 +0,0 @@
----
-title: CTA 收尾
-fps: 30
-width: 1280
-height: 720
----
-
-## Outro
-title: Skill 已开源
-cta: GitHub 搜 knowledge-explainer-skill · 点关注 · 下期见
-duration: 15

package/skills/knowledge-explainer-skill/examples/double_pendulum.md

@@ -1,20 +0,0 @@
----
-title: 双摆混沌 · 蝴蝶效应
-fps: 30
-width: 1280
-height: 720
----
-
-## Title
-title: 蝴蝶效应你能看见
-subtitle: 双摆混沌 · 12 秒一目了然
-duration: 4
-
-## DoublePendulum
-caption: 两个一模一样的双摆,初始角度只差 0.001°
-duration: 14
-
-## Outro
-title: 这就是混沌
-cta: 简单规则,无法预测
-duration: 4

package/skills/knowledge-explainer-skill/examples/paper_fold.md

@@ -1,20 +0,0 @@
----
-title: 一张纸对折 42 次到月球
-fps: 30
-width: 1280
-height: 720
----
-
-## Title
-title: 一张纸对折 42 次
-subtitle: 比月球还远
-duration: 4
-
-## PaperFold
-caption: 0.1 mm 的纸,每折一次厚度翻倍
-duration: 18
-
-## Outro
-title: 这就是指数增长
-cta: 翻倍 42 次 = 4 万亿倍
-duration: 4

package/skills/knowledge-explainer-skill/examples/script.md

@@ -1,40 +0,0 @@
----
-title: 三角形面积怎么算
-fps: 30
-width: 1280
-height: 720
----
-
-## Title
-title: 三角形面积怎么算?
-subtitle: 5 分钟讲明白
-duration: 4
-
-## ContentCard
-title: 已知什么
-color: "#6c5ce7"
-items:
-  - 📐 底边 = 10cm
-  - 📏 高 = 6cm
-  - 🧮 公式:面积 = 底 × 高 ÷ 2
-duration: 5
-
-## Triangle
-title: 套公式算一下
-base: 10
-height: 6
-unit: cm
-formula: 底 × 高 ÷ 2
-result: 30
-resultUnit: cm²
-duration: 9
-
-## CustomFunFact
-fact: 等腰直角三角形,两条腰相等
-hint: 把高画在中线上,两边对称
-duration: 4
-
-## Outro
-title: 一份文稿,出片
-cta: 安装 skill 试试
-duration: 4

package/skills/lanshu-create-ai-presenter-video/SKILL.md

@@ -1,253 +0,0 @@
----
-name: lanshu-create-ai-presenter-video
-description: "Lanshu Create AI Presenter Video: the method the original skill taught, run as an AICUT film — pages that draw any moment t, cut on tracks. Runs in AICUT: the film is film.html, a page per shot, drawn by `aicut look` and `aicut render`."
-license: MIT
-source: "cclank/lanshu-create-ai-presenter-video"
----
-
-# Lanshu Create AI Presenter Video
-
-## Running it in AICUT
-
-AICUT's film is `film.html`: it cuts pages, footage, pictures and sound together on tracks. A page is a web page that
-sets `window.film = { frame(t) }` and draws that moment — no framework, no build step, no composition object, no
-`registerRoot`. Five shots are five pages cut together, not one page that changes scene, so each shot stays trimmable
-and replaceable in Studio.
-
-```sh
-npx -y @autoaiai/aicut@latest          # the manual: the format and the commands, always current
-npx -y @autoaiai/aicut@latest open .   # make this folder a film and print Studio's address
-npx -y @autoaiai/aicut@latest look     # a contact sheet of the whole film, its sound, and a determinism check
-npx -y @autoaiai/aicut@latest look 4.5 # one frame, full size — look at the PNG, not at the code
-npx -y @autoaiai/aicut@latest render   # the MP4, beside film.html
-```
-
-Run the manual before the first film: it is authoritative for the format, and this skill is about the method above it.
-
-Where the words below name another program's part, it becomes this:
-
-| elsewhere | in AICUT |
-|---|---|
-| composition, timeline, project file | `film.html`; tracks and clips inside it |
-| a scene, a sequence, a slide | a page (`pages/<name>.html`) cut onto a track |
-| `useCurrentFrame()`, `interpolate()` | `frame(t)` — the picture depends only on `t`, never on state or `Date.now()` |
-| a still, a screengrab | `aicut look <t>` |
-| `render` / `build` / `export` | `aicut render` (the person can also export from Studio) |
-| a dev server, a preview window | `aicut open` and the Studio address it prints |
-
-Hard rules that hold whatever the method says: the picture depends only on `t`; every value in the person's prompt is
-binding; look at the frames `look` writes before saying a film is done.
-
-
-Produce a verified explainer video from minimal inputs — led by a digital human, or performed in one of twelve explainer styles. The final narration is the master clock for presenter motion, captions, graphics, cuts, and delivery duration.
-
-## Choose a route
-
-Every job takes one of two routes, recorded as `creative.route`. Infer it when the request is clear (cues below);
-otherwise ask once, with this table and the style gallery (`explainer/STYLES.md`; attach or link the images
-`explainer/gallery/nine-styles-kv-cache.jpg` and `explainer/gallery/three-narrative-styles-kv-cache.jpg`). Never fall back to `presenter` silently: it needs a portrait the user
-may not have.
-
-| Route | The video | The user provides | Paid generation | Format |
-|---|---|---|---|---|
-| `presenter` | A digital human presents; captions and keyword graphics support it | Topic or script + authorized presenter image | Voice + presenter video | Any; 9:16 by default |
-| `styled` | A performed explainer: every narrated phrase is acted out on screen in one of twelve styles (nine visual, three narrative), no presenter | Topic or script | Voice only | 16:9 |
-
-- A presenter image or the words 数字人 / presenter / 口播 / 真人出镜 point to `presenter`; 不要真人 / "no presenter" /
-  "faceless", a named style, or 动画讲解 / 手绘 / 黑板 / 黏土 / 漫画 / 推导 / 复盘 / 小剧场 point to `styled`.
-- A vertical platform (抖音 / 视频号 / 小红书 / 竖屏 / 9:16) is a format request, not a route: `styled` is 16:9 only.
-  If it comes with no portrait or with styled cues, ask (a 16:9 styled film vs a 9:16 presenter video) instead of
-  switching routes.
-- Narration the user already recorded is the locked audio on either route. Never pass it as `--voice-sample` (that
-  flag is for voice cloning). On `styled` use `story.py story --audio <file>` and ask for the matching script text
-  (or transcribe it and have the user check it).
-- To re-style an earlier job, keep its script and locked audio (no new voice cost), build a new film from the same
-  `story.json` in the new style, and re-approve the storyboard. Ask which job when it is not obvious.
-- This skill makes explainers. For 宣传片 / 广告 / 发布大片 / footage edits, say so, and offer a product explainer only
-  if the user wants one.
-- For `styled` also choose `creative.explainer_style` (`v1-editorial` … `v12-sitcom`). Recommend two or three from the
-  topic and audience (one reason each) using `explainer/STYLES.md`; when the user is unsure, build drafts in the nine
-  visual styles (no extra paid calls once the audio is locked, or with `--dry`) and let them pick from a still grid.
-  Settle the style before the script is locked: each style shapes how the narration is written and voiced
-  (`explainer/STYLES.md`, "按风格写稿"). The three narrative styles (`v10-reasoning` 推演, `v11-casefile` 案卷,
-  `v12-sitcom` 小剧场) go further: use the style's suggested arc when it helps the explanation, adapting chapters and
-  order to the topic. The examples are starting points; keep room for other storytelling choices. To compare
-  styles first, use `--dry` drafts of a first script, then adapt it to the chosen style.
-- `styled` follows [styled-explainer.md](references/styled-explainer.md) and reuses this skill's job directory, state
-  machine, approvals, and delivery checks. The styles are designed to carry the explanation on their own; if a user
-  also wants their digital human in a styled film, that file describes the method (time the film to the presenter's
-  locked narration, give the presenter its own space) as an optional addition, not a separate route.
-
-How to ask, when the request leaves the choice open — one message, in the user's language:
-
-1. The two routes, one line each: what the video looks like, what the user must provide, what is paid, and the
-   format (presenter: any ratio, 9:16 by default; styled: 16:9 only). Recommend one for this topic and say why (e.g. "no portrait yet, or a concept that needs to be shown → styled"; "personal brand,
-   talking to camera → presenter").
-2. For `styled`, assume the user does not know the styles yet: show the whole menu — the two gallery images plus the
-   twelve one-line entries of "风格菜单" in `explainer/STYLES.md` — and mark the two or three that fit this topic and
-   audience, one reason each. Offer "build drafts in the nine visual styles and pick from a still grid" as the
-   alternative. Do the same, without the route table, when the user only asks which styles there are.
-3. Proceed with the recommendation if the user agrees or does not mind; record the choice in `job.json`.
-
-## Required outcome
-
-- Start from a topic or script and, for the presenter route, one authorized image containing one clear adult presenter.
-- Deliver a fully decoded master video, a smaller share copy, captions, production records, and separate machine and visual QA notes.
-- Keep the workflow portable across providers, models, aspect ratios, languages, and durations.
-
-## Operating rules
-
-- Confirm image rights, adult status, remote-upload approval, and voice-cloning authorization before the relevant remote action.
-- Treat remote generation as potentially billable. Before the first paid call, state the uploaded assets, requested seconds or units, known cost, pilot size, retry ceiling, and expected output. Reuse an approval already given for that exact plan.
-- Never infer a real voice from an image. Use an authorized sample or record a selected stock voice.
-- Lock the complete narration before presenter generation, caption timing, or final scene boundaries.
-- Prefer one presenter image, one voice identity, one visual treatment, and one continuous presenter source.
-- Mute video sources in the final composition. Route only the approved external narration and intentional mix tracks.
-- Preserve provider request bodies and task IDs without credentials or expiring URLs. Poll interrupted work before considering resubmission.
-- Use numeric checks for technical faults and normal-speed visual review for identity, mouth timing, blinking, gestures, hands, lighting, and continuity.
-- Stop after three rejected paid candidates, or before a change that materially affects cost, privacy, voice, appearance, or provider.
-- Do not claim completion until the final files fully decode, the contact sheet or full playback has been reviewed, and `check_state.py` reports `verified`.
-
-## Start or resume a job
-
-For a new job, read [generation.md](references/generation.md). Set `SKILL_DIR` to the directory that contains this file; its location depends on the harness. Then run:
-
-```bash
-SKILL_DIR=/path/to/lanshu-create-ai-presenter-video
-
-python3 "$SKILL_DIR/scripts/init_job.py" \
-  --job-dir ~/Videos/my-presenter-video \
-  --presenter-image ~/Pictures/presenter.png \
-  --topic "用一分钟讲清楚上下文工程"
-```
-```
-For the styled route add `--route styled --explainer-style v3-notebook` (no presenter image needed).
-
-Use `--script` for an existing script file. Optional flags include `--voice-sample`, `--supporting-media`, `--duration`, `--aspect`, `--width`, `--height`, `--fps`, `--watermark`, and `--cta`. The initializer copies every input into the job and records job-relative paths, so the job directory is self-contained; keep later artifact paths job-relative too.
-
-Inspect the actual source image and listen to any voice sample. Record the manual review and approvals in `job.json`, then run:
-```
-```bash
-python3 "$SKILL_DIR/scripts/preflight.py" ~/Videos/my-presenter-video/job.json
-```
-```
-For an existing job, read `job.json`, current artifacts, task IDs, and QA reports, then run `check_state.py` (below) to find the earliest unfinished state. Resume there without regenerating accepted work.
-```
-
-## Production state machine
-
-Advance a job only when its evidence exists:
-
-```text
-intake
-→ content_locked       passing preflight report, script, beat sheet
-→ audio_locked         decodable final audio, ASR report
-→ visual_plan_locked   timeline, storyboard, plan.status "approved"
-→ presenter_generated  recorded main_presenter capability, selected video, visual review
-→ composition_checked  composition report
-→ rendered             decodable render with video and audio
-→ verified             master, share, delivery report with passing output loudness
-```
-On the `styled` route there is no presenter: `presenter_generated` is reached by the performed film instead
-(`artifacts.story`, `artifacts.film_project`, and the visual review).
-
-Never edit `state` by hand. Record artifacts in `job.json`, then let the checker compute the state:
-```
-```bash
-python3 "$SKILL_DIR/scripts/check_state.py" ~/Videos/my-presenter-video/job.json --write
-```
-```
-Without `--write` it only reports. It exits non-zero when the recorded state claims more than the evidence supports, and lists what the next state is missing.
-```
-
-### 1. Lock content and audio
-
-Read [generation.md](references/generation.md).
-
-1. Turn a topic into one spoken content spine, or polish a supplied script without changing factual meaning silently.
-2. Save the production script, beat sheet, pronunciations, and narration sections.
-3. Generate the complete approved narration with one voice configuration.
-4. Normalize sections consistently, run ASR on the final audio, and correct material omissions, additions, numbers, names, or repeated speech.
-5. Record real durations. These durations now define the timeline.
-
-### 2. Plan and generate the presenter
-
-Choose a presenter-led, screen-demo, or mixed-explainer route. Use supporting media only when it proves or clarifies a spoken point.
-
-When the provider caps request or reference-audio duration below the narration length, plan the split from the locked audio's ASR timings instead of guessing:
-
-```bash
-python3 "$SKILL_DIR/scripts/plan_segments.py" \
-  --timings ~/Videos/my-presenter-video/qa/asr/sentences.json \
-  --audio ~/Videos/my-presenter-video/assets/audio/final/narration.wav \
-  --cap 15 --whole-seconds \
-  --output ~/Videos/my-presenter-video/qa/requests/segment-plan.json
-```
-```
-Save the plan path in `plan.segment_plan`. Generate every segment from the same image, seed, framing, light, and motion constraints.
-
-Generate a short, low-cost pilot before a full run. Prioritize identity and mouth timing for the main track. Use one controlled gesture for an actionful opening or close. When body motion is accepted but mouth timing fails, preserve the motion plate and apply a dedicated lip-sync repair with the locked audio.
-
-Archive the prompt, parameters, provider/model/version, region, task ID, requested seconds, and acceptance notes.
-```
-
-### 3. Edit the video
-
-Read [editing.md](references/editing.md).
-
-Build a deterministic timeline driven by the locked audio. Keep authored start, duration, and source offset independent. Add captions and keyword callouts only after audio and selected media are final.
-
-When using HyperFrames, load the current `hyperframes`, `general-video`, and relevant domain instructions. Run the project check, inspect transition and emphasis frames, open the Studio preview, and wait for final visual approval before rendering.
-
-### 4. Verify and deliver
-
-Read [qa-recovery.md](references/qa-recovery.md).
-
-Render at delivery quality, watch the complete video, and finalize it:
-
-```bash
-bash "$SKILL_DIR/scripts/finalize_delivery.sh" \
-  ~/Videos/my-presenter-video/renders/rendered.mp4 \
-  ~/Videos/my-presenter-video/outputs \
-  my-video
-```
-```
-The finalizer preserves the input aspect ratio, performs two-pass program loudness normalization, creates master/share encodes, fully decodes them, measures their delivered loudness, counts black and frozen-picture events, and produces a nine-frame contact sheet. It builds everything in a temporary directory and publishes nothing unless every check passes. The target defaults to `-16 LUFS`; set `PROGRAM_LUFS` (for example `PROGRAM_LUFS=-14`) when the destination requires another.
-
-Inspect the contact sheet, review any freeze events against intentional still shots, record the outputs and delivery report in `job.json`, and run `check_state.py --write` to reach `verified`.
-```
-
-## Default behavior for minimal input
-
-- Infer language from the request.
-- On the presenter route, use 9:16, 1080×1920, 30fps unless the intended platform suggests another format. The styled route is always 16:9, 1920×1080, 30fps.
-- Preserve a supplied script's natural duration; for a topic, target 45–75 seconds.
-- Use a suitable stock voice when no authorized voice sample exists.
-- On the presenter route, use a presenter-led layout with a designed hook, 2–4 useful beats, and a concise close; on the styled route, the style's starter sets the layout.
-- Omit music and promotional CTA unless requested or clearly justified.
-- Keep styling credible, contemporary, readable, and safe for the destination platform.
-
-## Required job artifacts
-
-```text
-job.json
-docs/{SCRIPT,BEAT_SHEET,TIMELINE,STORYBOARD}.md
-assets/source/
-assets/audio/{reference,raw,final}/
-assets/video/{candidates,selected,render}/
-assets/captions/
-qa/{requests,asr,contacts,reports}/
-renders/
-outputs/
-
-## Reference routing
-
-- Read [styled-explainer.md](references/styled-explainer.md) whenever `creative.route` is `styled`; it maps every state above onto the explainer tools in `explainer/`. Choose styles with `explainer/STYLES.md`.
-- Read [generation.md](references/generation.md) for intake, content, voice, tool selection, presenter prompts, paid generation, or provider changes.
-- Read [editing.md](references/editing.md) for timeline construction, screen-demo layouts, openings, closes, captions, keyword callouts, previews, and exports.
-- Read [qa-recovery.md](references/qa-recovery.md) before accepting media or delivery, and whenever lip sync, identity, hands, exposure, freezes, captions, audio, or remote jobs fail.
-
-## Source
-
-Rewritten for AICUT from [`cclank/lanshu-create-ai-presenter-video`](https://github.com/cclank/lanshu-create-ai-presenter-video)
-(MIT), SKILL.md. The method is that skill's own; the way it runs is AICUT's.