@autoaiai/aicut 0.1.11 → 0.1.13

package/skills/laoxu-video-script/references/persona.md

@@ -1,38 +0,0 @@
-# 第 1 课 · 定位你自己的账号
-
-起号第一步不是拍视频，是想清楚**你这个号凭什么让人记住、让人信**。人设不是演的，是**定位**——把"你本来就是谁"提纯成一句话。
-
-## 人设三问（学员先填这个，再谈内容）
-
-1. **你是谁？** —— 你的真实身份 / 经历 / 手艺里，最有差异化的那一个标签。（不是"热爱生活的女孩"，是"做过 8 年供应链、现在一个人做跨境的老板"。）
-2. **给谁看？** —— 具体到一类人和他们的一个痛点。观众越具体，内容越有劲。
-3. **凭什么信你？** —— 你能拿出什么别人拿不出的**证据/视角/现场**？（一线经历、真金白银的踩坑、独家数据、反共识的判断。）
-
-**一个好人设的判据**：具体（不是形容词）、有立场（敢下判断）、可持续（能日更三年不塌）、有记忆点（一句话能被观众复述给别人）。四条缺一条，回去改。
-
-## 范例：老徐是怎么填的（学这个"填法"，不是抄这个"内容"）
-
-- **你是谁**：一人公司实践者 + 投资人视角 + 前大厂打工人（三合一，这三个标签互相加成，别人难复制）。
-- **给谁看**：想用 AI 一个人干成事的普通人（他管观众叫「精神股东」）。
-- **凭什么信**：真的在一个人 + AI 地干、真做过投资会用框架拆问题、真从大厂出来但不消费前东家。
-- **固定资产**（每个成熟的号都该有几件，观众靠它认出你）：
-  - 观众称呼：「精神股东」
-  - 口头禅：「去动手，去动手」
-  - 签名收尾：「命由己造，事在人为。神机妙算，不如自己说了算。我是老徐，中年辍班，All in AI 的一人公司创业者。」
-  - 招牌手法：「说句公道话」、替观众喊问题（"肯定有人要说"）、把个人经历放片尾做自我代入。
-
-**固定资产是衣柜，不是制服**：观众称呼可以常用；**口头禅和签名收尾只在合身的特定内容用**——老徐的签名挂着命理产品梗，只配特定期；「去动手」拢共没用过几次。次次都戴＝人设变模板，一眼假。写稿别默认往结尾贴签名。
-
-## 学员工作表（填完再进第 2 课）
-
-```
-我是谁（一个差异化标签）：__________
-给谁看（一类人 + 一个痛点）：__________
-凭什么信我（我的独家证据/视角）：__________
-我的观众我想叫他们：__________
-我的口头禅/固定收尾（设计一句你自己的）：__________
-我绝不碰的红线（例：不消费旧东家、不编数据）：__________
-```
-
-## 红线：造你自己的，别套老徐的
-老徐的「双机党/精神股东/命由己造」是**他的**固定资产，套过来你就成了低配模仿号。你要用同样的"三问 + 固定资产"方法，长出**属于你的**那套。人设可以有缺点、可以不完美，但必须**是你**、且**一贯**——信任是复利，装出来的完美是负债。

package/skills/laoxu-video-script/references/qihao-path.md

@@ -1,35 +0,0 @@
-# 第 6 课 · 起号运营（把一篇稿，变成一个号）
-
-会写单篇 ≠ 会做号。这一课把方法接到"经营"：发在哪、按什么节奏发、怎么冷启动、怎么把看的人变成自己的人。
-
-## 一、平台分工：别四处平均用力
-四个平台性格不同，按**角色**用，一主一辅起步：
-- **抖音 = 放大器**：公域最大，练钩子、测选题、抓新客。算法分发，粉丝≠触达。
-- **小红书 = 资产库**：65% 流量来自搜索，发**能被搜到的干货**，吃长尾——今天的内容半年后还在带客。
-- **B 站 = 信任场**：粉丝真的回来看更新，一条深度顶十条碎片。
-- **视频号 = 枢纽**：连着微信，是把公域观众**接进你私域**的那扇门。
-
-## 二、冷启动：前 20 条怎么发
-- **开局前三篇是重头戏**，单独打一套组合拳（你是谁 / 大便宜 / 活人）——见 `references/qihao-xinfa.md`「起号前三篇」。
-- **别追爆款，先立"人设+选题范围"**：前 20 条让人一眼看出"这号是干嘛的、这人是谁"。
-- **同一个母题，多个角度打**：用第 2 课的母题库，一个框架拆不同热点，观众重复看见=记住你。
-- **完播 > 涨粉**：新号先把单条做到"看完"，算法才给你下一波（各平台都在奖励留存，不只涨粉）。
-- **固定资产尽早上**：称呼、口头禅、签名从第一条就用，攒辨识度。
-
-## 三、内容节奏
-- 稳定 > 爆发。定一个你能扛三年的频率（哪怕周更）。
-- 选题配比参考：**7 分"能被搜到/能带走框架"的干货 + 3 分蹭热点**。热点是获客成本，干货是固定资产。
-
-## 四、留量漏斗：把流量变成"你的人"
-```
-公域（被看见：抖音/小红书） → 私域（被记住：微信/社群/视频号） → 产品（收钱：课程/服务/自己的东西）
-```
-- **别只攒粉丝（粉丝是平台的），要往私域沉**——那是算法动不了的自留地。
-- 变现结构立个目标：**广告收入 ≤ 1/3**，其余来自你自己的产品/服务。广告是别人的预算，产品才是你的生意。
-
-## 五、迭代：像老徐定稿那样运营
-- 每条内容发完做一次**第 4 课的诊断复盘**（尤其钩子和 AI 味）。
-- 数据不好别慌，先问是哪一维塌了：选题？开头？逻辑？还是根本没记忆点？——对症改，别整条推倒。
-
-## 一句话给学员
-**以前拼谁被更多人看见，以后拼谁被同一群人反复相信。** 起号不是赌一条爆款，是用这套方法，把"你是谁、你对谁有用"这件事，一条一条讲清楚、讲到别人信。

package/skills/laoxu-video-script/references/qihao-xinfa.md

@@ -1,39 +0,0 @@
-# 第 0 课 · 底层心法：为什么有人关注你，并留下来
-
-前面几课是「术」（破立合、格式、诊断），这一篇是「道」。带学员**从这一课开讲**——不先想明白"人凭什么关注你、凭什么留下来"，招式练得再溜也是空的。
-
-## 一条内容的三个动作：勾 → 留 → 关注
-任何一条内容，都要连过三关，缺一关前功尽弃：
-- **勾（3 秒进得来）**：刷到的人凭什么不划走？开头给反差、痛点、或"替身钩子"。→ 对应诊断 **D2 开场钩子**。
-- **留（看得完）**：中间凭什么不走？一层层给、留悬念、别啰嗦、别注水。→ 对应 **D3/D5**。
-- **关注（留得下）**：看完凭什么点关注？因为他**占到便宜**了，还感觉你是个**值得追的活人**。
-> 勾不住＝0 播放；留不住＝完播低、算法不给量；关注不了＝白涨一波过路流量。三关是递进的。
-
-## 让人占便宜：你到底能分享什么？
-起号的底层交换：**观众用注意力，换你的价值——让他每次都觉得"赚了"。**
-- 先问自己一句狠的：**凭什么是你？** 你有什么别人给不了的：一线现场、真金白银的踩坑、独家数据、反共识的判断、一个能立刻上手的方法？
-- "占便宜"的三种给法：**学到**（干货/方法）、**爽到**（情绪/共鸣/替身）、**省到**（帮他避坑、帮他做决定）。一条至少占一样。
-- 宁可一条**把一个小点讲透**，让人惊"这也白给？"，也别一条泛泛而谈、留下"又是正确的废话"。
-- 铁律——**别舍不得**。新号最怕藏着掖着；把压箱底的先给出去，信任才起得来。
-
-## 为什么关注"你这个人"：替身感 + 成长感
-涨粉分两种：粉「内容」的会流失，粉「你这个人」的才留得住。让人粉你，靠两种感觉：
-- **替身感**：你替观众**活了他想活的人生 / 做了他不敢做的事 / 试了他想试的东西**。"看你，就好像我也做了。"（老徐的"一个人 + AI 把公司干起来"，就是一群想单干的人的替身。）→ 想清楚：**你在替谁活着？**
-- **成长感**：让观众跟你**一起打怪升级**——你在变强、在踩坑、在往前走，他追的是这部"连续剧"。别一上来就"我是大神"，要"我们一起"。→ 敢不敢把**没做成的、正在做的**也摆出来？
-
-## 活人感：你的真实感受，就是护城河
-现在最贵的不是完美，是**活人**。满屏 AI 生成的完美内容里，一个有感受、有缺点、有具体现场的真人，天然稀缺。
-- **有感受**：讲事之外讲**你的感受**——你为什么生气 / 兴奋 / 犹豫。观众记不住信息，记得住情绪。
-- **有缺点**：忍住没买 M5 Max、"连诗都不怎么写了"——不完美才可信。
-- **有现场**：具体到你今天用哪台机器、学员在 Windows 上怎么翻的车。抽象让人走神，具体让人相信。
-> 这就是诊断 **D4 AI 味扫描**的正面版：目标不是"去掉 AI 味"，是"**加上活人味**"。
-
-## 起号前三篇（把心法落成开局三步）
-新号前三篇不是随手发，是一套组合拳，把"勾 / 占便宜 / 活人"各打一发，把账号雏形立住：
-- **第一篇 · 你是谁（勾 + 替身感）**：一句话说清你是谁、能给谁什么、凭什么是你，抛一个"我也想成为这样"的替身钩子。让人三秒决定要不要关注。
-- **第二篇 · 大便宜（占便宜 + 建立"关注你不亏"）**：给一个具体到"这也免费？"的干货/方法，让第一篇勾来的人**立刻尝到甜头**——把"关注你＝占便宜"这个印象砸实。
-- **第三篇 · 活人（留 + 成长感）**：露一次真实的你——一个感受、一段踩坑、一个正在打的怪。把"账号"升级成"人"，让人从"这内容有用"变成"这人我得追"。
-> 三篇打完，一个「有用 + 是个真人 + 我想成为」的账号就立住了。之后就是用这套心法持续供货。
-
----
-**心法接回六课**：勾＝D2，留＝D3/D5，占便宜＝选题（第 2 课）得让人带走东西，替身感/成长感＝定位（第 1 课），活人感＝AI 味扫描（D4）的正面。**心法是"为什么"，六课是"怎么做"。**

package/skills/laoxu-video-script/references/redlines.md

@@ -1,26 +0,0 @@
-# 立场与合规红线（带学员时先讲这个，帮他们躲开会翻车的坑）
-
-## 1 · 批判结构，不批判个人
-评论一件事，**唯一能批的是叙事/结构/机制，不是新闻当事人**。骂具体的人＝流量快但会翻车、会被起诉、会掉格。把"某某坏"改写成"那个位置在筛选人"。（老徐钉钉那期：全片唯一批判的是"非黑即白的叙事本身"，不碰马总个人。）
-
-## 2 · 对称分析：给另一方留一个位置
-冲突双方都做**对称**分析，不裁决谁对谁错。至少有一处主动"说句公道话"替被骂的一方讲道理。这不是和稀泥——**是把你和站队式流量号拉开差距的地方**，也是可信度的来源。
-
-## 3 · 落点回到观众和趋势
-再犀利的分析，收尾要落回**观众自己**和**行业趋势**，不是停在骂谁爽。给观众一个能带走、能用在自己身上的东西。
-
-## 4 · 不消费旧关系（谈自己/前东家时）
-- 不公开批评前东家/前领导。要谦逊、平视，别立牌坊。
-- 用"普通人、觉得没必要、在职说比离职写有用"这种口吻，**别用"我给自己定了一条原则"式的宣言**（太把自己当回事）。
-- 认知可以分享，旧关系不拿来消费。
-
-## 5 · 数字口径要标注（做数据类内容必守）
-- 引用数字忠实原文口径：ARR 和单月收入不能混；"约/据报道"等修饰要保留。
-- **二手解读 ≠ 官方精确数字**。行业拆解里流传的权重/公式，口播时说"行业拆解里""大概量级"，别说成"官方公布是 X%"。
-- 拿不准的数字，宁可用模糊口径（"六七个亿"），也别编一个精确假数——精确假数是最容易被打脸的。
-
-## 6 · 不立牌坊、不卖惨
-个人坦白段是"坦白不是表态"。可以自嘲，不卖惨、不喊口号、不显得高尚。观众信的是真实，不是完美。
-
----
-**一句话给学员**：流量有很多种赚法，但**会翻车的流量不要赚**。这六条不是道德洁癖，是让你能做长、做久、不被一条视频毁掉的护栏。

package/skills/lemo-opuscar/SKILL.md

@@ -1,67 +0,0 @@
----
-name: lemo-opuscar
-description: "Direct and produce a short film made entirely in code, in one of the styles of the Lemo-Opuscar library (e.g. Impasto Oil Painting 油画厚涂, Watercolor Brush 水彩笔刷, Ukiyo-e 浮世绘, Satellite Briefing 卫星简报, Exploded Teardown 产品拆解). Use when the user asks for a video, film, short, promo, explainer or animation (视频、短片、动画、宣传片) in a named style, including explainers built from real material such as satellite imagery, laser scans, CAD files or archive scans (数据解说、科普、产品拆解), and new films cut from real archive footage and documents (剪辑与纪实, e.g. 用档案影像剪一支新闻片); when they want a film about their own topic and haven't chosen a style (help them choose); when they want to change a style into their own, make their own style from a blank page, or use a style they saved (改风格、从空白开始、我的风格); when they start the skill without saying what they want; or when they ask which film styles there are. Runs in AICUT: the film is film.html, a page per shot, drawn by `aicut look` and `aicut render`."
-license: MIT
-source: "lemomo-ai/lemo-opuscar"
----
-
-# Lemo-Opuscar
-
-## 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.
-
-
-The styles, guides and tools ship with this plugin, in `library/` next to this file. Nothing is downloaded to tell you what to do.
-
-1. **Get the library ready.** Run `sh "<skill base directory>/scripts/setup.sh"`. It copies the bundled library to its working folder (default `~/.lemo-opuscar`, so installed packages survive plugin updates) and prints `LIB=<path>` on its last line.
-2. **Install the core tools early.** Start `sh "<skill base directory>/scripts/setup.sh" deps` right away, in the background if you can: it takes a few minutes the first time. Add `deps voice` or `deps music` later, only if the film needs them (`$LIB/TECHNIQUE.md` §1). Report missing system tools (Node, ffmpeg, Python) in your one round of questions; don't install system software yourself. Packages a style needs (its `STYLE.md` lists them) you install yourself, into the project folder.
-3. **Follow the library.** Read `$LIB/AGENTS.md` and do what it says, starting with **Start** (the user's own styles in `~/lemo-my-styles/`; when they started the skill without writing anything, the language question first, then the ways in): finding the style or making their own, the one round of questions, the treatment, production and delivery.
-
-What changes in skill mode:
-
-| | |
-|---|---|
-| Project folder | `<name>/` in the folder the user started from (lowercase letters, digits, hyphens; avoid `#` and `?` in the path). Wherever the guides say `films/<name>/`, read this folder |
-| Running tools | from `$LIB`, with the project's absolute path: `cd "$LIB" && node core/render/still.mjs "<project>" 1.5 3`. `sh tools/setup.sh` and `sh tools/fetch.sh` also run from `$LIB` |
-| Library files in pages | absolute URLs: `/core/lib.js`, `/node_modules/three/…` (the project is served at `/@film/`) |
-| Library files in scripts and `build.sh` | `$LIB/…`, with `LIB=<path>` at the top of `build.sh`; never `../..` |
-| Demo films | not in this edition: no `demo/` source and no `poster.jpg`. Each style's `DEMO.md` (how its demo was made) is there; read it only after your `TREATMENT.md` is written, as the guides say. An Edit & Documentary style needs its material before the treatment: find and log it yourself, as its `STYLE.md` describes (the `demo/tools/` it names aren't in this edition). The films are on the gallery, https://lemomo-ai.github.io/lemo-opuscar/, if the user wants to watch one |
-| Chinese narration | Kokoro's Chinese voices (offline) by default. edge-tts (`core/tts/tts_zh.py`) sounds better but sends the narration text to Microsoft's speech service: offer it in your one round of questions and use it only if the user agrees |
-| Big downloads | only what the film needs, from the sources `$LIB/TECHNIQUE.md` §1 lists (npm, PyPI, Playwright's browser, this library's GitHub Releases, Hugging Face for the speech check). Name them in your one round of questions the first time |
-
-Deliver what `$LIB/DIRECTOR.md` §11 lists, in the project folder, and tell the user where it is.
-
-## Source
-
-Rewritten for AICUT from [`lemomo-ai/lemo-opuscar`](https://github.com/lemomo-ai/lemo-opuscar)
-(MIT), tools/directory/SKILL.md. The method is that skill's own; the way it runs is AICUT's.
-
-The repository holds 2 skills; this is the one its entry stands for.

package/skills/lipnardo/SKILL.md

@@ -1,308 +0,0 @@
----
-name: lipnardo
-description: "Lipnardo -- HeyGen Avatar Video Production Director: 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: "AgriciDaniel/lipnardo"
----
-
-# Lipnardo -- HeyGen Avatar Video Production Director
-
-## 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.
-
-
-## Core Principle
-
-Act as a **Video Production Director** that orchestrates HeyGen's avatar video API.
-Analyze the user's intent, select the right generation mode, estimate costs before
-generating, and manage the full video lifecycle from creation through download.
-
-## Mandatory Pre-reads
-
-Before ANY video generation, you MUST read these references:
-1. `references/heygen-api-reference.md` -- endpoint details and request/response schemas
-2. `references/credit-costs.md` -- pricing table and cost estimation formulas
-
-## Quick Reference
-
-| Command | What it does |
-|---------|-------------|
-| `/lipnardo` | Interactive -- detect intent, select mode, generate |
-| `/lipnardo generate <prompt>` | Generate video with AI Video Agent (v3) |
-| `/lipnardo studio <config.json>` | Multi-scene video with Studio API (v2) |
-| `/lipnardo batch <file.csv>` | Batch generate from CSV/JSON data |
-| `/lipnardo template list` | List available HeyGen templates |
-| `/lipnardo template inspect <id>` | Show template scenes and variables |
-| `/lipnardo template generate <id>` | Generate from template with variable injection |
-| `/lipnardo translate <video_id> <lang>` | Translate video with lip-sync |
-| `/lipnardo tts <text>` | Generate TTS audio via Starfish engine |
-| `/lipnardo avatar create <photo>` | Create avatar from photo (full pipeline) |
-| `/lipnardo avatar list` | List available avatars |
-| `/lipnardo avatar voices` | List available voices |
-| `/lipnardo assets upload <file>` | Upload asset to HeyGen |
-| `/lipnardo assets list` | List uploaded assets |
-| `/lipnardo credits` | Check API balance |
-| `/lipnardo credits estimate` | Estimate cost before generation |
-| `/lipnardo download <video_id>` | Download video before URL expires |
-| `/lipnardo setup` | Validate API key and configuration |
-| `/lipnardo webhook register <url>` | Register webhook endpoint |
-
-## Setup and Authentication
-
-First-time users must validate their setup:
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/validate_setup.py
-```
-```
-API key resolution order (highest priority first):
-1. `--api-key` flag on any script (explicit override)
-2. `HEYGEN_API_KEY` environment variable (recommended)
-3. `~/.heygen/config.json` file with `{"api_key": "your-key"}`
-
-Get your key from: https://app.heygen.com/settings/api
-```
-
-## Generation Pipeline
-
-Follow this pipeline for every video generation:
-
-### Step 1: Analyze Intent
-
-Determine what the user needs:
-- **Simple prompt** → Video Agent mode (AI selects avatar, writes script)
-- **Specific avatar/scenes** → Studio mode (precise multi-scene control)
-- **Mass personalization** → Template or Batch mode
-- **Existing video** → Translation or download
-
-If the request is vague, ask about: use case, avatar preference, duration, aspect ratio.
-
-### Step 2: Estimate Cost
-
-ALWAYS estimate before generating:
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/credit_check.py estimate --feature video_agent --duration 60
-```
-```
-Show the user the estimated cost and confirm before proceeding.
-```
-
-### Step 3: Generate
-
-**Video Agent mode** (AI-driven, simple prompt):
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/generate_video.py --mode agent \
-  --prompt "A professional woman explaining quarterly results" \
-  --aspect-ratio 16:9
-```
-```
-**Studio mode** (multi-scene, precise control):
-```
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/generate_video.py --mode studio \
-  --config /path/to/scenes.json
-```
-```
-Studio scene config format:
-```
-```json
-{
-  "video_inputs": [
-    {
-      "character": {"type": "avatar", "avatar_id": "...", "avatar_style": "normal"},
-      "voice": {"type": "text", "input_text": "Script here", "voice_id": "..."},
-      "background": {"type": "color", "value": "#ffffff"}
-    }
-  ]
-}
-
-### Step 4: Poll and Download
-
-Scripts handle polling automatically with exponential backoff (10s → 60s, 30-minute ceiling).
-Videos download to `~/Documents/lipnardo_videos/` by default.
-
-### Step 5: Log Cost
-
-After successful generation, log the cost:
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/credit_check.py log \
-  --feature video_agent --duration DURATION --video-id VIDEO_ID --prompt "summary"
-```
-
-### Step 6: Report to User
-
-Show: file path, duration, file size, estimated cost, and video_id (for later translation/download).
-
-## Batch Pipeline
-
-For generating multiple personalized videos from CSV or JSON:
-
-1. **Estimate total cost first:**
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/credit_check.py estimate-batch \
-  --input data.csv --feature avatar3 --avg-duration 60
-```
-```
-2. **Confirm with user** before proceeding.
-
-3. **Run batch:**
-```
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/batch_generate.py --input data.csv --mode agent
-```
-```
-4. **Monitor progress** -- the script outputs JSON progress to stderr.
-
-5. **Resume interrupted batches:**
-```
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/batch_generate.py --resume manifest.json
-```
-```
-CSV format for agent mode: columns `prompt` (required), `avatar_id`, `voice_id`, `name` (optional).
-CSV format for template mode: columns match template variable names.
-```
-
-## Template Pipeline
-
-For template-based mass personalization:
-
-1. **List templates:** `template_video.py list`
-2. **Inspect variables:** `template_video.py inspect --template-id ID`
-3. **Generate with variables:**
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/template_video.py generate \
-  --template-id ID --variables '{"name":"John","company":"Acme"}'
-```
-```
-4. **Batch from CSV:**
-```
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/template_video.py generate \
-  --template-id ID --input prospects.csv
-```
-
-## Photo Avatar Pipeline
-
-Full pipeline from photo to talking-head video:
-
-1. **Create avatar from photo:**
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/photo_avatar.py create \
-  --photo /path/to/headshot.jpg --name "My Avatar"
-```
-```
-2. Training takes minutes to hours -- script waits automatically.
-3. **Generate video with trained avatar:**
-```
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/photo_avatar.py generate \
-  --avatar-id AVATAR_ID --script "Hello, welcome to our company!"
-```
-```
-Photo requirements: front-facing, 512x512 min, even lighting, mouth closed.
-Photo Avatar IV costs $0.05/sec with a 3-minute max. Read `references/avatar-types.md`.
-```
-
-## Translation Pipeline
-
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/translate_video.py \
-  --video-id VIDEO_ID --target-lang es --mode fast
-```
-```
-- **Fast/speed mode**: speed-optimized via v3 API, $0.0333/sec
-- **Quality/precision mode**: precision lip-sync via v3 API, $0.0667/sec
-- 175+ languages supported
-```
-
-## TTS Pipeline
-
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/tts.py synthesize \
-  --text "Hello world" --voice-id en-US-JennyNeural
-python3 ${CLAUDE_SKILL_DIR}/scripts/tts.py list-voices --language en
-```
-
-## Asset Management
-
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/asset_manager.py upload --file image.png
-python3 ${CLAUDE_SKILL_DIR}/scripts/asset_manager.py list --type image
-```
-
-## Error Handling
-
-| Error | Cause | Action |
-|-------|-------|--------|
-| 401 Unauthorized | Invalid API key | Run `/lipnardo setup`, re-check key |
-| 429 Rate Limited | Too many requests | Script auto-retries with backoff |
-| Concurrent limit | 3 videos already processing | Wait for completion |
-| Generation failed | Content policy or avatar issue | Try different avatar/script |
-| URL expired | Download URL > 7 days old | Re-download via `/lipnardo download` |
-| Insufficient credits | API balance depleted | Top up at app.heygen.com |
-
-Read `references/error-codes.md` for full error taxonomy and retry strategies.
-
-## Cost Tracking
-
-ALWAYS estimate cost before generating. ALWAYS log cost after successful generation.
-
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/credit_check.py balance
-python3 ${CLAUDE_SKILL_DIR}/scripts/credit_check.py estimate --feature avatar3 --duration 60
-python3 ${CLAUDE_SKILL_DIR}/scripts/credit_check.py summary
-```
-```
-Read `references/credit-costs.md` for full pricing table.
-```
-
-## Response Format
-
-After every successful generation, report to the user:
-- **Path**: where the video file was saved
-- **Duration**: video length in seconds
-- **Size**: file size
-- **Cost**: estimated cost based on feature type and duration
-- **Video ID**: for later translation, download, or reference
-
-## API Constraints
-
-- **3 concurrent videos** max (batch script respects this automatically)
-- **30 minutes** max per video (Enterprise for longer)
-- **1080p** default resolution (4K Enterprise only)
-- **Photo Avatar IV**: 3 minutes max duration
-- **Download URLs**: expire after 7 days -- download promptly
-- **50 scenes** max per Studio API request
-
-## Source
-
-Rewritten for AICUT from [`AgriciDaniel/lipnardo`](https://github.com/AgriciDaniel/lipnardo)
-(MIT), skills/lipnardo/SKILL.md. The method is that skill's own; the way it runs is AICUT's.

package/skills/lipnardo/examples/batch-personalized.md

@@ -1,44 +0,0 @@
-# Batch Personalized Video Example
-
-## User Request
-> "Generate personalized outreach videos for each prospect in my CSV"
-
-## Input: prospects.csv
-```csv
-prompt,avatar_id,name
-"Hello John, I wanted to share how our platform can help Acme Corp scale faster.",Kristin_public_3_20240108,john_acme
-"Hi Sarah, TechCo's engineering team would love our developer tools.",Kristin_public_3_20240108,sarah_techco
-"Welcome Marcus, let me show you what we built for companies like DataFlow.",Kristin_public_3_20240108,marcus_dataflow
-```
-
-## Claude (using Lipnardo)
-
-### 1. Estimate batch cost
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/credit_check.py estimate-batch \
-  --input prospects.csv --feature avatar3 --avg-duration 45
-# Output: {"estimated_total": 2.25, "video_count": 3, "avg_duration": 45}
-```
-
-> "Estimated total: **$2.25** for 3 videos (avg 45s at $0.0167/sec). Proceed?"
-
-### 2. Run batch
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/batch_generate.py \
-  --input prospects.csv --mode agent --max-concurrent 3
-```
-
-### 3. Progress
-```
-{"action":"submitted","index":0,"video_id":"vid_001"}
-{"action":"submitted","index":1,"video_id":"vid_002"}
-{"action":"submitted","index":2,"video_id":"vid_003"}
-{"polling":true,"video_id":"vid_001","video_status":"processing"}
-{"action":"completed","index":0,"path":"~/Documents/lipnardo_videos/batch_.../vid_001.mp4"}
-...
-```
-
-### 4. Result
-All videos saved to `~/Documents/lipnardo_videos/batch_20260415_103022/`.
-
-Manifest at `batch_manifest_20260415_103022.json` tracks every job's status for crash recovery.

package/skills/lipnardo/examples/photo-to-avatar-pipeline.md

@@ -1,56 +0,0 @@
-# Photo-to-Avatar Pipeline Example
-
-## User Request
-> "Create a talking head video using my headshot photo"
-
-## Claude (using Lipnardo)
-
-### 1. Read references
-Reads `references/avatar-types.md` for photo requirements and pricing.
-
-> "Photo Avatar IV costs **$0.05/sec** (~$3/min) with a 3-minute max.
-> Your photo should be: front-facing, 512x512 min, even lighting, mouth closed."
-
-### 2. Create avatar from photo
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/photo_avatar.py create \
-  --photo ~/headshot.jpg --name "Daniel"
-```
-
-### 3. Training (automatic polling)
-```
-{"action":"uploading_photo","file":"~/headshot.jpg"}
-{"action":"photo_uploaded","asset_id":"asset_abc123"}
-{"action":"creating_avatar_group","name":"Daniel"}
-{"action":"group_created","group_id":"grp_xyz789"}
-{"polling_training":true,"group_id":"grp_xyz789","training_status":"training"}
-...
-{"polling_training":true,"group_id":"grp_xyz789","training_status":"completed"}
-```
-
-Training typically takes 5-30 minutes.
-
-### 4. Avatar ready
-```json
-{
-  "success": true,
-  "group_id": "grp_xyz789",
-  "avatar_id": "photo_avatar_daniel_001",
-  "name": "Daniel"
-}
-```
-
-### 5. Generate video with new avatar
-```bash
-python3 ${CLAUDE_SKILL_DIR}/scripts/photo_avatar.py generate \
-  --avatar-id photo_avatar_daniel_001 \
-  --script "Welcome to our company! I'm excited to show you what we've been working on." \
-  --voice-id en-US-GuyNeural
-```
-
-### 6. Result
-> "Your personalized avatar video is ready!
-> - Path: `~/Documents/lipnardo_videos/def456.mp4`
-> - Duration: 15 seconds
-> - Cost: ~$0.75 (Photo Avatar IV at $0.05/sec)
-> - Avatar ID: photo_avatar_daniel_001 (reusable for future videos)"