Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

hyper3d-documentary

BSecurity

用 Hyper3D(Rodin Gen-2.5)把一个科普题材做成可分享的单文件网页 3D 纪录片:需求问答 → 写脚本 → 生参考图 → 生成 3D 模型 → 模型库审核 → 动画成片,外加一个项目总览管理页。

4 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentspythonnodeapi

Works with

api

Security Analysis

B84/100
mediumInstalls packages at runtime which could introduce malicious dependencies
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add xiaohuailabs/hyper3d-documentary --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of hyper3d-documentary?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for hyper3d-documentary
[![Security: B — Skills Directory](https://www.skillsdirectory.com/api/skills/xiaohuailabs-hyper3d-documentary/badge)](https://www.skillsdirectory.com/skills/xiaohuailabs-hyper3d-documentary)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: hyper3d-documentary
description: 用 Hyper3D(Rodin Gen-2.5)把一个科普题材做成可分享的单文件网页 3D 纪录片:需求问答 → 写脚本 → 生参考图 → 生成 3D 模型 → 模型库审核 → 动画成片,外加一个项目总览管理页。
---

# hyper3d-documentary:从一句话想法到 3D 网页纪录片

> 本文档使用自然语言 + 代码片段混合编写。代码部分按其语言语义执行;代码块只写逻辑骨架,判断标准写在代码块外面的正文里。

## 定位

用户说"我想做一个 ×× 的 3D 纪录片",本技能带着用户走完整条线,最终交付一个**双击就能打开、可以直接发给别人的单文件 HTML**:自动播放的分镜动画 + 片尾自由旋转、拆解、点零件看说明。3D 模型由 Hyper3D 的 Rodin Gen-2.5 从参考图生成,渲染引擎(three.js)已经打包在技能里,成片不依赖任何网络资源。

技能是原子的:生参考图的方式由用户在 `config.json` 里配置(任何能"提示词 → 图片文件"的命令都行),不依赖其他技能。

## 运行环境

- Python 3.10+(所有脚本),无第三方依赖
- Node 18+(只在压缩模型时用,首次运行自动 `npm install` 到 `tools/`)
- 可选:`pip install playwright && playwright install chromium`,用来给成片自动截图验收
- Hyper3D API Key:在 hyper3d.ai 后台申请。按优先级从环境变量 `HYPER3D_API_KEY` → 本目录 `config.json` 的 `hyper3d_api_key` → 项目目录 `.env` 读取

## 配置

第一次用时把 `config.example.json` 复制成 `config.json` 再填。`config.json` 含真实 Key,只在本地用;分享技能时只分享 `config.example.json`。各字段含义写在 example 文件的 `_说明` 里。

## 项目落盘结构

所有项目放在 `config.json` 的 `root` 下,一个项目一个目录,产物全部是用户能直接打开看的文件:

```
<root>/
├── 管理页.html                 所有项目的总览(每做完一步重新生成)
├── 共享缓存/                   地球贴图、星表等跨项目复用的下载
└── <项目名>/
    ├── 需求.md                 第 1 步:问答定下来的需求
    ├── 脚本.md                 第 2 步:分镜脚本(人读)
    ├── 素材清单.json           第 2 步:模型表 + 关键帧表(脚本读)
    ├── 参考图/M1-<名>/1-四分之三.png …   第 3 步:每个模型四个视角;<视角>-提交.png 是去掉文字标识后送 Hyper3D 的版本
    ├── 参考图/K1-<名>.png      第 3 步:分镜关键帧概念图(只给人看,不建模)
    ├── 参考图.html             第 3 步:审图页
    ├── 模型/M1-<名>/           第 4 步:Hyper3D 回包、原始 glb、零件/、web-4096.glb
    ├── 模型库.json             第 5 步:每个模型的状态、积分、体积、备注
    ├── 模型.html               第 5 步:模型库页(3D 预览 + 审核)
    ├── 素材/贴图/              第 6 步:环境贴图(太空题材)
    ├── 动画页.html             第 6 步:动画源码(AI 按脚本写,可反复改)
    ├── 成片.html               第 6 步:打包后的单文件成片(发给观众的就是它)
    └── 验收/                   第 6 步:每幕截图
```

模型目录统一叫 `M<序号>-<中文名>`,序号从 1 开始;关键帧叫 `K<序号>-<中文名>`。

## 总路由

用户的一句话进来后,先定位项目,再判断它走到哪一步,只读那一步的分支文件。

```python
project = 定位项目()          # 用户点名的项目;没有就按需求里的题材起一个中文目录名
stage = 判断阶段(project)
读取(f"rules/{stage}.md") 并执行
每一步结束后: python3 scripts/build_manage_page.py ; 告诉用户管理页和本步产物页的路径
```

阶段判断,按顺序取第一个成立的:

1. 没有 `需求.md` → **1-需求问答**
2. 没有 `脚本.md` 或 `素材清单.json` → **2-写脚本**
3. 素材清单里任一模型的参考图没齐、或用户在审图页标了重做 → **3-参考图**
4. 任一模型还没有 `模型/M*/web*.glb`、或模型库里有"重做" → **4-生成模型**
5. 模型库里还有"待审" → **5-模型库**
6. 其余 → **6-动画页**(没有成片就写并打包;有成片就按用户反馈改动画页再打包)

用户明确点名某一步("帮我重生 M3 的参考图"、"改一下第 4 幕镜头")就直接进那一步,不按顺序重走。

Hyper3D 接口细节(参数、计费、状态、坑)统一放在 `rules/hyper3d-api.md`,第 4 步和排错时读。

## 铁律

1. **花钱前先报价**:提交 Hyper3D 之前把要生成的模型数、每个的档位、预计积分、余额列给用户,得到同意才提交。
2. **每一步都落盘、都给用户看得见的页面**再进下一步;用户在页面上的判断(重做 / 通过)是流程往前走的依据,不替用户判断。
3. **成片是给观众的**:不含任何内部信息——不写生成参数、积分、文件路径、待办;字幕只讲题材本身。
4. **模型真实尺寸由脚本定**,不在动画里靠眼睛调:素材清单里每个模型写清真实长度和长轴,引擎按它缩放。
5. 会自动展开、旋转、伸缩的部件(太阳翼、天线、起落架、舱门)**不建进模型**,参考图里就去掉,在动画页里用简单几何体做成会动的附件。
6. 参考图**不能有文字、旗帜、标识、水印**,Hyper3D 会把它们当成几何体或贴图烧进模型;有就做一份 `-提交.png`。
7. API Key 只走环境变量 / `config.json` / 项目 `.env`,任何会被分享的文件里都不能出现它。

Attribution

xiaohuailabsxiaohuailabs
View sourceMore from xiaohuailabs →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →