skill-adsturboSAFE

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

git clone https://github.com/AdsTurbo/skill-adsturbo ~/.claude/skills/adsturbo

git clone https://github.com/AdsTurbo/skill-adsturbo ~/.codex/skills/adsturbo

clawhub install adsturbo/adsturbo

export ADSTURBO_API_KEY="your_api_key"

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: adsturbo
description: AdsTurbo full toolkit: AI spokesperson video, video generation & extension, ad cloning, watermark removal, 4K upscaling, video translation, character swap, motion control, subtitles, AI image generation and e-commerce photos. Best for workflows spanning multiple capabilities. Requires an AdsTurbo API key, created at https://adsturbo.ai/iris/api. AdsTurbo 全能力入口:AI 数字人口播、视频生成与延长、广告复刻、去水印、4K 超分、视频翻译、换角色、动作控制、字幕、AI 图片生成与电商图。适合需要跨能力串联的完整创作流程。需要 AdsTurbo API Key,在 https://adsturbo.ai/iris/api 创建。
---
# AdsTurbo AI Creation Suite

The full set of AdsTurbo's open capabilities: digital human voiceover, video generation, ad cloning, video refinement and transformation, AI image creation.

## When to use this skill

Use it for complete creative workflows that **chain multiple capabilities together** — e.g. "clone this ad, swap in our spokesperson, then translate it to English", a single request that bundles three capabilities.

For a single task (just remove a watermark, just generate one image), installing the corresponding single-capability skill is lighter weight.

## Prerequisites

- Python 3.8+ (the scripts use the standard library only; nothing to install)
- An AdsTurbo API key in the environment variable `ADSTURBO_API_KEY` (see below for how to get one)
- Optional `ADSTURBO_BASE_URL`, defaults to `https://adsturbo.ai/klian/novartapi`

### Getting an API key

1. Sign up or sign in at https://adsturbo.ai?channel=github
2. Open https://adsturbo.ai/iris/api (Workspace → API), click "Create API Key" and copy the key
3. `export ADSTURBO_API_KEY=<your key>`

Every plan can call the API with an API key, and usage is billed in credits; if you run out, top up or upgrade at https://adsturbo.ai/pricing. 1080p+ video and 4K images need a subscription (credit packs alone don't count), and creating a custom digital human needs a Pro plan.

**If the user has no key yet**: when `ADSTURBO_API_KEY` is not set, or a script reports a missing key or a 401, do not keep retrying. First finish everything that doesn't need the API (clarify the brief, draft the script or prompt, settle aspect ratio, duration, model and other parameters, prepare the exact command), then tell the user they need an AdsTurbo API key and give them the three steps above; once they have it, run the prepared command. Without a key the scripts print `"error": "api_key_required"` and the steps on stdout. Keep the key in the environment variable and never echo it back in a reply.

## Intent → script

```
What does the user want?
│
├─ Have someone read out a script
│   ├─ Use a platform avatar     → digital_human.py actors → perform
│   ├─ Use their own likeness    → digital_human.py persona-create → perform
│   └─ Just an image + audio     → digital_human.py lipsync
│
├─ Generate footage from scratch
│   ├─ Text-to-video / image-to-video / first-last frame → video_generation.py generate
│   ├─ Extend an existing video   → video_generation.py extend
│   └─ Edit part of a video       → video_generation.py edit
│
├─ Work from a reference video
│   ├─ Clone it                  → ad_clone.py analyze → generate
│   ├─ Clone with edited lines / your own people or products → ad_clone.py draft-create → draft-preview → draft-submit
│   └─ Analyze only, no generation → ad_clone.py inspect
│
├─ Existing video, make it cleaner (content unchanged)
│   ├─ Remove watermark/clutter  → video_enhance.py remove-object
│   ├─ Remove burned-in subtitles → video_enhance.py erase --method rm_subtitle
│   ├─ Boost resolution/4K       → video_enhance.py upscale
│   └─ Add/translate subtitles   → video_enhance.py subtitle
│
├─ Existing video, swap out an element
│   ├─ Swap the on-screen person → video_transform.py character-swap
│   ├─ Animate a static portrait → video_transform.py motion-control
│   └─ Change language (dubbing) → video_transform.py translate
│
├─ Images
│   ├─ Text-to-image / edit image → image.py create
│   ├─ Product photo set          → image.py ecommerce
│   ├─ Event poster                → image.py poster
│   ├─ Cutout                       → image.py cutout
│   ├─ Remove watermark             → image.py erase
│   └─ Upscale                      → image.py upscale
│
├─ Local file needs to become a URL → upload.py image / audio / file
└─ Check task progress               → work.py status / batch / wait
```

## Phrase quick-reference

| User says | Command |
|---|---|
| Digital human voiceover, have the avatar say this | `digital_human.py perform` |
| Clone my likeness, make a digital human from my photo | `digital_human.py persona-create` |
| Lip sync, sync lips to audio | `digital_human.py lipsync` |
| Text-to-speech, TTS | `digital_human.py say` |
| Text-to-video, image-to-video, first-last frame | `video_generation.py generate` |
| Extend video, continue, add a few seconds | `video_generation.py extend` |
| Edit video, change background, partial edit | `video_generation.py edit` |
| Clone video, replicate, shoot one just like it | `ad_clone.py analyze` + `generate` |
| Shot breakdown, video analysis | `ad_clone.py inspect` |
| Clone while rewriting lines, swapping in your own people or products, or checking the price first | `ad_clone.py draft-create` → `draft-preview` → `draft-submit` (submit charges credits; confirm the quote first) |
| Remove watermark, remove logo | `video_enhance.py remove-object` |
| Remove subtitles, erase burned-in subtitles | `video_enhance.py erase --method rm_subtitle` |
| 4K, improve quality, upscale, super-resolution | `video_enhance.py upscale` |
| Add subtitles, translate subtitles | `video_enhance.py subtitle` |
| Swap character, replace the whole person, face swap | `video_transform.py character-swap` |
| Motion control, animate a photo | `video_transform.py motion-control` |
| Video translation, translate to English | `video_transform.py translate` |
| Generate an image, AI drawing, text-to-image | `image.py create` |
| Cutout, remove background | `image.py cutout` |
| Product her

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

declared (4 observation(s))

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.