首页 › 龙虾技能列表 › free-kameo — 技能工具

free-kameo — 技能工具

v1.0.0

[自动翻译] Generate expressive talking-head videos from static images using Kameo AI. Converts static avatars/portraits into dynamic 5-second videos with realist...

2· 1,700·2 当前·2 累计
by @veya2ztn·MIT-0
下载技能包
License
MIT-0
最后更新
2026/4/10
安全扫描
VirusTotal
可疑
查看报告
OpenClaw
可疑
medium confidence
The skill largely does what it says (generate talking-head videos via Kameo), but its manifest and docs disagree with the scripts about required tools and credentials, and the enhancement workflow will send user images to an external vision API that is not declared — these inconsistencies warrant caution.
评估建议
Before installing, verify a few things: (1) Confirm the source/repository and that kameo.chat and the GitHub repo (package.json) are legitimate; anonymous/unknown source is riskier. (2) Expect to provide KAMEO_API_KEY — the scripts require it even though the registry metadata lists none. (3) The prompt-enhancement step calls Google Generative Language (Gemini) and requires GOOGLE_API_KEY; if you don't want images sent to Google, skip enhancement or remove that step. (4) Remove or validate the ex...
详细分析 ▾
ℹ 用途与能力
The skill's code and instructions match the stated purpose: scripts take an image, build a prompt, and call api.kameo.chat to generate videos. Requiring a KAMEO_API_KEY is expected. However, package.json advertises required binaries (curl, jq, base64) while the registry metadata lists none — a metadata mismatch. Overall capability aligns with purpose but the declared requirements are incomplete.
⚠ 指令范围
Enhancement and generation scripts instruct the agent to: read an image file, base64-encode it, send it to https://generativelanguage.googleapis.com (Gemini) for scene analysis and to https://api.kameo.chat for generation. The SKILL.md/USAGE omit mentioning the required GOOGLE_API_KEY while enhance_prompt.sh requires it and will transmit the image to Google. The scripts also read/write ~/.config/kameo/credentials.json (normal for storing API keys). Sending user images to external services (Google + Kameo CDN) is privacy-sensitive and not fully documented in the manifest.
ℹ 安装机制
There is no install spec (no downloads or archives), which lowers installation risk. All code is delivered as plain shell/python scripts. This is lower-risk than remote downloads, but package.json and scripts expect standard CLI tools (curl, jq, base64, python3) — the registry metadata failed to declare those requirements.
⚠ 凭证需求
The skill actually requires KAMEO_API_KEY (and optionally stores it in ~/.config/kameo/credentials.json). enhance_prompt.sh also requires GOOGLE_API_KEY to call Gemini; neither env var is declared in the registry metadata. The docs include an example API key string embedded in SKILL.md/USAGE.md (kam_I3rdx43...), which could be a leaked or placeholder key — presence of such a token in docs is suspicious and should be validated. register.sh references SUPABASE_URL and SUPABASE_ANON_KEY placeholders; if misconfigured they could expose credentials during registration flows.
✓ 持久化与权限
The skill does not request always:true and does not modify other skills or system-wide agent settings. It writes only to its own config path (~/.config/kameo/credentials.json) when registering a key (with chmod 600), which is appropriate for storing a service API key.
安全有层次，运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发，无需署名。

运行时依赖

无特殊依赖

版本

latestv1.0.02026/2/4

Initial release of Kameo AI skill—generate lifelike talking-head videos from static images. - Convert a single portrait or avatar photo into a 5-second video with realistic facial expression, lip-sync, and motion - Supports prompt-driven scene customization for enhanced expressions and gestures (basic to advanced prompts) - Choose video aspect ratios: 9:16, 16:9, or 1:1 - Bash scripts and API instructions provided for simple video generation, credits management, and registration - Includes best practices, troubleshooting, and detailed usage guidance

● 可疑

安装命令 点击复制

官方npx clawhub@latest install kameo-free
镜像加速npx clawhub@latest install kameo-free --registry https://cn.clawhub-mirror.com

技能文档

Transform static images into expressive talking-head videos with realistic motion and lip-sync.

Quick Start

scripts/generate_video.sh   [output_file]

Example: 

scripts/generate_video.sh avatar.jpg "Hello, I am an AI assistant" output.mp4

What It Does

  • Takes a static image (portrait/avatar)
  • Adds realistic facial motion, expressions, and lip-sync based on your prompt
  • Generates 5-second video in 9:16, 16:9, or 1:1 aspect ratio
  • Returns CDN URL instantly (processing ~10-30 seconds)

Authentication

Set your Kameo API key: 

export KAMEO_API_KEY="kam_I3rdx43IymFNbfBw1c0ZbSc7o3aUfQgz8cljZA6T7fs"

Or store in ~/.config/kameo/credentials.json: 

{
  "api_key": "kam_I3rdx43IymFNbfBw1c0ZbSc7o3aUfQgz8cljZA6T7fs"
}

Getting an API Key:

  • Register at kameo.chat (requires email verification)
  • Login to get JWT token
  • Create API key via /api/public/keys endpoint
  • Or use the registration helper: scripts/register.sh

Prompt Engineering

Basic Prompts (Simple)

Just the dialogue: 

"Hello, I'm here to help you today"
"こんにちは、私はガッキーです。愛してます。"

Works but results are generic.

Enhanced Prompts (Recommended)

Format: 

[Detailed scene/environment], [person's complete appearance and expression], speaking in [tone], "[DIALOGUE]". [Camera and lighting details].

Example: 

In a bright outdoor winter setting with soft, overcast daylight, a young woman with long dark hair wearing a white knitted winter hat with ear flaps and a colorful patterned sweater stands centered in frame. She looks directly into the camera with a warm, genuine smile, her eyes crinkling with joy, speaking in a cheerful, affectionate tone, "こんにちは、私はガッキーです。愛してます。" The scene is captured in a medium close-up shot, framed at eye level. The lighting is natural and diffused from above, creating soft, even illumination.

Why Enhanced Prompts Matter:

  • Better facial expressions matching the scene context
  • More natural motion and gestures
  • Improved lip-sync quality
  • Contextual emotional delivery

Prompt Enhancement Workflow

For best results, use vision AI to analyze the image first:

  • Feed the image to a vision model (Gemini, GPT-4V, Claude)
  • Ask it to describe the scene in cinematic detail
  • Insert your dialogue into the description
  • Use the enhanced prompt for Kameo

See: scripts/enhance_prompt.sh for automated enhancement.

API Details

Base URL: https://api.kameo.chat/api/public

Generate Video

curl -X POST https://api.kameo.chat/api/public/generate \
  -H "X-API-Key: kam_I3rdx43IymFNbfBw1c0ZbSc7o3aUfQgz8cljZA6T7fs" \
  -H "Content-Type: application/json" \
  -d '{
    "image_base64": "",
    "prompt": "Your detailed prompt here",
    "seconds": 5,
    "aspect_ratio": "9:16"
  }'

Parameters:

  • image_base64 (required): Base64-encoded JPEG/PNG
  • prompt (required): Dialogue and/or scene description
  • seconds (optional): 5 (default) or 10
  • aspect_ratio (optional): "9:16" (default), "16:9", or "1:1"

Response: 

{
  "job_id": "uuid",
  "status": "completed",
  "video_url": "https://cdn.kameo.chat/videos/{uuid}.mp4",
  "duration_seconds": 5,
  "processing_time_ms": 15000
}

Check Credits

curl -H "X-API-Key: kam_..." \
  https://api.kameo.chat/api/public/credits

Response: 

{
  "permanent_credits": 294,
  "subscription_credits": 0,
  "total_available": 294
}

Pricing

curl https://api.kameo.chat/api/public/pricing

Cost: 3 credits per video

Performance

  • Processing time: 8-35 seconds (depends on aspect ratio and queue)
  • 9:16 (portrait): ~30-35s
  • 16:9 (landscape): ~15-20s
  • 1:1 (square): ~10-15s

Best Practices

  • Optimize image size - Resize large images before encoding (saves bandwidth, faster upload)
   ffmpeg -i large.jpg -vf scale=720:-1 optimized.jpg
  • Use descriptive prompts - Enhanced prompts = better results
  • Choose aspect ratio wisely
- 9:16: Mobile/social media (TikTok, Instagram Stories) - 16:9: Desktop/YouTube - 1:1: Profile pictures, square posts

  • Monitor credits - Check balance with scripts/check_credits.sh

Limitations

  • CDN access: Video URLs may have time-limited access or require authentication
  • Download: Videos may return 403 when downloaded via curl (use browser or authenticated session)
  • Rate limits: 10 generations per minute

Troubleshooting

"401 Unauthorized"

  • Check your API key is set correctly
  • Verify key hasn't been revoked

"402 Insufficient credits"

  • Check credit balance: scripts/check_credits.sh
  • Need to add credits at kameo.chat

"Timeout errors"

  • 9:16 videos take longer (~30s)
  • Increase timeout in scripts
  • Retry if server is busy

"403 when downloading video"

  • CDN URLs may be time-limited
  • Try accessing in browser immediately after generation
  • Or save the base64 response if available

Use Cases

  • AI character videos - Bring bot avatars to life
  • Social media content - Dynamic profile videos
  • Demos and presentations - Talking product demos
  • Educational content - Video tutorials with AI presenters
  • Multilingual content - Same avatar speaking different languages
数据来源：ClawHub ↗ · 中文优化：龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制

免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制

了解定制服务