# Send Kie Ai Skill to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "kie-ai-skill",
    "name": "Kie Ai Skill",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/jon-xo/kie-ai-skill",
    "canonicalUrl": "https://clawhub.ai/jon-xo/kie-ai-skill",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/kie-ai-skill",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=kie-ai-skill",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "config.example.json",
      "kie-ai.sh",
      "lib/balance.py",
      "lib/generate-image.py"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/kie-ai-skill"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/kie-ai-skill",
    "downloadUrl": "https://openagent3.xyz/downloads/kie-ai-skill",
    "agentUrl": "https://openagent3.xyz/skills/kie-ai-skill/agent",
    "manifestUrl": "https://openagent3.xyz/skills/kie-ai-skill/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/kie-ai-skill/agent.md"
  }
}
```
## Documentation

### kie.ai API Wrapper

Unified access to multiple AI models through kie.ai's API. Generate images, videos, and music at 30-80% lower cost than official APIs.

### Features

🎨 Image Generation: Nano Banana Pro (Gemini 3 Pro), Flux, 4o-image
📤 Google Drive Upload: Optional automatic upload to Drive folder
📊 Usage Tracking: Local task history and cost estimation
💾 Local Storage: All files saved to images/ before optional upload
🎬 Video Generation (coming soon): Veo 3.1, Runway Gen-4 Aleph
🎵 Music Generation (coming soon): Suno V4/V4.5

### Quick Start

# Generate an image
./kie-ai.sh generate-image "A serene Japanese garden at sunset"

# With custom options
./kie-ai.sh generate-image "Cyberpunk city" --resolution 2K --aspect 16:9

# Upload to Google Drive
./kie-ai.sh generate-image "Space nebula" --upload-drive

# Check usage
./kie-ai.sh balance

### Prerequisites

kie.ai API Key:

Sign up at https://kie.ai
Get API key from dashboard
Add to ~/.openclaw/openclaw.json:
"env": {
  "vars": {
    "KIE_API_KEY": "your-key-here"
  }
}





(Optional) Maton API Key for Google Drive uploads:

Sign up at https://maton.ai
Get API key from https://maton.ai/settings
Set up Google Drive connection at https://ctrl.maton.ai
Add to config:
"MATON_API_KEY": "your-maton-key"

### Setup

# Clone to ~/src
cd ~/src
git clone https://github.com/jon-xo/kie-ai-skill.git
cd kie-ai-skill

# Make executable
chmod +x kie-ai.sh lib/*.py

# Create symlink for OpenClaw
ln -s ~/src/kie-ai-skill ~/.openclaw/workspace/skills/kie-ai-skill

# Test it
./kie-ai.sh generate-image "test image"

### Google Drive Upload (Optional)

# View/edit config
./kie-ai.sh config

# Edit config.json
{
  "drive": {
    "enabled": true,
    "folder_id": "YOUR_GOOGLE_DRIVE_FOLDER_ID"
  }
}

Get your folder ID from the Google Drive URL:

https://drive.google.com/drive/folders/1abc...xyz
                                          ^^^^ this part

### generate-image

Generate images with various models.

./kie-ai.sh generate-image <prompt> [options]

Options:
  --model <name>         Model: nano-banana-pro (default), google/nano-banana, flux-kontext, 4o-image
  --resolution <res>     Resolution: 1K (default), 2K, 4K
  --aspect <ratio>       Aspect ratio: 1:1 (default), 16:9, 9:16, 4:3, etc.
  --upload-drive         Upload to Google Drive after generation (requires config)

Examples:

# Basic generation
./kie-ai.sh generate-image "A red apple on a wooden table"

# High resolution
./kie-ai.sh generate-image "Mountain landscape" --resolution 4K

# Widescreen
./kie-ai.sh generate-image "Cinematic scene" --resolution 2K --aspect 16:9

# 16-bit pixel art
./kie-ai.sh generate-image "Cyberpunk lobster, 16-bit pixel art, no text" --aspect 16:9

# Generate and upload
./kie-ai.sh generate-image "Abstract art" --upload-drive

### balance

Check credit usage and remaining balance.

./kie-ai.sh balance

Shows:

Link to web UI for actual balance
Local task history
Estimated credit consumption
USD equivalent

### status

Show active/pending tasks.

./kie-ai.sh status

### models

List available models and pricing.

./kie-ai.sh models

### config

View/configure Google Drive upload settings.

./kie-ai.sh config

### Pricing

Approximate costs (kie.ai vs official):

Modelkie.aiOfficialSavingsNano Banana Pro~18-24 credits ($0.09-$0.12)$0.1520-40%Veo 3.1VariableN/A—Flux Kontext~50 credits ($0.25)$0.30~17%Suno V4Variable$0.10/trackComparable

Credit pricing: ~$0.005 per credit (1,000 credits = $5)

Check exact costs at: https://docs.kie.ai/pricing

### File Storage

Generated files are saved to the images/ directory (gitignored):

~/src/kie-ai-skill/images/
  2026-02-11-12-05-01-1.png
  2026-02-11-12-09-56-1.png
  ...

Format: YYYY-MM-DD-HH-MM-SS-{index}.png

Retention:

Local: Forever (or until you delete)
kie.ai CDN: 14 days
Google Drive: Forever (if uploaded)

### Task State

Tasks are tracked in:

~/src/kie-ai-skill/.task-state.json

Used for:

Resume interrupted tasks
Usage tracking
Preventing duplicate submissions

### Image Generation

nano-banana-pro - Gemini 3 Pro Image (1K/2K/4K)
google/nano-banana - Gemini 2.5 Flash Image (cheaper)
flux-kontext - Flux by Black Forest Labs
4o-image - OpenAI GPT-4o Image

### Video Generation (coming soon)

veo-3.1 - Google Veo 3.1 (cinematic)
veo-3.1-fast - Veo 3.1 Fast (cheaper)
runway-aleph - Runway Gen-4 Aleph

### Music Generation (coming soon)

suno-v4 - Suno V4 (up to 8min)
suno-v4.5 - Suno V4.5 Plus

See https://docs.kie.ai for full list.

### "KIE_API_KEY not set"

Add to ~/.openclaw/openclaw.json:

"env": {
  "vars": {
    "KIE_API_KEY": "your-key-here"
  }
}

### "Credits insufficient"

Top up at: https://kie.ai/billing

### "MATON_API_KEY not set" (Drive upload)

Sign up at https://maton.ai
Add MATON_API_KEY to openclaw.json
Create Google Drive connection at https://ctrl.maton.ai

### "Drive upload failed"

Check MATON_API_KEY is set
Verify Google Drive connection is active at https://ctrl.maton.ai
Ensure folder_id in config.json is correct
Try generating without --upload-drive first

### Integration with OpenClaw

Use via exec or directly in OpenClaw agent conversations:

# From OpenClaw chat
Generate a cyberpunk city image with kie.ai

# The agent will run:
cd ~/src/kie-ai-skill && ./kie-ai.sh generate-image "cyberpunk city"

### Environment Variables

VariableRequiredPurposeKIE_API_KEYYesAuthenticates all requests to api.kie.aiMATON_API_KEYNoAuthenticates Google Drive uploads via gateway.maton.ai

### External Endpoints

EndpointMethodData SentUsed Byhttps://api.kie.ai/api/v1/jobs/createTaskPOSTprompt, model, resolution, aspect ratiogenerate-image.pyhttps://api.kie.ai/api/v1/jobs/recordInfoGETtask IDgenerate-image.py, watch_task.pyhttps://api.kie.ai/api/v1/chat/creditGET— (auth header only)balance.pyhttps://gateway.maton.ai/google-drive/upload/...POSTimage file bytes, filenameupload-drive.py (optional)

### Data Leaving This Machine

Prompt text is sent to api.kie.ai to generate images.
Generated image files are sent to gateway.maton.ai only when --upload-drive is explicitly passed.
API keys are transmitted as Authorization: Bearer headers and are never logged or written to disk by this skill.
No telemetry, analytics, or usage data is collected by this skill itself.

### Trust Statement

This skill sends data to two third-party services: kie.ai for AI generation and maton.ai as an OAuth gateway for Google Drive. Review their respective privacy policies before use. Drive upload is strictly opt-in via --upload-drive.

### Autonomous Invocation

This skill can be invoked autonomously by an OpenClaw agent when asked to generate images. It does not execute autonomously on its own — it must be called explicitly. To prevent autonomous invocation, remove the skill symlink from your OpenClaw workspace.

### Links

kie.ai Dashboard: https://kie.ai
Documentation: https://docs.kie.ai
Pricing: https://docs.kie.ai/pricing
Logs/Balance: https://kie.ai/logs
Billing: https://kie.ai/billing
Maton (for Drive): https://maton.ai
GitHub Repo: https://github.com/jon-xo/kie-ai-skill

### License

MIT

### Support

Issues: https://github.com/jon-xo/kie-ai-skill/issues
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: jon-xo
- Version: 1.0.1
## Source health
- Status: healthy
- Source download looks usable.
- Yavira can redirect you to the upstream package for this source.
- Health scope: source
- Reason: direct_download_ok
- Checked at: 2026-04-30T16:55:25.780Z
- Expires at: 2026-05-07T16:55:25.780Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/kie-ai-skill)
- [Send to Agent page](https://openagent3.xyz/skills/kie-ai-skill/agent)
- [JSON manifest](https://openagent3.xyz/skills/kie-ai-skill/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/kie-ai-skill/agent.md)
- [Download page](https://openagent3.xyz/downloads/kie-ai-skill)