A utility for generating standardized model inventories and high-quality visual model card images from your OpenClaw configuration.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-model-card
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install openclaw-model-card using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OpenClaw Model Card?
The OpenClaw Model Card skill is designed to provide a consistent and automated way to manage AI model configurations. By analyzing the openclaw.json file, this skill helps developers verify their default and fallback chains, ensuring that all model references are accurate and functional. As a core component of the Openclaw Skills ecosystem, it bridges the gap between raw configuration files and readable documentation.
Beyond simple text output, the skill supports the generation of visual model card images. This is particularly useful for sharing configurations in chat interfaces or documentation where terminal output may not be easily accessible. It prioritizes reproducibility and security, encouraging users to keep sensitive configurations local while publishing only sanitized, generated artifacts.
OpenClaw Model Card Use Cases
- Documenting active AI model inventories for team transparency.
- Verifying complex fallback chains and default model settings.
- Auditing openclaw.json for alias conflicts or suspicious context window sizes.
- Sharing visual snapshots of model configurations in messaging platforms.
How OpenClaw Model Card Works
- The skill identifies the location of the openclaw.json configuration file via the --config flag.
- It runs a Python script to parse the JSON and perform consistency checks, such as identifying missing model references.
- Depending on the flags provided, it generates either a structured text summary or a visual PNG card.
- Visual cards are rendered using md2img.js, which leverages wkhtmltoimage to turn markdown summaries into professional images.
- The output is provided to the user, ensuring a standardized representation within the Openclaw Skills framework.
OpenClaw Model Card Setup
To use this skill, ensure you have the necessary system dependencies for image rendering and execute the Python script.
# Install rendering dependency
sudo apt-get install wkhtmltoimage
# Generate a text-based model inventory
python3 skills/openclaw-model-card/scripts/show-model-config.py --config /path/to/openclaw.json
# Generate a visual model card image
python3 skills/openclaw-model-card/scripts/show-model-config.py --config /path/to/openclaw.json --image ./model-card.png
OpenClaw Model Card Data Schema & Taxonomy
| Data Point | Description |
|---|---|
| openclaw.json | The primary source of truth for model and alias configurations. |
| model-card.png | The rendered visual artifact generated for sharing. |
| Alias Conflicts | Logged during the consistency check process. |
| contextWindow | Validated against model definitions to identify suspicious settings. |
OpenClaw Model Card Advanced Features
- Integrated consistency engine to detect alias conflicts and broken model links.
- Multi-format output supporting both standard terminal text and image rendering.
- Sanitization-first workflow that separates sensitive config files from shareable artifacts.
- Dependency-aware rendering using wkhtmltoimage for high-fidelity documentation as part of the Openclaw Skills library.
SKILL.md
Loading
Related Openclaw Skills
YouTube Video Analyzer (Multimodal)
A sophisticated multimodal analysis tool that synchronizes YouTube transcripts with visual frame extraction to provide comprehensive video understanding.
YouTube Knowledge Extractor
A multimodal AI agent skill that combines timestamped transcripts with visual frame extraction to provide comprehensive YouTube video analysis.
Top ClawHub Skills
A live API integration for discovering, searching, and verifying the performance and security of skills within the ClawHub ecosystem.
Claude for Safari
A powerful automation skill that allows AI agents to control the native Safari browser on macOS through AppleScript and screen captures.
Ceaser Privacy Protocol
A privacy-preserving ETH wrapper on Base L2 using zero-knowledge proofs for shielded transactions and gasless withdrawals.
Scrapling Web Scraping Skill
A powerful Python web scraping skill designed to bypass anti-bot protections and extract structured data from complex dynamic websites.
Featured*
