The primary command-line interface for executing multi-modal AI inference, search, and embedding tasks across various providers.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-infer
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-infer 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 Infer?
OpenClaw Infer is the first-party command-line utility designed to streamline AI inference workflows. As a core component of the Openclaw Skills framework, it provides a unified interface for interacting with various provider-backed models. Whether you are generating text, creating cinematic videos, or transcribing audio, this tool eliminates the need for multiple provider-specific CLIs by centralizing capabilities under the infer command family.
By leveraging this skill, developers can interact with LLMs, generate embeddings, and perform web searches with standardized syntax. It is built to work seamlessly in both local environments and automated pipelines, offering a robust foundation for building AI-driven applications and agentic workflows.
OpenClaw Infer Use Cases
- Running text-based model prompts to generate code or content.
- Generating lobster illustrations or describing existing image files.
- Transcribing meeting memos into text with specific focus on action items.
- Converting text to high-quality speech for voice-enabled applications.
- Creating cinematic video content or analyzing video files for descriptions.
- Performing real-time web searches to augment agent knowledge bases.
- Creating vector embeddings for semantic search and data analysis.
How OpenClaw Infer Works
- The user installs the openclaw package to ensure the binary is available on the system path.
- Commands are structured using the openclaw infer prefix followed by the specific modality such as model, image, or web.
- The CLI processes user flags like --json to determine if the output should be human-readable or structured for machine processing.
- OpenClaw Infer routes the request to the specified or default AI provider to execute the inference task.
- The tool returns the result directly to the terminal or saves generated media files to the local file system.
OpenClaw Infer Setup
To get started with this component of Openclaw Skills, install the CLI via npm:
npm install -g openclaw
Verify that the installation is successful by listing the available model providers:
openclaw infer model providers --json
OpenClaw Infer Data Schema & Taxonomy
OpenClaw Infer utilizes a structured approach to input and output, ensuring compatibility with Openclaw Skills workflows.
| Data Type | Description |
|---|---|
| Commands | Standardized sub-commands like image, tts, and embedding. |
| Flags | Use --json for machine-readable output and --provider to target specific backends. |
| Media Output | Local file paths for generated MP3, MP4, and image assets. |
| Metadata | JSON responses include provider details, execution status, and task-specific results. |
OpenClaw Infer Advanced Features
- Support for local checkouts to allow developers to use custom-built versions of the OpenClaw CLI.
- Machine-readable JSON output for easy piping into other automation steps.
- Multi-modal capabilities covering text, image, audio, video, and web search in a single binary.
- Selection rules that prioritize first-party inference over older wrapper skills.
- Integrated provider discovery to quickly identify available backends for speech and model tasks.
SKILL.md
Loading
Related Openclaw Skills
Security Incident Recovery
A comprehensive framework for managing post-incident recovery, scoping attacker impact, and executing structured remediation after a security breach.
Security Testing Strategy
A technical framework for selecting and implementing layered security testing from unit tests and fuzzing to dynamic analysis and deep static analysis using Openclaw Skills.
Security & Reliability Design Review
A technical framework for auditing system architectures to ensure security and reliability are built-in emergent properties rather than afterthoughts.
Abstract Factory Implementor
A technical skill to implement the Abstract Factory pattern for creating families of related objects while ensuring strict interface isolation.
Code Generation Assistant
A comprehensive AI assistant for generating high-quality code snippets, intelligent completions, and reusable project templates.
Cloud Architect
A professional AI assistant for designing high-availability, cost-effective, and secure cloud architectures across AWS, GCP, and Azure.
Featured*
