A specialized architectural tool designed to decompose complex AI agent skills into safer, modular, and more manageable components.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install skill-risk-splitter
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 skill-risk-splitter 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 Skill Risk Splitter?
The Skill Risk Splitter is a governance-focused utility within the Openclaw Skills ecosystem. It is specifically engineered to analyze AI agent skills that have become too broad or high-risk, refactoring them into distinct versions such as a safe core version and an enhanced privilege version. By breaking down responsibilities, it reduces the complexity of security scanning and simplifies long-term maintenance.
This skill ensures that high-risk behaviors are never hidden but rather isolated and documented. It provides a structured approach to skill refactoring, prioritizing transparency and auditability through automated scripts and standardized templates.
Skill Risk Splitter Use Cases
- Refactoring monolithic skills that handle too many disparate responsibilities.
- Designing multi-tiered skill structures to separate read-only operations from high-privilege execution.
- Identifying hidden risk sources and security boundaries in existing agent workflows.
- Generating structured migration plans and compatibility impact reports for skill updates.
How Skill Risk Splitter Works
- The skill ingests existing skill descriptions, script responsibilities, and identified risk points.
- It reorganizes the input into a structured task book, highlighting items that require manual confirmation.
- A draft version is generated for user review, focusing on the safe vs. enhanced split logic.
- If a script execution environment is available, it runs a Python-based refactoring process to generate the new files.
- The final output provides a comprehensive package including migration suggestions and priority assessments.
Skill Risk Splitter Setup
To get started with this component of Openclaw Skills, ensure you have Python 3 installed. You can execute the refactoring script using the following command:
python3 "{baseDir}/scripts/run.py" --input <path_to_input_skill> --output <path_to_destination>
If your environment restricts script execution, the skill will directly output the structured text based on the provided templates in the resources directory.
Skill Risk Splitter Data Schema & Taxonomy
The skill organizes its operations through a set of local resources to ensure consistency across the Openclaw Skills ecosystem:
| File Path | Description |
|---|---|
resources/spec.json |
Technical specification defining the data structure for the refactoring process. |
resources/template.md |
The Markdown output template used for generating the final refactored reports. |
examples/ |
A directory containing sample input and output scenarios for reference. |
tests/smoke-test.md |
Pre-defined tests to verify the integrity of the splitting logic. |
Skill Risk Splitter Advanced Features
- Support for shell and execution hooks to automate the refactoring of large-scale skill libraries.
- Integrated dry-run logic for high-risk operations like system configuration changes or data deletion.
- Compatibility impact analysis to predict how splitting a skill will affect existing dependencies.
- Standardized boundary definitions for privacy, permissions, and compliance monitoring.
SKILL.md
Loading
Related Openclaw Skills
Skill README Rebuilder
A maintenance utility that synchronizes agent documentation, FAQs, and examples by reverse-engineering SKILL.md and local script resources.
screenshot-to-task
A specialized tool for Openclaw Skills that transforms visual inspirations and screenshot context into structured, prioritized task lists.
SBOM Explainer
An AI-powered skill that converts technical SBOM data into prioritized, human-readable risk assessments.
Command Execution Safety Inspector
A dedicated security skill that identifies and audits dangerous shell command patterns before execution to prevent system compromise.
Skill Routing Benchmark
A specialized benchmarking tool to detect description conflicts and generate test cases for AI agent skills.
Skill Smoke Test Author
An automated utility for generating comprehensive smoke test templates to ensure AI coding agent skills handle edge cases and standard workflows reliably.
METADATA
Featured*
