A structural protocol for AI agents to organize code into modular subskills and centralized data directories.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install subskill-generation-rule
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 subskill-generation-rule 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 Subskill Generation Rule?
The Subskill Generation Rule provides a standardized framework for managing the lifecycle and organization of AI-generated assets. By enforcing a strict directory hierarchy, it ensures that functional code, documentation, and data artifacts remain isolated and discoverable. This approach is essential for developers building complex Openclaw Skills that require modularity and long-term maintainability.
This rule prevents the common issue of root-level clutter in AI projects. It mandates that any new logic be encapsulated within a feature-specific subfolder, while generated recommendations or temporary results are kept within a dedicated data store. This separation of concerns allows both human developers and AI agents to navigate the codebase with high precision.
Subskill Generation Rule Use Cases
- Creating modular subskills for complex AI agent tasks.
- Organizing feature-specific scripts to avoid root directory pollution.
- Enforcing standardized file placement across collaborative development teams.
- Documenting specific sub-features using localized SKILL.md files.
- Scaling Openclaw Skills architectures without losing project clarity.
How Subskill Generation Rule Works
- The AI agent evaluates the task to determine if it requires a new feature or data artifact.
- All generated results or recommendation outputs are automatically routed to the data/ directory.
- New functional scripts are placed in a dedicated subfolder within subskills/
/. - A local SKILL.md file is created inside the feature folder if specific usage instructions are needed.
- The system verifies the structure to ensure no one-off scripts remain in the main skill root.
Subskill Generation Rule Setup
To apply these organization rules to your Openclaw Skills, structure your project directory according to the following layout:
mkdir -p data subskills
touch SKILL.md config.json
Ensure your agent's system prompt or root SKILL.md references these placement conventions to maintain consistency during automated code generation.
Subskill Generation Rule Data Schema & Taxonomy
The rule organizes project data using a hierarchical taxonomy to ensure clear separation between logic and output.
| Directory | Content Type | Description |
|---|---|---|
data/ |
Artifacts | Stores generated recommendations, results, and logs. |
subskills/ |
Feature Logic | Parent directory for all modular functional scripts. |
subskills/<feature>/ |
Module Root | Contains the code (e.g., .py) and local SKILL.md for a specific feature. |
config.json |
Configuration | Global settings for the skill and its subskills. |
Subskill Generation Rule Advanced Features
- Modular documentation support via nested SKILL.md files for every sub-feature.
- Scalable architecture that supports unlimited feature expansion within the subskills directory.
- Automated cleanup of one-off scripts by enforcing strict directory-only placement rules.
- Enhanced compatibility with multi-agent systems using Openclaw Skills by providing predictable file paths.
SKILL.md
Loading
Related Openclaw Skills
A-Share Short-Term Decision
A data-driven decision engine for CN A-share momentum trading with a 1-5 day horizon.
ModelReady
Instantly transform local or Hugging Face models into OpenAI-compatible endpoints for direct chat interaction within your agent environment.
Weekly Skills Update
An automated maintenance skill that updates all agent capabilities and generates comprehensive versioning reports.
Sales Oratory Master
An AI-powered negotiation assistant designed to handle B2B sales objections through strategic value-shifting and diagnostic communication.
Weather in China (weather-zh)
A zero-token Python script for retrieving real-time weather data and lifestyle indices for Chinese cities directly from official sources.
Instagram Saver
An automated downloader that extracts high-resolution images and videos from Instagram posts using the Cobalt API.
Featured*
