An AI agent skill for searching official Jingyi Module commands and generating runnable E-Language code snippets within Openclaw Skills.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install jingyi-module
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 jingyi-module 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 Jingyi Module Skill?
The Jingyi Module Skill is a dedicated technical resource designed to assist developers working with E-Language (易语言). It facilitates seamless interaction with the popular Jingyi Module by providing a bridge between official documentation and the development environment. By leveraging Openclaw Skills, this tool allows users to query specific command details, understand parameter structures, and verify return types without manual searching.
The primary focus of this skill is high-fidelity retrieval followed by precise code generation. It ensures that developers have access to the technical truth of the module's API, preventing the common issue of AI-generated hallucinations in niche programming languages. Whether you are a beginner or an expert, using this skill within Openclaw Skills ensures your automation and software development workflows remain accurate and efficient.
Jingyi Module Skill Use Cases
- Searching for the correct Jingyi Module command based on functional requirements.
- Retrieving official parameters, return values, and technical remarks for specific functions.
- Generating copy-pasteable E-Language code blocks (version 2) for immediate execution.
- Verifying the correct usage of commands like random character generation or time manipulation within Openclaw Skills.
How Jingyi Module Skill Works
- The skill identifies the user's intent to use a Jingyi Module function.
- It executes a Python-based search script to find the top matching commands from the local index.
- The agent fetches the comprehensive official documentation JSON for the chosen command ID or name.
- It validates the command signature and behavior against the retrieved metadata.
- The skill generates a concise explanation and a formatted E-Language code block for the user.
Jingyi Module Skill Setup
To enable this skill within your Openclaw Skills environment, ensure you have Python installed. The skill relies on internal scripts located in the base directory.
# Verify your Python environment
python --version
# The skill automatically invokes the following search mechanism
python "scripts/search_jingyi.py" "search_term" --top 8
# Official documentation is fetched via
python "scripts/fetch_jingyi_doc.py" --id [command_id]
Jingyi Module Skill Data Schema & Taxonomy
The skill utilizes a structured data model to ensure accuracy. Below is the metadata schema used for command retrieval:
| Attribute | Description |
|---|---|
| id | The unique identifier from the official Jingyi database |
| name | The Chinese name of the command as used in E-Language |
| canonical_path | The full namespace path of the function |
| cmdtype | The classification of the command (e.g., text, time, system) |
| score | The search relevance score for the query |
| summary | A brief functional description of the command |
Jingyi Module Skill Advanced Features
- Retrieval-Augmented Generation (RAG) workflow that prioritizes official documentation over model weights.
- Built-in data patching for known empty official documentation nodes like Time_GetMonthEnd and Text_GetRandomHanzi.
- Support for specific E-Language versioning (version 2) in all code output.
- Intelligent ranking of search results to find the most relevant API calls within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
DaoReview: AI Document Auditor & Scorer
An intelligent document auditor that analyzes, scores, and provides actionable feedback on text-based files across multiple quality dimensions.
Self-Improving Agent (Proactive Self-Reflection)
A proactive self-reflection and memory management skill that enables AI agents to learn from corrections and improve performance permanently.
SDD Requirements Normalizer
A professional tool that converts fragmented product ideas into structured, high-fidelity requirement documents optimized for Spec Driven Development (SDD).
Hotels Near Attraction (flyai-hotel-near-attraction)
A location-focused travel skill that finds the closest hotels to specific landmarks with real-time distance sorting and integrated attraction data.
EmmeStudio Brand Identity
An AI agent skill that automatically applies the EmmeStudio visual and textual brand identity to all professional outputs.
Sherpa ONNX Local TTS
A high-performance, private text-to-speech engine that runs entirely offline using the sherpa-onnx runtime and Piper voice models.
Featured*
