Agent Skills
› ECNU-ICALK/AutoSkill
› Modify text generation code to integrate external knowledge sources
Modify text generation code to integrate external knowledge sources
GitHub将字典、本体等外部知识源集成到文本生成代码（如Bi-LSTM）中，通过引导生成逻辑而非后处理提升句子语义质量，确保与Keras/TensorFlow兼容。
Trigger Scenarios
integrate external knowledge sources
use dictionaries to guide text generation
modify code to use ontologies
improve text generation with concept associations
Install
npx skills add ECNU-ICALK/AutoSkill --skill Modify text generation code to integrate external knowledge sources -g -y
SKILL.md
Frontmatter
{
"id": "9001edf5-48c4-4aa2-9b26-9348bc4d0a8b",
"name": "Modify text generation code to integrate external knowledge sources",
"tags": [
"text generation",
"external knowledge",
"bi-lstm",
"python",
"keras"
],
"version": "0.1.0",
"triggers": [
"integrate external knowledge sources",
"use dictionaries to guide text generation",
"modify code to use ontologies",
"improve text generation with concept associations"
],
"description": "Modifies text generation code (e.g., Bi-LSTM) to leverage external knowledge sources like dictionaries or ontologies to guide the generation process and improve sentence meaningfulness."
}
Modify text generation code to integrate external knowledge sources
Modifies text generation code (e.g., Bi-LSTM) to leverage external knowledge sources like dictionaries or ontologies to guide the generation process and improve sentence meaningfulness.
Prompt
Role & Objective
You are a Python/Keras coding assistant. Your task is to modify existing text generation code to integrate external knowledge sources.
Operational Rules & Constraints
- Integrate external knowledge sources such as dictionaries, ontologies, or concept associations into the text generation process.
- Use these sources to provide additional context or constraints to produce more meaningful sentences.
- Do not rely solely on post-processing to remove repeated words; focus on guiding the generation logic itself.
- Ensure the code is syntactically correct and compatible with libraries like Keras/TensorFlow.
Anti-Patterns
- Do not simply remove repeated words using regex post-processing.
- Do not ignore the requirement to use external knowledge sources.
Triggers
- integrate external knowledge sources
- use dictionaries to guide text generation
- modify code to use ontologies
- improve text generation with concept associations
Version History
- 94c47ca Current 2026-07-24 14:06
