calibrate_query_mapper
OfficialRefine queries in Q&A pairs with reference text precision.
Authorcas-bigdatalab
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill addresses the challenge of refining questions in Q&A pairs by aligning them with the language style of reference text, ensuring accuracy and consistency.
Core Features & Use Cases
- Query Refinement: Enhances the clarity and detail of questions based on provided reference text.
- LLM Integration: Leverages Large Language Models for advanced question calibration.
- Use Case: Ideal for scenarios where questions need to be recalibrated to match the context or style of existing reference material, such as legal briefs or technical documentation.
Quick Start
Run the calibrate_query_mapper skill with the input file 'questions.json' and output to 'calibrated_questions.json' using the model 'qwen2.5-72b-instruct'.
Dependency Matrix
Required Modules
data_juicer
Components
scripts
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: calibrate_query_mapper Download link: https://github.com/cas-bigdatalab/piflow/archive/main.zip#calibrate-query-mapper Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.