ZJUNLP
Official@zjunlp · China
Knowledge Engine Lab: A NLP & KG Group of Zhejiang University
Agent Skills by ZJUNLP
Showing 141 vetted skills indexed across 2 GitHub repositories.
zjunlpTotal_Fees_Calculation
Compute total payment processing fees from dabstep transaction data and fee rules.
zjunlpRouting_and_Cost_Optimization
Identifies card scheme or ACI with minimum/maximum fees for payment routing.
zjunlpApplicable_Fee_IDs
Determine applicable fee IDs from merchant transaction data and fee rules.
zjunlpHighest_Cost_Scenario_Identification
Identify the most expensive MCC or ACI for a transaction using predefined fee rules.
zjunlpFraud_and_General_Macro_Analysis
Analyze fraud rates and transaction distributions on the dabstep payment dataset.
zjunlpAverage_Fee_Estimation
Calculate average card scheme transaction fees by scheme, credit type, and MCC.
zjunlpAverage_Transaction_Value_Stats
Compute average transaction value statistics from payment data with optional filters.
zjunlpFee_Delta_and_Impact_Simulation
Calculates fee deltas for merchant payment scenarios with rate and MCC changes.
zjunlpDataset_Metadata_and_Business_Rules
Analyze payment processing dataset structure, metadata, and business rules.
zjunlpdabstep-fraud-general-macro-analysis
Analyze macro-level fraud rates and statistics on the dabstep payment dataset using Python.
zjunlpdabstep-dataset-metadata-business-rules
Interpret metadata and business rules in the dabstep payment processing dataset.
zjunlpskill-creator
Guide creating Claude skills with Python scripts and structured resources.
zjunlpcsv-analysis
Automates CSV data analysis including grouping, aggregates charts and Markdown reports using Python.
zjunlpmimic-patient-analysis
Query MIMIC-IV SQLite tables to generate structured patient analysis reports.
zjunlpsec-10k-company-analysis
Extract and analyze financial metrics from SEC 10-K filings in SQLite databases.
zjunlpglobem-user-analysis
Analyze individual user behavior and mental health from GLOBEM smartphone sensor data.
zjunlpddr-globem-analysis
Analyze GLOBEM participant data and generate QA pairs on mental health changes.
zjunlpmimic-iv-patient-analysis
Analyze MIMIC-IV patient records and generate clinical QA pairs.
zjunlplongds-bench
Evaluate agent multi-turn data analysis skills using the LongDS-Bench benchmark.
zjunlpalfworld-open-receptacle
Open closed receptacles in the ALFWorld environment using precise identifiers.
zjunlpalfworld-receptacle-preparer
Navigate to and open target receptacles in ALFWorld environments.
zjunlpalfworld-receptacle-closer
Close open receptacles after inspection to maintain environment tidiness.
zjunlpalfworld-object-picker
Take a specified object from a receptacle into agent inventory.
zjunlpalfworld-object-retriever
Retrieve a visually confirmed object from a receptacle in ALFWorld.
Frequently Asked Questions About ZJUNLP
FAQPage SchemaWhat specific tasks can I perform using ZJUNLP's simulated environment skills?▼
You can execute complex object manipulation tasks, including locating, heating, cooling, cleaning, and storing items within ALFWorld and ScienceWorld environments, as well as conducting scientific experiments like circuit building and substance mixing.
Which personas benefit most from these technical capabilities?▼
Researchers and developers focused on embodied cognition, decision-making benchmarks, and multi-turn data analysis will find these capabilities most relevant for testing and refining complex reasoning systems.
What are the primary data dependencies for the financial and clinical analysis skills?▼
These skills require structured datasets, specifically SQLite databases containing MIMIC-IV patient records or SEC 10-K financial filings, to perform metric extraction and report generation.