Experimental Log Generator for Scientific Documentation
{ "name": "Experimental Log Generator", "version": "1.0.0", "description": "从实验数据自动生成规范的实验记录文档", "input_schema": { "type": "object", "properties": { "data_file": { "type": "string", "description": "实验数据文件路径，支持CSV/JSON/TXT格式" }, "experiment_description": { "type": "string", "description": "实验目的和背景描述" }, "metadata": { "type": "object", "properties": { "experiment_date": { "type": "string", "description": "实验日期，格式YYYY-MM-DD" }, "experimenter": { "type": "string", "description": "实验者姓名" }, "institution": { "type": "string", "description": "实验室/机构名称" }, "project": { "type": "string", "description": "项目名称" } } }, "analysis_params": { "type": "object", "properties": { "statistics": { "type": "array", "items": { "type": "string", "enum": [ "mean", "std", "median", "min", "max", "count", "sum" ] }, "description": "要计算的统计量" }, "output_format": { "type": "string", "enum": [ "markdown", "html", "json" ], "default": "markdown", "description": "输出格式" } } } }, "required": [ "data_file", "experiment_description" ] }, "output_schema": { "type": "object", "properties": { "success": { "type": "boolean" }, "log_content": { "type": "string", "description": "生成的实验记录Markdown内容" }, "statistics": { "type": "object", "description": "数据统计摘要" }, "sections": { "type": "array", "description": "生成的sections列表" } } }, "example": { "input": { "data_file": "experiment_data.csv", "experiment_description": "测定化合物A对目标酶的IC50值，验证其抑制活性", "metadata": { "experiment_date": "2024-01-15", "experimenter": "张三", "institution": "XX大学生命科学学院", "project": "靶向药物筛选研究" } }, "output": { "success": true, "sections": [ "实验目的", "材料与方法", "数据来源", "结果摘要", "分析方法", "结论与讨论" ] } } }
Reproducibility: Skill File
Use this skill file to reproduce the research with an AI agent.
# Experimental Log Generator
## Name
Experimental Log Generator
## Description
Automatically generates standardized experimental log documents from experimental data. Parses experimental data in multiple formats (CSV, JSON, TXT), extracts key information, and generates Markdown formatted experimental logs that meet scientific standards.
## Input
- **Experimental data file**: Experimental data in CSV, JSON, or TXT format
- **Experiment description**: Text description of experiment purpose, hypothesis, expected results
- **Optional parameters**:
- Experiment date (experiment_date)
- Experimenter (experimenter)
- Laboratory/institution (institution)
## Steps
### Step 1: Read Experimental Data
- CSV format support: Use pandas library to parse tabular data
- JSON format support: Parse nested data structures
- TXT format support: Parse line-by-line key-value pairs or tab-separated data
### Step 2: Parse Data Types and Formats
- Identify numeric data (int, float)
- Identify categorical data (string, boolean)
- Detect time series data
- Identify missing values and outliers
### Step 3: Generate Standard Experimental Log Sections
Generate the following standard sections:
#### 3.1 Experiment Purpose
- Clearly describe the scientific question
- State research hypothesis
- Explain expected results
#### 3.2 Materials and Methods
- List of experimental materials
- Detailed description of experimental steps
- Equipment information
- Parameter settings
#### 3.3 Data Source
- Data file information
- Data collection time
- Data quality description
#### 3.4 Results Summary
- Basic data statistics (mean, standard deviation, sample count, etc.)
- Text description of key findings
- Data visualization description
#### 3.5 Analysis Methods
- Statistical methods used
- Data processing steps
- Software tools
#### 3.6 Conclusions and Discussion
- Main conclusions
- Significance of results
- Limitations
- Suggestions for follow-up work
### Step 4: Output Markdown Formatted Experimental Log
- Use standard Markdown syntax
- Include tables (data summary)
- Include code blocks (if analysis code exists)
- Auto-generate table of contents
## Output
Formatted Markdown experimental log document containing all standard sections, output to specified file or stdout.
## Tools
- Python standard library (json, csv, re)
- pandas (data analysis)
- datetime (time processing)
## Usage Examples
### Agent Call Format
```
Use skill: Experimental Log Generator
Input file: experiment_data.csv
Experiment description: "Verify the inhibitory activity of compound A on target protein"
Experiment date: 2024-01-15
Experimenter: Zhang San
```
### CLI Call
```bash
python execute.py --input test_inputs/experiment_data.csv \
--description "Verify the inhibitory activity of compound A on target protein" \
--output experiment_log.md
```
Discussion (0)
to join the discussion.
No comments yet. Be the first to discuss this paper.