data-extractor
Extract numerical data from scientific figure images using Claude vision + OpenCV calibration. Supports 26+ plot types including bar charts, scatter plots, forest plots, Kaplan-Meier curves, box plots, and more.
Best use case
data-extractor is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Extract numerical data from scientific figure images using Claude vision + OpenCV calibration. Supports 26+ plot types including bar charts, scatter plots, forest plots, Kaplan-Meier curves, box plots, and more.
Teams using data-extractor should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/data-extractor/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How data-extractor Compares
| Feature / Agent | data-extractor | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Extract numerical data from scientific figure images using Claude vision + OpenCV calibration. Supports 26+ plot types including bar charts, scatter plots, forest plots, Kaplan-Meier curves, box plots, and more.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# 📊 Data Extractor
You are the **Data Extractor**, a ClawBio skill for digitizing scientific figures. Your role is to extract numerical data from plot images for meta-analyses and systematic reviews.
## When to Use This Skill
Route to this skill when the user:
- Provides an image file (PNG, JPG, TIFF) containing a scientific figure
- Asks to "extract data from a figure", "digitize a plot", "read values from a chart"
- Mentions "meta-analysis data extraction" or "figure digitization"
- Wants to convert a bar chart, scatter plot, or other figure to CSV/JSON
## Capabilities
### Supported Plot Types (26)
scatter, bar, line, box, violin, histogram, heatmap, forest, kaplan_meier,
dot_strip, stacked_bar, funnel, roc, volcano, waterfall, bland_altman,
paired, bubble, area, dose_response, manhattan, correlation_matrix,
error_bar, table, other
### Pipeline (4 phases)
1. **Panel Detection** — Identify sub-panels in multi-panel figures (Claude vision)
2. **Pre-Analysis** — Identify axes, scale (linear/log), legend entries, error bars (Claude tool calling)
3. **CV Calibration + Extraction** — OpenCV detects markers/bars at pixel level, Claude extracts numerical data with calibration context
4. **Validation** — Heuristic checks for axis range, series count, error bar polarity
### Output Formats
- **CSV** — One row per data point with series name, x/y values, error bars
- **JSON** — Structured ExtractedData objects with full metadata
- **Web UI** — Interactive table + SVG preview with editable cells
## Usage
### CLI
```bash
python data_extractor.py --image figure.png --output results/
python data_extractor.py --web --port 8765
python data_extractor.py --demo
```
### API (importable)
```python
from api import run
result = run(options={"image_path": "figure.png", "output_dir": "results/"})
```
### Web UI
Launch with `--web` flag. Upload images, draw boxes around plots, extract and edit data interactively.
## Input Formats
- PNG, JPG, JPEG, TIFF image files
- Screenshots from papers, posters, slides
- Multi-panel composite figures (auto-detected and split)
## Notes
- Requires ANTHROPIC_API_KEY environment variable
- Uses Claude Sonnet for pre-analysis/detection, Claude Opus for extraction
- OpenCV calibration improves accuracy for scatter/bar plots with clear markers
- Error bars are reported as ± extent (delta from mean), not absolute positionsRelated Skills
College Football Data (CFB)
Before writing queries, consult `references/api-reference.md` for endpoints, conference IDs, team IDs, and data shapes.
College Basketball Data (CBB)
Before writing queries, consult `references/api-reference.md` for endpoints, conference IDs, team IDs, and data shapes.
validating-database-integrity
Process use when you need to ensure database integrity through comprehensive data validation. This skill validates data types, ranges, formats, referential integrity, and business rules. Trigger with phrases like "validate database data", "implement data validation rules", "enforce data integrity constraints", or "validate data formats".
forecasting-time-series-data
This skill enables Claude to forecast future values based on historical time series data. It analyzes time-dependent data to identify trends, seasonality, and other patterns. Use this skill when the user asks to predict future values of a time series, analyze trends in data over time, or requires insights into time-dependent data. Trigger terms include "forecast," "predict," "time series analysis," "future values," and requests involving temporal data.
generating-test-data
This skill enables Claude to generate realistic test data for software development. It uses the test-data-generator plugin to create users, products, orders, and custom schemas for comprehensive testing. Use this skill when you need to populate databases, simulate user behavior, or create fixtures for automated tests. Trigger phrases include "generate test data", "create fake users", "populate database", "generate product data", "create test orders", or "generate data based on schema". This skill is especially useful for populating testing environments or creating sample data for demonstrations.
test-data-builder
Test Data Builder - Auto-activating skill for Test Automation. Triggers on: test data builder, test data builder Part of the Test Automation skill category.
splitting-datasets
Process split datasets into training, validation, and testing sets for ML model development. Use when requesting "split dataset", "train-test split", or "data partitioning". Trigger with relevant phrases based on skill purpose.
scanning-database-security
Process use when you need to work with security and compliance. This skill provides security scanning and vulnerability detection with comprehensive guidance and automation. Trigger with phrases like "scan for vulnerabilities", "implement security controls", or "audit security".
preprocessing-data-with-automated-pipelines
Process automate data cleaning, transformation, and validation for ML tasks. Use when requesting "preprocess data", "clean data", "ETL pipeline", or "data transformation". Trigger with relevant phrases based on skill purpose.
optimizing-database-connection-pooling
Process use when you need to work with connection management. This skill provides connection pooling and management with comprehensive guidance and automation. Trigger with phrases like "manage connections", "configure pooling", or "optimize connection usage".
modeling-nosql-data
This skill enables Claude to design NoSQL data models. It activates when the user requests assistance with NoSQL database design, including schema creation, data modeling for MongoDB or DynamoDB, or defining document structures. Use this skill when the user mentions "NoSQL data model", "design MongoDB schema", "create DynamoDB table", or similar phrases related to NoSQL database architecture. It assists in understanding NoSQL modeling principles like embedding vs. referencing, access pattern optimization, and sharding key selection.
monitoring-database-transactions
Monitor use when you need to work with monitoring and observability. This skill provides health monitoring and alerting with comprehensive guidance and automation. Trigger with phrases like "monitor system health", "set up alerts", or "track metrics".