A specialized CLI tool for batch extracting specific text segments from image filenames based on customizable delimiters and positions.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install extract-pic-text
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install extract-pic-text using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Extract Pic Text?
The extract-pic-text skill is a robust utility designed to automate the harvesting of metadata from standardized image naming conventions. As a vital component of the Openclaw Skills library, it allows developers and data managers to programmatically isolate critical information like SKUs, unique IDs, or timestamps that are embedded directly within file names.
This tool is particularly valuable for workflows involving large volumes of media where manual data entry is impractical. By leveraging Python-based logic, it scans directories, parses strings based on user-defined delimiters, and provides clean, actionable output for database synchronization or file organization tasks.
Extract Pic Text Use Cases
- Extracting SKU numbers from e-commerce product photos (e.g., SKU_12345_v1.jpg).
- Harvesting specific event dates from organized photo archives (e.g., 2024_03_07_conference.png).
- Generating unique ID lists for database verification and inventory management.
- Automating metadata extraction for batch renaming or file migration workflows.
How Extract Pic Text Works
- The tool scans a target directory for files matching supported image extensions (JPG, PNG, WebP, etc.).
- It splits each filename into segments using a specified delimiter, such as an underscore or hyphen.
- The script identifies and isolates the text segment located at the user-defined index position.
- Optional processing steps like alphabetical sorting and duplicate removal are applied to the gathered data.
- The final extracted list is either printed to the console (stdout) or written to a designated output file.
Extract Pic Text Setup
The extract-pic-text skill requires Python 3. To get started, navigate to the skill directory and execute the script via the command line:
# Basic extraction using default settings (underscore delimiter, position 1)
python3 scripts/extract_pic_text.py /path/to/your/images
# Advanced extraction with custom delimiter and sorting
python3 scripts/extract_pic_text.py /path/to/images -d '-' -p 0 --sort --unique -o results.txt
Extract Pic Text Data Schema & Taxonomy
The skill utilizes a set of parameters to define its extraction logic. Below is the configuration schema:
| Parameter | Shortcut | Description | Default Value |
|---|---|---|---|
directory |
N/A | Path to the image folder | Required |
--delimiter |
-d |
Character splitting the filename | _ |
--position |
-p |
0-based index of text to extract | 1 |
--extensions |
-e |
List of targeted image formats | .jpg, .png, .webp, etc. |
--output |
-o |
File path for saved results | stdout |
--sort |
N/A | Sort results alphabetically | False |
--unique |
N/A | Remove duplicate entries | False |
Extract Pic Text Advanced Features
- Support for a wide range of image formats including TIFF, BMP, and WebP.
- Customizable extraction positions allowing for flexible parsing of complex naming structures.
- Integrated data cleaning features including automated sorting and unique value filtering.
- Clear error reporting for files that do not meet the specified naming criteria, ensuring high data integrity within Openclaw Skills workflows.
SKILL.md
Loading
Related Openclaw Skills
clawctl
A centralized coordination layer for managing tasks, messaging, and activity feeds across autonomous agent fleets.
Stock Analysis Agent Skill
A high-performance AI agent skill for technical stock analysis, trend prediction, and automated market reporting.
Video to Text
A versatile command-line tool for downloading and transcribing videos from major platforms or local files into high-quality text.
Office to Markdown Converter
A high-performance utility to convert PDF, DOC, DOCX, and PPTX documents into structured Markdown for AI agents.
Contract Review
An AI-powered legal analysis tool that reviews contracts for risks, extracts key terms, and suggests redlines based on market standards.
Humanizer
A specialized writing editor that identifies and strips away 24 common AI writing patterns to make text sound authentically human.
Featured*
